Artificial intelligence system and method for predicting traffic accident occurrence place

文档序号：1145920 发布日期：2020-09-11 浏览：4次中文

阅读说明：本技术 预测交通事故发生地的人工智能系统和方法 (Artificial intelligence system and method for predicting traffic accident occurrence place ) 是由杨瑞飞于 2018-09-18 设计创作，主要内容包括：提供了用于预测交通事故地点的系统和方法。一种方法包括：获取多个交通事故的多个事故记录,所述多个事故记录中的每一个事故记录与相应的目标用户终端相关联,并且包括多个位置；确定多个精确事故地点,对于多个事故记录中的每一个,通过,运行第一聚类过程,将所述目标用户终端对应的多个位置作为所述第一聚类过程的输入,以及将所述第一聚类过程的第一结果作为所述目标用户终端的多个位置的精确事故地点；通过操作第二聚类过程来确定至少一个事故多发地段,所述多个事故记录对应的所述多个精确事故地点作为所述第二聚类过程的输入。(Systems and methods for predicting a location of a traffic accident are provided. One method comprises the following steps: obtaining a plurality of incident records for a plurality of traffic incidents, each incident record of the plurality of incident records being associated with a respective target user terminal and comprising a plurality of locations; determining a plurality of accurate accident locations, for each of a plurality of accident records, by running a first clustering process, taking a plurality of positions corresponding to the target user terminal as an input of the first clustering process, and taking a first result of the first clustering process as an accurate accident location of the plurality of positions of the target user terminal; determining at least one accident-prone location by operating a second clustering process, the plurality of precise accident locations to which the plurality of accident records correspond as inputs to the second clustering process.)

1. A system, comprising one or more electronic devices, for predicting a location of a traffic accident, comprising:

at least one storage medium including a first operating system and a set of instructions compatible with the first operating system for providing a accident-prone location to at least one information receiving terminal; and

at least one processor in communication with the storage medium, wherein the at least one processor, when executing the first operating system and the set of instructions, is configured to:

obtaining a plurality of incident records for a plurality of traffic incidents, each incident record of the plurality of incident records being associated with a respective target user terminal and comprising a recorded incident time and a plurality of locations for a traffic incident, the plurality of locations being locations at which the target user terminal occurs before and after the recorded incident time;

a plurality of precise incident locations are determined, and for each of the plurality of incident records, a plurality of accident records are generated, by,

running a first clustering process, taking a plurality of positions corresponding to the target user terminal as input of the first clustering process, and taking a first result of the first clustering process as an accurate accident site of the plurality of positions of the target user terminal;

in response to determining the plurality of precise accident locations, determining at least one accident-prone location by operating a second clustering process, the plurality of precise accident locations to which the plurality of accident records correspond as inputs to the second clustering process;

in response to determining the at least one incident-prone location, generating an electronic signal comprising information of the at least one incident-prone location; and

and instructing the information receiving terminal to display an interface presenting the at least one accident multi-occurrence section by transmitting the electronic signal to the information receiving terminal.

2. The system 1 of, wherein running a first clustering process, the at least one processor is configured to:

identifying a plurality of points corresponding to the input;

determining a result cluster and a result point associated with the result cluster by a point identification operation, comprising:

selecting a candidate cluster of a point from the plurality of points;

selecting a candidate point from the candidate cluster of points;

executing a first iterative operation until a first stop condition is satisfied, wherein the first iterative operation includes a plurality of first iterations, and each of the first iterations includes:

a target cluster using the candidate point as a center point and using a candidate cluster of the point as one point;

identifying one cluster within a preset distance from the central point from the target clusters of the points as a candidate cluster of the points; and

a point is identified from the candidate cluster of points as a candidate point.

3. The system of claim 2, wherein in each first iteration, the candidate points in the first iteration are related to the average coordinates of the points in the corresponding candidate cluster in the first iteration.

4. The system 2, wherein the at least one processor is further configured to:

when the candidate cluster of points determined in the last first iteration of the first iterative operation meets the first stop condition,

obtaining a candidate cluster of points corresponding to the last first iteration as a result cluster of the first iteration operation; and

and acquiring a candidate point corresponding to the last first iteration as a result point of the first iteration operation.

5. The system 4 of claim, wherein the at least one processor is further configured to output a result point of the first iterative operation as a first result of the first clustering process.

6. The system 4 of claim, wherein the result point is one of a plurality of result points and the result cluster is one of a plurality of result clusters; and

the at least one processor is further configured to execute a second iterative operation based on an output of the first iterative operation, obtain a plurality of subsequent result points and a plurality of subsequent result clusters by executing the second iterative operation until a second stop condition is satisfied, wherein the second iterative operation includes a plurality of second iterations, and each second iteration includes:

updating the plurality of points by removing from the plurality of points a result cluster of locations identified in a last iteration of the second iterative operation;

determining a subsequent cluster of results and a subsequent point of results based on the updated plurality of points by performing the point identification operation.

7. The system 6, wherein the at least one processor is further configured to:

for each of the plurality of clusters of results,

determining a stop time based on the number of points in the result cluster;

determining whether a stop time associated with the result cluster is greater than a time threshold; and

and responding to the stopping time being larger than the time threshold value, and allocating the result point corresponding to the result cluster as the accurate accident site.

8. The system 1 of, wherein the second clustering process comprises a first clustering process; and

determining the at least one incident multi-occurrence segment, the processor further to:

acquiring the plurality of precise accident sites;

determining a plurality of result clusters by running a second clustering process, the plurality of precise accident sites as inputs to the second clustering process; and

for each of the plurality of result clusters, assigning a road segment associated with the result cluster as an accident-prone segment.

9. The system 8, wherein the at least one processor is further configured to:

for each of the plurality of result clusters,

determining a number of points in a result cluster;

determining whether the number is greater than a density threshold; and

in response to the number being greater than the density threshold, determining a road segment associated with the result cluster based on a point in the result cluster.

10. The system 1, wherein a plurality of incident records are obtained, and wherein the at least one processor is further configured to:

receiving a plurality of incident reports, each of the plurality of incident reports being associated with a respective target user terminal and including a recorded incident time and a recorded incident location;

acquiring a plurality of historical positions of the target user terminal;

for each incident report of a plurality of incident reports, merging a respective recorded incident time and recorded incident location with a historical location of the corresponding target user terminal to obtain an incident record associated with the corresponding target user terminal.

11. The system 10 of, wherein each of the plurality of incident reports includes at least one of:

an accident report of a user report of the target user terminal;

accident reports reported by insurance companies; or

Accident reporting by traffic police.

12. A method of predicting a location of a traffic accident, the method being implemented on one or more electronic devices having at least one storage medium and at least one processor in communication with the at least one storage medium, the method comprising:

a plurality of precise incident locations are determined, and for each of the plurality of incident records, a plurality of accident records are generated, by,

in response to determining the plurality of precise accident locations, determining at least one accident-prone location by operating a second clustering process, a plurality of precise accident locations corresponding to the plurality of accident records as inputs to the second clustering process;

in response to determining the at least one incident-multiple location, generating an electronic signal comprising information of the at least one incident-multiple location; and

13. The method 12, wherein operating the first clustering process input comprises:

identifying a plurality of points corresponding to the input;

determining a result cluster and a result point associated with the result cluster by a point identification operation, comprising:

selecting a candidate cluster of a point from the plurality of points;

selecting a candidate point from the candidate cluster of points;

a target cluster using the candidate point as a center point and using a candidate cluster of the point as one point;

identifying one cluster within a preset distance from the central point from the target clusters of the points as a candidate cluster of the points; and

a point is identified from the candidate cluster of points as a candidate point.

14. The method of claim 13, wherein in each of the first iterations, the candidate points in the first iteration are related to average coordinates of corresponding candidate cluster points in the first iteration.

15. The method of claim 13, further comprising:

when the candidate cluster of points determined in the last first iteration of the first iterative operation meets the first stop condition,

obtaining a candidate cluster of points corresponding to the last first iteration as a result cluster of the first iteration operation; and

and acquiring a candidate point corresponding to the last first iteration as a result point of the first iteration operation.

16. The method of claim 15, further comprising outputting a result point of the first iterative operation as a first result of the first clustering process.

17. The method of claim 15, wherein the result point is one of a plurality of result points and the result cluster is one of a plurality of result clusters; and the method further comprises:

obtaining a plurality of subsequent result points and a plurality of subsequent result clusters by executing a second iterative operation until a second stop condition is satisfied based on an output of the first iterative operation, wherein the second iterative operation includes a plurality of second iterations, and each of the second iterations includes:

updating the plurality of points by removing from the plurality of points a result cluster of locations identified in a last iteration of the second iterative operation;

determining a subsequent cluster of results and a subsequent point of results based on the updated plurality of points by performing the point identification operation.

18. The method of claim 17, further comprising:

for each of the plurality of clusters of results,

determining a stop time based on the number of points in the result cluster;

determining whether a stop time associated with the result cluster is greater than a time threshold; and

and in response to the stopping time being larger than the time threshold, taking a result point corresponding to the result cluster as the accurate accident site.

19. The method 12 of, wherein the second clustering process comprises a first clustering process; and

determining the at least one incident multi-occurrence segment comprises:

acquiring the plurality of precise accident sites;

determining a plurality of result clusters by running a second clustering process, the plurality of precise accident sites as inputs to the second clustering process; and

for each of the plurality of result clusters, assigning a road segment associated with the result cluster as an accident-prone segment.

20. The method of claim 19, further comprising:

for each of the plurality of clusters of results,

determining a number of points in the result cluster;

determining whether the number is greater than a density threshold; and

in response to the number being greater than a density threshold, determining a road segment associated with the result cluster based on a point in the result cluster.

21. The method 12, wherein obtaining the plurality of incident records comprises:

acquiring historical positions of the target user terminals;

for each incident report of the plurality of incident reports, merging the respective recorded incident time and recorded incident location with the historical location of the corresponding target user terminal to obtain an incident record associated with the corresponding target user terminal.

22. The method of claim 21, wherein each of the plurality of incident reports comprises at least one of:

an accident report of a user report of the target user terminal;

accident reports reported by insurance companies; or

Accident reporting for traffic police reporting.

23. A non-transitory computer readable medium comprising an operating system and at least one set of instructions compatible with the operating system for predicting a traffic accident site, wherein when the instructions are executed by at least one processor of one or more electronic devices, the at least one set of instructions cause the at least one processor to:

a plurality of precise incident locations are determined, and for each of the plurality of incident records, a plurality of accident records are generated, by,

in response to determining the plurality of precise accident locations, at least one accident-prone segment is determined by operating a second clustering process, the plurality of precise accident locations to which the plurality of accident records correspond as inputs to the second clustering process.

In response to determining the at least one incident-prone location, generating an electronic signal comprising data of the at least one incident-prone location; and

24. A system for predicting a location of a traffic accident, comprising:

a record acquisition module configured to acquire a plurality of incident records for a plurality of traffic incidents, each of the plurality of incident records being associated with a corresponding target user terminal and comprising an incident time for a record of a traffic incident and a plurality of locations, the plurality of locations being locations at which the target user terminal appears before and after the recorded incident time;

an incident location determination module configured to determine a plurality of precise incident locations and, for each of the plurality of incident records, by,

a segment determination module configured to determine at least one accident-prone segment by operating a second clustering process in response to determining the plurality of precise accident locations, a plurality of precise accident locations corresponding to the plurality of accident records as inputs to the second clustering process;

an information transmitting module configured to transmit the information of the at least one accident-prone location to an information receiving terminal.

25. An artificial intelligence system, comprising one or more electronic devices, for predicting a location of a traffic accident, comprising:

at least one information receiving port of the information providing system for receiving a plurality of incident records for a plurality of traffic incidents, each of the plurality of incident records,

associated with a corresponding target user terminal, an

Including a recorded accident time of the traffic accident and a plurality of locations of the target user terminal occurring before and after the recorded accident time, wherein the plurality of locations are acquired from at least one GPS system of the information providing system via a network;

at least one information sending port of an information receiving system sends a signal to at least one information receiving terminal, wherein the at least one information receiving terminal runs an application installed therein in response to the signal;

at least one storage medium including a first operating system and a set of instructions compatible with the first operating system for providing the at least one information receiving terminal with a accident-prone location; and

at least one processor in communication with the storage medium, wherein the at least one processor, when executing the first operating system and the set of instructions, is configured to:

obtaining a plurality of incident records received from the at least one information receiving port;

a plurality of precise incident locations are determined, and for each of the plurality of incident records, a plurality of accident records are generated, by,

in response to determining the at least one incident multi-occurrence segment, generating an electronic signal comprising information for one of the at least one incident multi-occurrence segment and a trigger code, wherein the trigger code:

is a format recognizable by the application installed in the information receiving terminal; and also

Configured to cause the application to present the at least one incident multi-occurrence segment on an interface of the information receiving terminal; and

and instructing the information receiving terminal to display an interface by sending the electronic signal to the information sending port so as to present the accident-prone area.

26. The system 25 of, wherein operating said first clustering process, said at least one processor is configured to:

identifying a plurality of points corresponding to the input;

determining a result cluster and a result point associated with the result cluster by a point identification operation, comprising:

selecting a candidate cluster of a point from the plurality of points;

selecting a candidate point from the candidate cluster of points;

operating a first iterative operation until a first stop condition is satisfied, wherein the first iterative operation includes a plurality of first iterations, and each of the first iterations includes:

a target cluster using the candidate point as a center point and using a candidate cluster of the point as one point;

identifying one cluster within a preset distance from the central point from the target clusters of the points as a candidate cluster of the points; and

a point is identified from the candidate cluster of points as a candidate point.

27. The system of claim 26, wherein in each of the first iterations, the candidate points in the first iteration are associated with average coordinates of corresponding candidate cluster points in the first iteration.

28. The system 26 of claim, wherein the at least one processor is further configured to:

when the candidate cluster of points determined in the last first iteration of the first iterative operation meets a first stop condition,

obtaining a candidate cluster of points corresponding to the last first iteration as a result cluster of the first iteration operation;

and acquiring a candidate point corresponding to the last first iteration as a result point of the first iteration operation.

29. The system 28 of, wherein the at least one processor is further configured to output a result point of the first iterative operation as a first result of the first clustering process input.

30. The system of claim 28, wherein the result point is one of a plurality of result points and the result cluster is one of a plurality of result clusters; and is

The at least one processor is further configured to execute a second iterative operation based on an output of the first iterative operation, obtain a plurality of subsequent result points and a plurality of subsequent result clusters by executing the second iterative operation until a second stop condition is satisfied, wherein the second iterative operation includes a plurality of second iterations, and each second iteration includes:

updating the plurality of points by removing from the plurality of points a result cluster of locations identified in a last iteration of the second iterative operation;

determining a subsequent cluster of results and a subsequent point of results based on the updated plurality of points by performing the point identification operation.

31. The system 30, wherein the at least one processor is further configured to:

for each of the plurality of clusters of results,

determining a stop time based on the number of points in the result cluster;

determining whether a stop time associated with the candidate cluster is greater than a time threshold; and responding to the stopping time being larger than the time threshold value, and distributing the result point corresponding to the candidate result cluster as the accurate accident site.

32. The system 25 of, wherein said second clustering process comprises a first clustering process; and

determining the at least one incident multi-occurrence segment, the processor further to:

acquiring the plurality of precise accident sites;

operating the second clustering process by taking the plurality of precise accident sites as input to the second clustering process to determine a plurality of result clusters; and

for each of the plurality of result clusters, a road segment responsive to the result cluster is assigned as an accident-prone segment.

33. The system 32, wherein the at least one processor is further configured to:

for each of the plurality of clusters of results,

determining a number of points in the result cluster;

determining whether the number is greater than a density threshold; and

in response to the number being greater than the density threshold, determining a road segment associated with the result cluster based on a point in the result cluster.

34. The system 25, wherein the plurality of incident records are obtained, and wherein the at least one processor is further configured to:

acquiring a plurality of historical positions of the target user terminal;

35. The system 34 of claim, wherein each of the plurality of incident reports includes at least one of:

an accident report of a user report of the target user terminal;

accident reports reported by insurance companies; or

Accident reporting by traffic police.

36. A method for predicting a location of a traffic accident, the method being implemented on one or more electronic devices having at least one information receiving port of an information providing system, at least one information transmitting port of an information receiving system, at least one storage medium, and at least one processor in communication with the storage medium, the method comprising:

obtaining a plurality of incident records for a plurality of traffic incidents from the at least one information receiving port, each incident record of the plurality of incident records being associated with a corresponding target user terminal and comprising an incident time for a record of a traffic incident and a plurality of locations, the plurality of locations being locations at which the target user terminal appears before and after the recorded incident time;

a plurality of precise incident locations are determined, and for each of the plurality of incident records, a plurality of accident records are generated, by,

is a format recognizable by the application installed in the information receiving terminal; and also

Configured to cause the application to present the at least one incident multi-occurrence segment on an interface of the information receiving terminal; and

and instructing the information receiving terminal to display an interface by sending the electronic signal to the information sending port so as to present the accident-prone area.

37. The method 36, wherein operating the first clustering process input comprises:

identifying a plurality of points corresponding to the input;

determining a result cluster and a result point associated with the result cluster by a point identification operation, the method comprising:

selecting a candidate cluster of a point from the plurality of points;

selecting a candidate point from the candidate cluster of points;

a target cluster using the candidate point as a center point and using a candidate cluster of the point as one point;

identifying one cluster within a preset distance from the central point from the target clusters of the points as a candidate cluster of the points; and

a point is identified from the candidate cluster of points as a candidate point.

38. The method of claim 37, wherein in each of the first iterations, the candidate points in the first iteration are related to average coordinates of corresponding candidate cluster points in the first iteration.

39. The method of claim 37, further comprising:

when the candidate cluster of points determined in the last first iteration of the first iterative operation meets the first stop condition,

acquiring a candidate cluster of points corresponding to the last first iteration as a first iteration operation result cluster; and

and acquiring a candidate point corresponding to the last first iteration as a result point of the first iteration operation.

40. The method of claim 39, further comprising outputting a result point of the first iterative operation as a first result of the first clustering process.

41. The method of claim 39, wherein the result point is one of a plurality of result points and the result cluster is one of a plurality of result clusters; and the method further comprises:

obtaining a plurality of subsequent result points and a plurality of subsequent result clusters by running a second iteration operation until a second stop condition is satisfied based on an output of the first iteration operation, wherein the second iteration operation comprises a plurality of second iterations, and each second iteration comprises:

updating the plurality of points by removing from the plurality of points a result cluster of locations identified in a last iteration of the second iterative operation;

determining a subsequent cluster of results and a subsequent point of results based on the updated plurality of points by performing the point identification operation.

42. The method 41 of claim, further comprising:

for each of the plurality of result clusters,

determining a stop time based on the number of points in the result cluster;

determining whether a stop time associated with the candidate cluster is greater than a time threshold; and

and responding to the stopping time larger than the time threshold value, and allocating the result point corresponding to the candidate result cluster as the accurate accident site.

43. The method of claim 36, wherein the second clustering process comprises a first clustering process; and

determining the at least one incident multi-occurrence segment comprises:

acquiring the plurality of precise accident sites;

operating the second clustering process by taking the plurality of precise accident sites as input to the second clustering process to determine a plurality of result clusters; and

for each of the plurality of result clusters, assigning a road segment associated with the result cluster as an accident-prone segment.

44. The method of claim 43, further comprising:

for each of the plurality of result clusters,

determining a number of points in the result cluster;

determining whether the number is greater than a density threshold; and

in response to the number being greater than a density threshold, determining a road segment associated with the result cluster based on the points of the result cluster.

45. The method of claim 36, wherein the obtaining a plurality of incident records comprises:

acquiring historical positions of the target user terminals;

46. The method according to claim 45, wherein each of the plurality of incident reports includes at least one of:

an accident report of a user report of the target user terminal;

accident reports reported by insurance companies; or

Accident reporting by traffic police.

47. A non-transitory computer readable medium comprising an operating system and at least one set of instructions compatible with the operating system for predicting a traffic accident site, wherein when the instructions are executed by at least one processor of one or more electronic devices, the at least one set of instructions cause the at least one processor to:

a plurality of precise incident locations are determined, and for each of the plurality of incident records, a plurality of accident records are generated, by,

In response to determining the at least one incident multiple occurrence, generating an electronic signal comprising information for one of the at least one incident multiple occurrence and a trigger code, wherein the trigger code:

is a format recognizable by an application installed in the information receiving terminal; and also

Configured to cause the application to present the at least one incident multi-occurrence segment on an interface of an information receiving terminal; and

and instructing the information receiving terminal to display an interface by sending the electronic signal to the information sending port so as to present the accident-prone area.

48. A system for one or more electronic devices to predict a location of a traffic accident, comprising:

at least one storage medium comprising a first operating system and a location of a traffic accident associated with a set of instructions to operate the first system; and

at least one processor in communication with the storage medium, wherein the at least one processor, when executing the first operating system and the set of instructions, is to:

a plurality of precise incident locations are determined, and for each of the plurality of incident records, a plurality of accident records are generated, by,

and operating a first clustering process, taking a plurality of positions corresponding to the target user terminal as the input of the first clustering process, and taking a first result of the first clustering process as the accurate accident site of the plurality of positions of the target user terminal.

49. The system 48, wherein said at least one processor, in operation of said first clustering process, is configured to:

identifying a plurality of points corresponding to the input;

determining a result cluster and a result point associated with the result cluster by a point identification operation, comprising:

selecting a candidate cluster of a point from the plurality of points;

selecting a candidate point from the candidate cluster of points;

a target cluster using the candidate point as a center point and using a candidate cluster of the point as one point;

identifying one cluster within a preset distance from the central point from the target clusters of the points as a candidate cluster of the points; and

a point is identified from the candidate cluster of points as a candidate point.

50. The system 49 of, wherein in each of said first iterations, a candidate point in said first iteration is associated with an average coordinate of a corresponding candidate cluster point in said first iteration.

51. The system 49 of claim, wherein said at least one processor is further configured to:

when the candidate cluster of points determined in the last first iteration of the first iterative operation meets the first stop condition,

obtaining a candidate cluster of points corresponding to the last first iteration as a result cluster of the first iteration operation; and

and acquiring a candidate point corresponding to the last first iteration as a result point of the first iteration operation.

52. The system 51 of claim, wherein the at least one processor is further involved in outputting a result point of the first iterative operation as a first result of the first clustering process.

53. The system 51 of claim, wherein a result point is one of a plurality of result points and a result cluster is one of a plurality of result clusters;

the at least one processor is further configured to obtain a plurality of subsequent result points and a plurality of subsequent result clusters by executing a second iteration operation until a second stop condition is satisfied based on an output of the first iteration operation, wherein the second iteration operation includes a plurality of second iterations, and each of the second iterations includes:

updating the plurality of points by removing from the plurality of points a result cluster of locations identified in a last iteration of the second iterative operation; and

determining, by the point identification operation, a subsequent cluster of results and a subsequent point of results based on the updated plurality of points.

54. The system 51 of, wherein the at least one processor is further involved in:

responsive to determining a plurality of precise accident locations, determining at least one accident-prone location by operating a second clustering process, a plurality of precise accident locations corresponding to the plurality of accident records as an input to the second clustering process;

in response to determining the at least one incident-multiple location, generating an electronic signal comprising information of the at least one incident-multiple location; and

55. The system 54 of, wherein the second clustering process comprises a first clustering process; and

determining at least one incident multi-occurrence segment, the processor being further configured to:

acquiring a plurality of accurate accident sites;

determining a plurality of result clusters by running a second clustering process, the plurality of precise accident sites serving as input clusters of the second clustering process;

for each of the plurality of result clusters, a road segment associated with the result cluster is designated as an accident-prone segment.

56. A method for predicting a location of a traffic accident, implemented in communication with one or more electronic devices including at least one storage medium and at least one processor and the at least one storage medium, comprising:

obtaining a plurality of incident records for a plurality of traffic incidents, each of the plurality of incident records being associated with a respective target user terminal and comprising a recorded incident time for the traffic incident and a plurality of locations at which the target user terminal is present near the recorded incident time;

a plurality of precise accident locations are determined and, for each accident record, a plurality of accident locations are determined, by,

and running a first clustering process, taking a plurality of positions corresponding to the target user terminal as input of the first clustering process, and designating a first result of the first clustering process as an accurate accident site of the plurality of positions of the target user terminal.

57. The method 56, wherein running the first clustering process comprises:

identifying a plurality of points corresponding to the input;

determining a result cluster and a result point associated with the result cluster by a point identification operation, comprising:

selecting a candidate cluster of a point from a plurality of points;

selecting candidate points from the candidate clusters of points;

a target cluster using the candidate point as a center point and using a candidate cluster of the point as one point;

identifying one cluster within a preset distance from the central point from the target clusters of the points as a candidate cluster of the points; and

a point is identified from the candidate cluster of points as a candidate point.

58. The method of claim 57, wherein in each first iteration, the candidate points in the first iteration are related to the average coordinates of the points in the corresponding candidate cluster in the first iteration.

59. The method of claim 57 further comprising:

upon determining in the last first iteration of the first iterative operation that the candidate cluster of points meets a first stop condition,

obtaining a candidate cluster of points corresponding to the last first iteration as a result cluster of the first iteration operation; and

and acquiring a candidate point corresponding to the last first iteration as a result point of the first iteration operation.

60. The method 59 of claim, further comprising outputting a result point of a first iterative operation as a first result of a first clustering process.

61. The method of claim 59, wherein the result point is one of a plurality of result points and the result cluster is one of a plurality of result clusters; the method further comprises the following steps:

updating the plurality of points by removing from the plurality of points a result cluster of locations identified in a last iteration of a second iteration operation;

by performing the point identification operation, a subsequent cluster of results and a subsequent point of results are determined based on the updated plurality of points.

62. The method 56 of claim further comprising:

generating an electronic signal comprising information of at least one incident-multiple location in response to the determination of the at least one incident-multiple location; and

63. The method of claim 62, wherein the second clustering process comprises a first clustering process; and

determining at least one incident multi-occurrence segment, the processor being further configured to:

acquiring a plurality of accurate accident sites;

determining a plurality of result clusters by running a second clustering process, the plurality of precise accident sites as inputs to the second clustering process;

for each of the plurality of result clusters, the road segment associated with the result cluster is taken as an accident-prone segment.

64. A system for predicting a location of a traffic accident, comprising:

a record acquisition module to acquire a plurality of incident records for a plurality of traffic incidents, each incident record of the plurality of incident records being associated with a respective target user terminal and comprising a recorded incident time for a traffic incident and a location at which the target user terminal appears around the recorded incident time;

an accident location determination module for determining a plurality of precise accident locations by, for each of a plurality of accident records

Running a first clustering process, taking the corresponding plurality of positions of the target user terminal as an input of the first clustering process, and designating a first result of the first clustering process as an accurate accident site of the plurality of positions of the target user terminal; and

a segment determination module for determining at least one accident-prone segment by operating a second clustering process in response to determining the plurality of precise accident locations, the plurality of precise accident locations corresponding to the plurality of accident records being an input to the second clustering process.

Technical Field

The application relates to a system and method for determining a traffic accident location and an accident multiple location using artificial intelligence, and displaying the accident multiple location on a user mobile device.

Background

Vehicles are widely used in public transportation and are becoming more and more popular for people to get on and off duty daily. When an accident occurs, the driver of the vehicle, the passenger of the vehicle, the accident witness or the police need to report the time and place of the accident (e.g., the time and place of the accident) in order to seek road assistance, ambulance service, fire truck assistance or insurance service. However, the reported time and place of the incident are often inaccurate, thus making it difficult to locate the actual incident and delaying the provision of the necessary services. Accordingly, there is a need to provide systems and methods for remotely determining an accurate time of an accident and an accurate place of the accident so that effective location of the accident can be achieved. Further, it is desirable to provide methods and systems for predicting multiple accident-prone areas to provide driver assistance in safe driving.

Disclosure of Invention

One aspect of the present application introduces a system of one or more electronic devices for predicting a location of a traffic accident, comprising: at least one storage medium including a first operating system and a set of instructions compatible with the first operating system for providing a accident-prone location to at least one information receiving terminal; and at least one processor in communication with the storage medium, wherein the at least one processor, when executing the first operating system and the set of instructions, is configured to: obtaining a plurality of incident records for a plurality of traffic incidents, each incident record of the plurality of incident records being associated with a respective target user terminal and comprising a recorded incident time and a plurality of locations for a traffic incident, the plurality of locations being locations at which the target user terminal occurs before and after the recorded incident time; determining a plurality of accurate accident locations, for each of a plurality of accident records, by running a first clustering process, taking a plurality of positions corresponding to the target user terminal as an input of the first clustering process, and taking a first result of the first clustering process as an accurate accident location of the plurality of positions of the target user terminal; in response to determining the plurality of precise accident locations, determining at least one accident-prone location by operating a second clustering process, the plurality of precise accident locations to which the plurality of accident records correspond as inputs to the second clustering process; in response to determining the at least one incident-prone location, generating an electronic signal comprising information of the at least one incident-prone location; and instructing the information receiving terminal to display an interface presenting the at least one accident multi-occurrence section by transmitting the electronic signal to the information receiving terminal.

In some embodiments, running the first clustering process, the at least one processor is configured to: identifying a plurality of points corresponding to the input; determining a result cluster and a result point associated with the result cluster by a point identification operation, comprising: selecting a candidate cluster of a point from the plurality of points; selecting a candidate point from the candidate cluster of points; executing a first iterative operation until a first stop condition is satisfied, wherein the first iterative operation includes a plurality of first iterations, and each of the first iterations includes: a target cluster using the candidate point as a center point and using a candidate cluster of the point as one point; identifying one cluster within a preset distance from the central point from the target clusters of the points as a candidate cluster of the points; and identifying a point from the candidate cluster of points as a candidate point.

In some embodiments, in each first iteration, the candidate points in the first iteration are related to the average coordinates of the points in the corresponding candidate cluster in the first iteration.

In some embodiments, the at least one processor is further configured to: when the candidate cluster of the point determined in the last first iteration of the first iteration operation meets the first stop condition, acquiring the candidate cluster of the point corresponding to the last first iteration as a result cluster of the first iteration operation; and acquiring a candidate point corresponding to the last first iteration as a result point of the first iteration operation.

In some embodiments, the at least one processor is further configured to output the result point of the first iterative operation as a first result of the first clustering process.

In some embodiments, the result point is one of a plurality of result points and the result cluster is one of a plurality of result clusters; and the at least one processor is further configured to execute a second iterative operation based on an output of the first iterative operation, obtain a plurality of subsequent result points and a plurality of subsequent result clusters by executing the second iterative operation until a second stop condition is satisfied, wherein the second iterative operation includes a plurality of second iterations, and each second iteration includes: updating the plurality of points by removing from the plurality of points a result cluster of locations identified in a last iteration of the second iterative operation; determining a subsequent cluster of results and a subsequent point of results based on the updated plurality of points by performing the point identification operation.

In some embodiments, the at least one processor is further configured to: determining, for each of a plurality of result clusters, a stop time based on a number of points in the result cluster; determining whether a stop time associated with the result cluster is greater than a time threshold; and responding to the stopping time being larger than the time threshold value, and distributing the result point corresponding to the result cluster as the accurate accident site.

In some embodiments, the second clustering process comprises a first clustering process; and determining the at least one incident multi-occurrence segment, the processor further to: acquiring the plurality of precise accident sites; determining a plurality of result clusters by running a second clustering process, the plurality of precise accident sites as inputs to the second clustering process; and for each of the plurality of result clusters, assigning the road segment associated with the result cluster as an accident-prone segment.

In some embodiments, the at least one processor is further configured to: determining, for each of the plurality of result clusters, a number of points in the result cluster; determining whether the number is greater than a density threshold; and responsive to the number being greater than the density threshold, determining a road segment associated with the result cluster based on a point in the result cluster.

In some embodiments, a plurality of incident records are obtained, the at least one processor further configured to: receiving a plurality of incident reports, each of the plurality of incident reports being associated with a respective target user terminal and including a recorded incident time and a recorded incident location; acquiring a plurality of historical positions of the target user terminal; for each incident report of a plurality of incident reports, merging a respective recorded incident time and recorded incident location with a historical location of the corresponding target user terminal to obtain an incident record associated with the corresponding target user terminal.

In some embodiments, each of the plurality of incident reports includes at least one of: an accident report of a user report of the target user terminal; accident reports reported by insurance companies; or traffic police reported accident reports.

According to another aspect of the present application, there is provided a method of predicting a location of a traffic accident, the method being implemented on one or more electronic devices having at least one storage medium and at least one processor in communication with the at least one storage medium, the method comprising: obtaining a plurality of incident records for a plurality of traffic incidents, each incident record of the plurality of incident records being associated with a respective target user terminal and comprising a recorded incident time and a plurality of locations for a traffic incident, the plurality of locations being locations at which the target user terminal occurs before and after the recorded incident time; determining a plurality of accurate accident locations, for each of a plurality of accident records, by running a first clustering process, taking a plurality of positions corresponding to the target user terminal as an input of the first clustering process, and taking a first result of the first clustering process as an accurate accident location of the plurality of positions of the target user terminal; in response to determining the plurality of precise accident locations, determining at least one accident-prone location by operating a second clustering process, a plurality of precise accident locations corresponding to the plurality of accident records as inputs to the second clustering process; in response to determining the at least one incident-multiple location, generating an electronic signal comprising information of the at least one incident-multiple location; and instructing the information receiving terminal to display an interface presenting the at least one accident multi-occurrence section by transmitting the electronic signal to the information receiving terminal.

According to yet another aspect of the present application, a non-transitory computer-readable medium includes an operating system and at least one set of instructions compatible with the operating system for predicting a traffic accident site, wherein when the instructions are executed by at least one processor of one or more electronic devices, the at least one set of instructions cause the at least one processor to: obtaining a plurality of incident records for a plurality of traffic incidents, each incident record of the plurality of incident records being associated with a respective target user terminal and comprising a recorded incident time and a plurality of locations for a traffic incident, the plurality of locations being locations at which the target user terminal occurs before and after the recorded incident time; determining a plurality of accurate accident locations, for each of a plurality of accident records, by running a first clustering process, taking a plurality of positions corresponding to the target user terminal as an input of the first clustering process, and taking a first result of the first clustering process as an accurate accident location of the plurality of positions of the target user terminal; in response to determining the plurality of precise accident locations, at least one accident-prone segment is determined by operating a second clustering process, the plurality of precise accident locations to which the plurality of accident records correspond as inputs to the second clustering process. In response to determining the at least one incident-prone location, generating an electronic signal comprising data of the at least one incident-prone location; and instructing the information receiving terminal to display an interface presenting the at least one accident multi-occurrence section by transmitting the electronic signal to the information receiving terminal.

According to yet another aspect of the present application, a system for predicting a location of a traffic accident includes: a record acquisition module configured to acquire a plurality of incident records for a plurality of traffic incidents, each of the plurality of incident records being associated with a corresponding target user terminal and comprising an incident time for a record of a traffic incident and a plurality of locations, the plurality of locations being locations at which the target user terminal appears before and after the recorded incident time; an accident location determination module configured to determine a plurality of precise accident locations, by, for each of a plurality of accident records, running a first clustering process, taking a plurality of locations corresponding to the target user terminal as an input to the first clustering process, and taking a first result of the first clustering process as a precise accident location for the plurality of locations of the target user terminal; a segment determination module configured to determine at least one accident-prone segment by operating a second clustering process in response to determining the plurality of precise accident locations, a plurality of precise accident locations corresponding to the plurality of accident records as inputs to the second clustering process; an information transmitting module configured to transmit the information of the at least one accident-prone location to an information receiving terminal.

Additional features will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following and the accompanying drawings or may be learned by production or operation of the examples. The features of the present application may be realized and obtained by means of the instruments and methods and by means of the methods and combinations set forth in the detailed examples discussed below.

Drawings

The present application is further described in terms of exemplary embodiments. The detailed description of these exemplary embodiments may refer to the accompanying drawings. These embodiments are non-limiting exemplary embodiments, in which like reference numerals represent similar structures throughout the several views of the drawings, and in which:

FIG. 1 is a schematic diagram of an exemplary artificial intelligence system, in accordance with some embodiments of the present application;

FIG. 2 is a schematic diagram of exemplary hardware and/or software components of a computing device according to some embodiments of the present application;

FIG. 3 is a schematic diagram of exemplary hardware and/or software components of a mobile device according to some embodiments of the present application;

FIG. 4 is a block diagram of an exemplary processing engine according to some embodiments of the present application;

FIG. 5A is a flow diagram of an exemplary process for determining at least one incident multi-occurrence segment, according to some embodiments of the present application;

FIG. 5B is an exemplary user interface of an information receiving terminal for displaying an incident-prone location according to some embodiments of the present application;

FIG. 6 is a flow diagram of an exemplary process for running a first clustering process according to some embodiments of the present application;

FIG. 7 is a flow diagram of an exemplary process for a run-point identification operation according to some embodiments of the present application;

FIG. 8 is a flow diagram illustrating an exemplary process for running a first iterative operation in accordance with some embodiments of the present application;

FIG. 9 is a flow diagram of an exemplary process for running a first clustering process in accordance with some embodiments of the present application;

FIG. 10 is a flow diagram of an exemplary process for running a second iterative operation in accordance with some embodiments of the present application;

FIG. 11 is a flow chart of an exemplary process for determining an accurate incident location according to some embodiments of the present application;

FIG. 12 is a flow diagram of an exemplary process for determining at least one incident multi-occurrence segment according to some embodiments of the present application;

FIG. 13 is a flow diagram of an exemplary process for determining at least one incident multi-occurrence segment according to some embodiments of the present application; and

FIG. 14 is a flow diagram of an exemplary process for obtaining a plurality of incident records according to some embodiments of the present application.

Detailed Description

The following description is presented to enable one of ordinary skill in the art to make and use the application and is provided in the context of a particular application and its requirements. Various modifications to the disclosed embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the present application. Thus, the present application is not limited to the embodiments shown, but is to be accorded the widest scope consistent with the claims.

The terminology used herein is for the purpose of describing particular example embodiments only and is not intended to limit the scope of the present application. As used in this application and the appended claims, the terms "a," "an," "the," and/or "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that steps and elements are included which are explicitly identified, that the steps and elements do not form an exclusive list, and that a method or apparatus may include other steps or elements.

The features and characteristics of the present application, as well as the methods of operation and functions of the related elements of structure and the combination of parts and economies of manufacture, will become more apparent upon consideration of the following description of the drawings, which form a part hereof. It is to be understood, however, that the drawings are designed solely for the purposes of illustration and description and are not intended as a definition of the limits of the application. It should be understood that the drawings are not to scale.

Flow charts are used herein to illustrate operations performed by systems according to embodiments of the present application. It should be understood that the preceding and following operations are not necessarily performed in the exact order in which they are performed. Rather, various steps may be processed in reverse order and/or co-workers. Meanwhile, other operations may be added to the processes, or a certain step or several steps of operations may be removed from the processes.

Positioning techniques used in the present application may include Global Positioning System (GPS), global navigation satellite system (GLONASS), COMPASS navigation system (COMPASS), galileo positioning system, quasi-zenith satellite system (QZSS), wireless fidelity (WiFi) positioning techniques, and the like, or any combination thereof. One or more of the above-described positioning techniques may be used interchangeably in this application.

One aspect of the present application relates to systems and methods for predicting accurate traffic accident locations and accident multiple locations and presenting the accident multiple locations to a user of a user mobile device. To this end, the system and method may analyze a travel track of an accident vehicle and match an accident time and an accident location reported by an accident information provider (e.g., a driver of the accident vehicle, an insurance company of the accident vehicle, etc.) with data of the travel track. The system may further obtain location data for the accident vehicle to determine an accurate location of the traffic accident. The system may further cluster the location data according to the duration of the vehicle stopping in an area to obtain an accurate traffic accident location for the accident vehicle. In addition, the system may acquire multiple accurate traffic accident locations for multiple accidents to determine accident-rich zones. The system may cluster multiple accurate traffic accident locations according to the frequency of the traffic accidents to obtain accident-prone locations, and present the accident-prone locations to alert information recipients (e.g., drivers, passengers, etc.) to caution when passing the accident-prone locations.

FIG. 1 is a schematic diagram of an exemplary artificial intelligence system 100 according to some embodiments of the present application. In some embodiments, the artificial intelligence system 100 can be an online-to-offline service artificial intelligence system. For example, the artificial intelligence system 100 can be used for an online-to-offline service platform for transportation services such as taxi drivers, driver services, delivery vehicles, carpools, bus services, driver hiring, shift services, and online navigation services. The artificial intelligence system 100 can be a system that includes a server 110, a user terminal 120, an information source 130, a storage 140, a network 150, and an information receiving terminal 160. The server 110 may include a processing engine 112.

The server 110 may be used to process information and/or data related to incident records. For example, the server 110 may determine the precise incident location for each incident record. For another example, the server 110 can determine a plurality of incident multi-occurrence zones based on a plurality of precise incident locations associated with a plurality of incident records. The precise location of the accident may be the exact location of the actual traffic accident contained in the accident log. An accident-prone location may be a location or area where traffic accidents are more likely to occur than other locations or areas.

The server 110 may be a stand-alone server or a group of servers. The set of servers can be centralized or distributed (e.g., server 110 can be a distributed system). The server 110 may be regional or remote in some embodiments. For example, server 110 may access information and/or data stored in information attestation system 130 and/or memory 130 via network 150. As another example, server 110 may be connected to memory 130 to access stored information and/or data. In some embodiments, the server 110 may be implemented on a cloud platform. For example, the cloud platform may include one or any combination of a private cloud, a public cloud, a hybrid cloud, a community cloud, a decentralized cloud, an internal cloud, and the like. In some embodiments, server 110 may be implemented on a computing device 200 having one or more components shown in FIG. 2 in the present application.

In some embodiments, the server 110 may include a processing device 112. The processing device 112 may process data and/or information related to the service request to perform one or more of the functions described herein. For example, the processing engine 112 may determine the precise incident location for each incident record. For another example, the processing engine 112 can determine a plurality of incident multi-occurrence segments based on a plurality of precise incident locations associated with a plurality of incident records. In some embodiments, the processing device 112 may include one or more sub-processing devices (e.g., a single core processing device or a multi-core processing device). By way of example only, the processing device 112 may include a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), an Application Specific Instruction Processor (ASIP), a Graphics Processor (GPU), a Physical Processor (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a programmable logic circuit (PLD), a controller, a micro-controller unit, a Reduced Instruction Set Computer (RISC), a microprocessor, or the like, or any combination thereof.

The user terminal 120 may be any type of device used by a user to report a traffic accident. For example, the user terminal 120 may send an accident report, including an accident time record and an accident location record, to report the traffic accident to the server 110. The user of the user terminal 120 may be any organization or individual reporting a traffic accident, such as a driver (or passenger) of the traffic accident, a traffic police handling the traffic accident, a staff member of an insurance company of the traffic accident, a witness of the traffic accident, and the like, or any combination thereof. The incident time record and the incident location record may be different from the corresponding actual incident time and actual incident location.

In some embodiments, the user terminal 120 may include any type of device, such as a mobile device, an electronic device, an automobile, and the like, or any combination thereof. For example, the user terminal 120 may include a desktop computer 120-1, a laptop computer 120-2, a built-in device 120-3 in a motor vehicle, a mobile device 120-4, and the like or any combination thereof. The built-in device 120-3 may include an on-board computer, an on-board television, an on-board positioning system, and the like. In some embodiments, the mobile device 120-4 may include a smart home device, a wearable device, a smart mobile device, a virtual reality device, an augmented reality device, and the like, or any combination thereof. In some embodiments, the wearable device may include a smart bracelet, smart footwear, smart glasses, smart helmet, smart watch, smart clothing, smart backpack, smart accessory, or the like, or any combination thereof. In some embodiments, the smart mobile device may comprise a smart phone, a Personal Digital Assistant (PDA), a gaming device, a navigation device, a POS device, or the like, or any combination thereof. In some embodiments, the metaverse device and/or the augmented reality device may include a metaverse helmet, metaverse glasses, metaverse eyewear, augmented reality helmets, augmented reality glasses, augmented reality eyewear, and the like, or any combination thereof. For example, the metaverse and/or augmented reality devices may include Google Glass^TM、RIFTCON^TM、FraceTS^TM、Gear VR^TMAnd the like. In some embodiments, the user terminal 120 may be a device having a positioning technology for locating the position of the user terminal 120 and/or the user. In some embodiments, the user terminal 120 may be implemented on a computing device 200 having one or more components shown in FIG. 2 of the present application or a mobile device 300 having one or more components shown in FIG. 3 of the present application.

The information source 130 may be used to provide information to the system 100. For example, the information source 130 may provide traffic accident reports to the system 100. The information source 130 may be a traffic system of a traffic police or an insurance system of an insurance company. As another example, the information sources 130 may provide information and/or data related to traffic accidents to the system 100, such as news, real-time traffic conditions, road monitoring images or videos, and so forth. The information source 130 may be a television station, a radio station, real-time media, a road network, a road monitoring device, etc., or any combination thereof. In some embodiments, the information source 130 may include a network port to send and/or receive information to one or more components of the artificial intelligence system 100 (e.g., the server 110, the memory 140, etc.). For example, the information 130 may send a plurality of incident reports to the server 110 through a network port.

Storage device 140 may store data and/or instructions. In some embodiments, the storage device 140 may store data (e.g., positioning data) retrieved from the user terminal 120. In some embodiments, storage device 140 may store information and/or instructions for execution or use by server 110 to perform the example methods described herein. In some embodiments, storage device 140 may include mass storage, removable storage, volatile read-and-write memory (e.g., random access memory, RAM), read-only memory (ROM), the like, or any combination thereof. Exemplary mass storage devices may include magnetic disks, optical disks, solid state drives, and the like. Exemplary removable memory may include flash drives, floppy disks, optical disks, memory cards, compact disks, magnetic tape, and the like. Exemplary volatile read and write memories can include Random Access Memory (RAM). Exemplary random access memories may include Dynamic Random Access Memory (DRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), Static Random Access Memory (SRAM), thyristor random access memory (T-RAM), zero capacitor random access memory (Z-RAM), and the like. Exemplary read-only memories may include mask read-only memory (MROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM), digital versatile disc read-only memory (dvd-ROM), and the like. In some embodiments, memory 140 may be implemented on a cloud platform. By way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an intermediate cloud, a multi-cloud, and the like or any combination thereof.

In some embodiments, the memory 140 may include at least one network port for communicating with other devices in the artificial intelligence system 100. For example, the memory 140 may be coupled to at least one network port and one or more components of the artificial intelligence system 100 (e.g., the server 110, the user terminal 120) via the network 150. One or more components in the artificial intelligence system 100 can access data or instructions stored in the memory 140 over the network 150. In some embodiments, the memory 140 may be directly connected to or in communication with one or more components in the artificial intelligence system 100 (e.g., server 110, user terminal 120). In some embodiments, memory 140 may be part of server 110.

The network 150 may facilitate the exchange of information and/or data. In some embodiments, one or more components of the online-offline serviced artificial intelligence system 100 (e.g., the server 110, the user terminal 120, and the memory 140) may send information and/or data over a network to other components of the online-offline serviced artificial intelligence system 100. For example, the server 110 may obtain a plurality of incident records from an information receiving port of the information source 130 via the network 150. In some embodiments, the network 150 may be any type of wired or wireless network. For example, network 150 may include a cable network, a wired network, a fiber optic network, a telecommunications network, an intranet, the Internet, a Local Area Network (LAN), a Wide Area Network (WAN), a Wireless Local Area Network (WLAN), a Metropolitan Area Network (MAN), a Public Switched Telephone Network (PSTN), a Bluetooth network, a ZigBee network, a Near Field Communication (NFC) network, the like, or any combination thereof. In some embodiments, the network 150 may include one or more network access points. For example, the network 150 may include wired or wireless network access points, such as base stations and/or Internet switching points 150-1, 150-2, …, through which one or more components of the offline service artificial intelligence system 100 may connect to the network 150 to exchange data and/or information.

The information receiving terminal 160 may be any type of device that a user uses to receive information related to an incident multi-occurrence segment. For example, when the information receiving terminal 160 appears around the accident-prone location, the information receiving terminal 160 may be a mobile device that receives an alarm voice or an alarm display of the accident-prone location from the server 110. The user of the information receiving terminal 160 may be a driver, a passenger, a pedestrian, or the like, or any combination thereof. In some embodiments, the information receiving terminal 160 may be a similar or the same device as the user terminal 120. In some embodiments, the information receiving terminal 160 may be a device having a positioning technology for locating the position of the information receiving terminal 160 and/or its user. In some embodiments, information receiving terminal 160 may be implemented on computing device 200 having one or more of the components shown in FIG. 2 herein or on mobile device 300 having one or more of the components shown in FIG. 3 herein.

Fig. 2 is exemplary hardware and software components of a computing device 200 on which the server 110, passenger terminal 120, memory 130, driver's terminal 140, and/or information source 160 may be implemented according to some embodiments of the present application. For example, the processing engine 112 may be implemented on the computing device 200 and used to perform the functions of the processing engine 112 as claimed herein.

The computing device 200 may be used to implement one or more functions of any of the components of the artificial intelligence system 100 as claimed herein. For example, the processing engine 112 may be implemented on the computing device 200 by its hardware, software program, firmware, or any of the above. Although only one such computer is shown, for ease of description, computer functions associated with the offline service may be implemented in a distributed manner across multiple similar platforms to spread processing load.

For example, the computing device 200 may include a COM port 250 connected to and to a network thereon to facilitate data communications. COM port 250 may refer to any network port, information exchange port, or any information transmission port to facilitate data communications. Computing device 200 may also include a processor (e.g., processor 220) in the form of one or more processors (e.g., logic circuits) for executing program instructions. For example, a processor may include interface circuitry and processing circuitry therein. Interface circuitry may be used to receive electronic signals from bus 210, where the electronic signals encode structured data and/or instructions for processing by the processing circuitry. The processing circuitry may perform logical computations and then determine conclusions, results and/or instructions encoded into electronic signals. The processing circuit may also generate an electronic signal that includes a conclusion or result (e.g., a multi-incident period) and a trigger code. In some embodiments, the trigger code may be in a format recognizable by the operating system (or an application installed therein) of the electronic device (e.g., user terminal 120) in the artificial intelligence system 100. For example, the trigger code may include instructions, code, indicia, symbols, etc., or any combination thereof, that may activate certain functions and/or operations of the mobile phone or cause the mobile phone to execute a preset program. In some embodiments, the trigger code may be used to run an operating system (or application) of the electronic device to generate a presentation of a conclusion or result (e.g., an accident-prone location) on an interface of the electronic device. The interface circuit may then send out electronic signals from the processing circuit over the bus 210.

An exemplary computing device may include an internal communication bus 210, different forms of program storage and data storage, including, for example, a disk 270, a Read Only Memory (ROM)230 or a Random Access Memory (RAM)240 for storing various data files processed and/or transmitted by the computing device. The exemplary computing device may also include program instructions stored in read-only memory 230, random access memory 240, and/or other types of non-transitory storage media to be executed by processor 220. The program instructions may implement the methods and/or processes of the present application. The exemplary computing device may also include an operating system stored in read-only memory 230, random access memory 240, and/or other types of non-transitory storage media to be executed by processor 220. The program instructions may be compatible with an operating system for providing online-to-offline services. Computing device 200 also includes input/output components 260 that support between the computer and other components. Computing device 200 may also receive programs and data via network communications.

For illustration only, only one processor is shown in FIG. 2, and multiple processors are also contemplated. Thus, operations and/or method steps described herein as being performed by one processor may also be performed by multiple processors, either jointly or separately. For example, if in the present application the processors of computing device 200 perform steps a and B, it should be understood that steps a and B may also be performed by two different processors in computing device 200, either collectively or individually (e.g., a first processor performing step a and a second processor performing step B, or a first and second processor performing steps a and B collectively).

Fig. 3 is a diagram illustrating exemplary hardware and/or software components of a mobile device 300 upon which a user terminal 130 may be implemented according to some embodiments of the present application.

As shown in fig. 3, mobile device 300 may include a communication unit 310, a display 320, a Graphics Processing Unit (GPU)330, a Central Processing Unit (CPU)340, an input/output port 350, a memory 360, and a memory 390. The central processing unit may include interface circuitry and processing circuitry similar to processor 220. In some embodiments, any other suitable component, including but not limited to a system bus or a controller (not shown), may also be included in the mobile device 300. In some embodiments, the mobile operating system 370 (e.g., iOS) may be moved from the memory 390^TM，Android^TM，Windows Phone^TMEtc.) and one or more application programs 380 are loaded into memory 360 for execution by the central processing unit 340. The application 380 may include a browser or any other suitable mobile application for receiving and presenting information related to voice requests for services. User interaction with the information stream may be accomplished through the input output port 350 and provided to the processing engine 112 and/or other components of the artificial intelligence system 100 via the network 120. The communication unit 310 may be any information exchange port, information transfer port, or network port to facilitate data communication.

To implement the various modules, units, and functions thereof described herein, a computer hardware platform may be used as the hardware platform for one or more of the elements described herein (e.g., artificial intelligence system 100 and/or other components of artificial intelligence system 100 described with respect to fig. 1-14). The hardware elements, operating systems, and programming languages of such computers are conventional in nature, and it is assumed that those skilled in the art are sufficiently familiar with this to enable these techniques to provide services in response to voice requests as described herein. A computer with user interface elements may be used to implement a Personal Computer (PC) or other type of workstation or terminal device, but if suitably programmed, the computer may also act as a server. It is believed that those skilled in the art are familiar with the structure, programming, and general operation of such computer devices, and therefore the drawings will not be described.

It will be understood by those of ordinary skill in the art that when elements of the artificial intelligence system 100 are implemented, the elements may be implemented by electrical and/or electromagnetic signals. For example, when the user terminal 120 handles tasks such as reporting a traffic accident, the user terminal 120 may operate logic circuits in its processor to handle such tasks. When the user terminal 120 issues an incident report, the processor of the user terminal 120 may generate an electrical signal of the encoded incident report. The processor of the user terminal 120 may then transmit the electrical signal to at least one information receiving port of an information providing system associated with the user terminal 120. The information providing system may include a user terminal 120, a network 150, and an information receiving port between the network 150 and the server 110. The user terminal 120 communicates with the information providing system through a wired network, and the at least one information exchange port may be physically connected to a cable that may further transmit the electrical signal to an input port (e.g., an information exchange port) of the server 110. If the user terminal 120 communicates with the information providing system through a wireless network, at least one information receiving port of the information providing system may be one or more antennas, which may convert electrical signals into electromagnetic signals. Within an electronic device, such as user terminal 120 and/or server 110, when its processor processes instructions, issues instructions, and/or performs actions, the instructions and/or actions are performed by electrical signals. For example, when the processor retrieves or saves data from a storage medium (e.g., memory 140), it may send electrical signals to the storage medium's read/write device, which may read or write structured data in the storage medium. The structured data may be transmitted to the processor in the form of electrical signals over a bus of the electronic device. Herein, an electrical signal may refer to one electrical signal, a series of electrical signals, and/or a plurality of discrete electrical signals. After the processor of the server 110 determines the result, the processor may generate an electrical signal encoding the result and transmit the electrical signal to at least one information transmission port of the information receiving system. The information receiving system may include an information receiving terminal 160, a network 150, and an information transmission port between the network 150 and the server 110. The information receiving terminal 160 communicates with the information receiving system through a wired network, and at least one information transmission port may be physically connected to a cable, which may further transmit electrical signals to an input port (e.g., an information exchange port) of the server 110. If the information receiving terminal 160 communicates with the information receiving system through a wireless network, at least one information transmission port of the information receiving system may be one or more antennas, which may convert electrical signals into electromagnetic signals.

Fig. 4 is a block diagram of an exemplary processing engine 112 according to some embodiments of the present application. The processing engine 112 may include a record acquisition module 410, an incident location determination module 420, a road segment determination module 430, an information transmission module 440, and a data consolidation module 450.

The record acquisition module 410 may be used to acquire a plurality of incident records. In some embodiments, each of the plurality of incident records is associated with a corresponding target user terminal and includes a recorded incident time and a plurality of locations at which the target user terminal occurs around the recorded incident time. For example, an incident record of the plurality of incident records may record a traffic incident of a vehicle associated with the target user terminal. The recorded time of the accident may be the time reported by the user witnessing the traffic accident. The plurality of historical locations where the target user terminal occurs around the recorded time of the incident may be obtained by matching all of the historical locations of the target user terminal with the recorded time of the incident.

The incident location determination module 420 may determine a plurality of precise incident locations. The precise location of the accident may be the exact location where the actual traffic accident occurred. In some embodiments, the accident location determination module 420 may use a first clustering process based on a plurality of locations of the target user terminal. For example, the incident location determination module 420 may take as input a plurality of locations of the target user terminal for a first clustering process. The incident location determination module 420 may designate the first result of the first clustering process as the precise incident location of the plurality of locations of the target user terminal. In some embodiments, the incident location determination module 420 may be used to determine a plurality of precise incident locations for a corresponding plurality of incident records. A detailed description of determining multiple precise accident sites may be found elsewhere in this application (e.g., fig. 5-11 and their descriptions).

The road segment determination module 430 may determine at least one accident multi-occurrence segment. The accident-prone location may be an area that is more prone to traffic accidents than other areas. In some embodiments, the road segment determination module 430 may use a second clustering process to determine at least one accident multi-occurrence segment, with a plurality of precise accident locations corresponding to a plurality of accident records as a second clustering process input. A detailed description of determining multiple precise incident locations may be found elsewhere in this application (e.g., fig. 5-13 and their descriptions).

The information transmitting module 440 may transmit information related to at least one accident multi-occurrence section to the information receiving terminal. In some embodiments, the information associated with the at least one incident multi-occurrence segment may be in the format of a plurality of electronic signals along with a trigger code. The trigger code may issue an application to generate a display of at least one accident-prone road section on an interface of the information receiving terminal.

The data consolidation module 450 may be used to obtain multiple incident reports and multiple historical locations for a target user terminal. The data consolidation module 450 may consolidate the recorded incident time and the recorded incident location in each incident report with a plurality of historical locations of the target user terminals to obtain incident records associated with the corresponding target user terminals. A detailed description of merging data to obtain an incident record can be found elsewhere in this application (e.g., fig. 14 and its description).

The modules in the processing engine 112 may be connected or in communication with each other through wired or wireless connections. The wired connection may include a metal cable, an optical cable, a hybrid cable, and the like, or any combination thereof. The wireless connection may include a Local Area Network (LAN), a Wide Area Network (WAN), bluetooth, ZigBee, Near Field Communication (NFC), etc., or any combination of the above, two or more modules may be combined into a single module, and any one module may be divided into two or more units. For example, the record acquisition module 410 and the data consolidation module 450 may be combined into a single module that may consolidate incident reports and acquire incident records. As another example, the processing engine 112 may include a storage module (not shown) for storing data and/or information for determining an accurate incident location and/or incident multi-occurrence segment.

Fig. 5A is a flow diagram of an exemplary process for determining at least one incident multi-occurrence segment according to some embodiments of the present application. The process 500 may be performed by the on-demand service artificial intelligence system 100. For example, the process 500 may be performed by a set of instructions (e.g., an application program) stored in the read only memory 230 or the random access memory 240. Processor 220 may execute the set of instructions and, when executing the instructions, may perform flow 500. The operations of the illustrative process shown below are intended to be illustrative. In some embodiments, flow 500 may be accomplished with one or more additional operations not described and/or without one or more of the operations discussed. Additionally, the order of the operations of the processes shown in FIG. 5A and described below is not intended to be limiting.

In operation 510, the processing engine 112 (e.g., the processor 220, the record acquisition module 410) may acquire a plurality of incident records. In some embodiments, each of the plurality of incident records is associated with a corresponding target user terminal and includes a recorded incident time and a plurality of locations at which the target user terminal occurs around the recorded incident time.

In some embodiments, one of the plurality of incident records may record a traffic incident of a vehicle associated with the target user terminal. When a traffic accident occurs, a user of the target subscriber terminal (or a worker of an insurance company handling the traffic accident, a traffic police handling the traffic accident) may report the recorded accident time and the recorded accident location. The recorded time of the accident may be the time reported by the user witnessing the traffic accident. In some embodiments, the recorded accident time may be different from the actual accident time at which the traffic accident occurred. For example, the actual time of the accident is 15:00, and the user who has a traffic accident reports the time of the accident to be about 15: 24. The recorded accident location may be the location reported by the user witnessing the traffic accident. In some embodiments, the recorded accident location may be different from the actual accident location reported by the user witnessing the traffic accident. For example, the actual accident location is the intersection of road No. 1 and road No. 2, and the recorded accident location is near road No. 1.

In some embodiments, the target user terminal may be a device that includes positioning technology for acquiring a real-time location of the vehicle. For example, the target user terminal may be a mobile terminal of a passenger or a mobile terminal of a driver of the vehicle, a vehicle navigation system, a vehicle positioning system, etc., or any combination thereof. The real-time location may be stored as a plurality of historical locations in a storage medium (e.g., memory 140, read-only memory 230, random access memory 240, etc.) of the artificial intelligence system 100. For example, the target user terminal may acquire a location every preset period of time (e.g., every 5 seconds, every 10 seconds, every 30 seconds, etc.), and transmit the location and a time corresponding to the location to the storage medium. When the processing engine 112 obtains a traffic accident report for the vehicle, the processing engine 112 may access the storage medium to obtain a plurality of location sums of the target user terminal occurring around the recorded accident time and/or around the recorded accident location by matching the recorded accident time and/or the recorded accident location with the plurality of historical locations. The plurality of locations at which the target user terminal occurs around the recorded incident time may include locations at which the user terminal occurs during a period from a first preset time period before the recorded incident time to a second preset time after the recorded incident time. The first and/or second preset time periods may be determined by the processing engine 112 and its user. For example, when the recorded incident time is 15:00, the processing engine 112 may: 00-16: 00 obtain multiple locations of a target user terminal. The plurality of positions where the target user terminal appears near the recorded accident site may include a position where the user terminal appears within a range of a preset distance from the recorded accident site. The preset distance may be determined by the processing engine 112 and its user. For example, the recorded accident location is intersection 1, and the processing engine 112 may acquire a plurality of positions of the target user terminal in an area within a range of 5 km from the intersection 1.

In operation 520, the processing engine 112 (or incident location determination module 420) may determine a plurality of precise incident locations. In some embodiments, a first clustering process is used to determine a plurality of precise accident locations based on a plurality of locations of target user terminals. For example, the processing engine 112 may take as input a plurality of locations of the target user terminal for a first clustering process. The processing engine 112 may assign the first result of the first clustering process as a precise incident location for the plurality of locations of the target user terminal. In some embodiments, the precise accident location may be the exact location where the actual traffic accident occurred.

In some embodiments, multiple locations of a target user terminal may be mapped to multiple points on a map. The density of the plurality of points during the preset time period may reflect a dwell time of a vehicle associated with the target user terminal in the plurality of locations. For example, an area including a higher density of points on the map for one hour indicates that the vehicle stays longer in the same hour than an area including a lower density of points on the map. In some embodiments, the processing engine 112 may run the first clustering process based on the dwell time of the corresponding vehicle. The first clustering process may be a method and/or algorithm for clustering a plurality of points corresponding to a plurality of locations of the target user terminal. For example, the processing engine 112 may input a plurality of points into a first clustering process. The first clustering process may cluster the plurality of points to obtain a cluster including the most dense points, and select a point associated with an average coordinate of points in the cluster as a first result of the first clustering process. The processing engine 112 may determine the location corresponding to the selected point as the precise incident location of the target user terminal. In some embodiments, the first clustering process may be a density-based clustering method, such as the DBSCAN algorithm, the OPTICS algorithm, the Mean-shift algorithm, the cancel algorithm, or the like, or any combination thereof. In some embodiments, an exemplary method of the first clustering process may be found elsewhere in this application (e.g., fig. 6-10 and their descriptions).

In operation 530, based on the determination of the plurality of precise accident locations, the processing engine 112 (or the road segment determination module 430) may determine at least one accident multi-occurrence segment. In some embodiments, the at least one accident-multiple location may be determined using a second clustering process with a plurality of precise accident locations as inputs to the second clustering process.

In some embodiments, the accident-rich segment may be an area where traffic accidents are more likely to occur than other areas. The accident-prone location may be an exact location (e.g., a street intersection), a road segment (e.g., from 100 meters to 300 meters of a service road prior to an expressway entrance), etc., or any combination thereof.

In some embodiments, multiple precise incident locations may be mapped to multiple points on a map. The density of the plurality of dots may reflect the number of accidents that occurred in the past. More traffic accidents may occur in areas with higher density than in areas with lower density of points. In some embodiments, processing engine 112 may run the second classification process using the plurality of points as inputs. The second clustering process may be a method and/or algorithm that clusters a plurality of points corresponding to a plurality of precise accident locations. For example, processing engine 112 may input the plurality of points into a second clustering process. The second clustering process may cluster the plurality of points to obtain at least one cluster including points that are denser than other clusters, and identify an area (e.g., precise location, road segment) for each of the at least one cluster as an accident-high-speed road segment. In some embodiments, processing engine 112 may identify regions based on the corresponding clusters. For example, the processing engine 112 may determine an average coordinate of a plurality of points in at least one cluster and assign road segments within a preset distance from the average coordinate as corresponding accident-prone locations. In some embodiments, the second clustering process may be a density-based clustering method, such as DBSCAN algorithm, OPTICS algorithm, Mean-shift algorithm, cancel algorithm, or the like, or any combination thereof. In some embodiments, exemplary methods of the second clustering process may be found elsewhere in this application (e.g., fig. 6-11 and their descriptions). The second clustering process may be the same as the first clustering process. For example, the second clustering process and the first clustering process may be the exemplary methods described in fig. 6-11. Alternatively, the second clustering process may be a different method from the first clustering process. For example, the second clustering process is the DBSCAN algorithm, and the first clustering method may be the exemplary methods described in fig. 6-11.

In some embodiments, after determining the at least one incident multi-occurrence segment, the processing engine 112 (e.g., the processor 220, the information transmission module 440) may generate an electronic signal including the at least one incident multi-occurrence segment and a trigger code. In some embodiments, the trigger code may be in a format recognizable by an application installed in the information receiving terminal (e.g., a transportation service application, a car calling service application, a navigation service application, etc.). For example, the trigger code may be instructions, codes, indicia, symbols, or the like, or any combination thereof, that may activate or cause the information receiving terminal to execute a computer readable program. The trigger code may execute a program to display at least one accident-prone location on an interface of the information receiving terminal. For example, when the information receiving terminal enters an area within a preset distance from at least one accident-prone location, the processing engine 112 may instruct the information receiving terminal to display the corresponding accident-prone location to remind the user to drive cautiously or walk cautiously. In some embodiments, the processing engine 112 (e.g., the processor 220, the information sending module 440) may send the electronic signal to the information receiving terminal through an information sending port of the information receiving system. In response to the received electronic signal, the information receiving terminal may display the accident-prone section on its interface to remind the user of caution. Fig. 5B is an exemplary user interface of an information receiving terminal for displaying an accident-prone location according to some embodiments of the present application.

Fig. 6 is a flow diagram of an exemplary process for running a first clustering process according to some embodiments of the present application. The process 600 may be performed by the artificial intelligence system 100. For example, process 600 may be implemented with a set of instructions (e.g., an application program) stored in storage read only memory 230 or random access memory 240. Processor 220 may execute the set of instructions and, when executing the instructions, may perform flow 600. The operations of the process shown below are for illustration only. In some embodiments, flow 600 may be accomplished with one or more additional operations not described and/or without one or more of the operations discussed. In addition, the order of the processing operations shown in FIG. 6 and described below is not intended to be limiting.

In operation 610, the processing engine 112 (e.g., the processor 220) may identify a plurality of points corresponding to the input of the first clustering process. In some embodiments, each of the plurality of locations of the target user terminal may be mapped to a point on the map according to the coordinates of the location.

In operation 620, processing engine 112 (e.g., processor 220) may determine a result cluster and a result point associated with the result cluster through a point identification operation.

In some embodiments, the processing engine 112 may partition the plurality of identified points into a plurality of clusters according to some preset rules and select a result cluster from the plurality of clusters. For example, processing engine 112 may select the cluster that includes the most dense points as the result cluster. In some embodiments, processing engine 112 may determine a result point based on points in the result cluster. For example, processing engine 112 may determine an average coordinate or a weighted average coordinate of points in the result cluster and designate the points having the average coordinate or the weighted average coordinate as result points. As another example, processing engine 112 may determine a point in the result cluster that is closest to the average coordinate or the weighted average coordinate as the result point. The point identification operation may be a method or algorithm for determining clusters of results and points of results. A detailed description of the point identification operation can be found in fig. 7 and its description.

FIG. 7 is a flow diagram of an exemplary process for point identification operations according to some embodiments of the present application. The process 700 may be performed by the artificial intelligence system 100. For example, the process 700 may be implemented with a set of instructions (e.g., an application program) stored in the storage read only memory 230 or the random access memory 240. Processor 220 may execute the set of instructions and, when executing the instructions, may perform flow 700. The operations of the processes shown below are merely illustrative. In some embodiments, flow 700 may be accomplished with one or more additional operations not described and/or without one or more of the operations discussed. Additionally, the order in which the process operations are illustrated in FIG. 7 and described below is not intended to be limiting.

In operation 710, processing engine 112 (e.g., processor 220) may select a candidate cluster of points from a plurality of points. In some embodiments, the candidate cluster of points may include all of the plurality of points corresponding to the plurality of locations of the target user terminal. Alternatively, the candidate cluster of points may include a part of points among a plurality of points corresponding to a plurality of positions of the target user terminal.

In operation 720, the processing engine 112 (e.g., processor 220) may select a candidate point from the candidate cluster of points. In some embodiments, the candidate point may be an average coordinate of the candidate cluster midpoint, a weighted average coordinate of the candidate cluster midpoint, or any calculated value of the candidate cluster midpoint. In some embodiments, the candidate point may be the point closest to the average coordinate of the midpoint of the candidate cluster, the point closest to the weighted average coordinate of the midpoint of the candidate cluster, or the point closest to any calculated value of the midpoint of the candidate cluster.

In operation 730, processing engine 112 (e.g., processor 220) may run a first iterative operation on the candidate clusters and candidate points. In some embodiments, the first iterative operation may include a plurality of iterations.

Fig. 8 is a flow diagram of an exemplary process for a first iteration operation according to some embodiments of the present application. Each of the plurality of iterations may include three processes of operations 810-830 in sequence.

In operation 810, the processing engine 112 (e.g., processor 220) may use the candidate point as a center point and the candidate cluster of points as a target cluster of points. The center point may be used as a midpoint to obtain clusters of points within a preset distance from the center point.

In operation 820, the processing engine 112 (e.g., the processor 220) may identify a cluster of points within a preset distance from the center point from the target cluster of points as a candidate cluster of points. For example, processing engine 112 may update candidate clusters of points by selecting a plurality of points from a target cluster of points within a preset distance from a center point. For another example, the processing engine 112 may determine a distance for each point of the target cluster from the point of the center point and select a plurality of points whose respective distances are within a preset distance to obtain a candidate cluster for the point.

In some embodiments, the preset distance may be determined based on a type of vehicle associated with the target user terminal, an average traveling speed of the vehicle associated with the target user terminal, a type of traffic accident of the respective vehicle associated with the target user terminal, or the like, or any combination thereof. For example, the preset distance corresponding to the car is different from the preset distance corresponding to the electric bicycle. The preset distance corresponding to the automobile is 15 meters, and the preset distance corresponding to the electric bicycle is 8 meters.

In operation 830, the processing engine 112 (e.g., processor 220) may identify one point from the candidate cluster of points as a candidate point. In some embodiments, processing engine 112 may calculate an average coordinate of the candidate cluster midpoints, a weighted average coordinate of the candidate cluster midpoints, or any calculated value of the candidate cluster midpoints. The candidate point may be the point closest to the average coordinate of the midpoint of the candidate cluster, the point closest to the weighted average coordinate of the midpoint of the candidate cluster, or the point closest to any calculated value of the midpoint of the candidate cluster. In some embodiments, the candidate point may be updated to be the point in the candidate cluster that is closest to the average coordinate of the candidate cluster midpoint, the weighted average coordinate of the candidate cluster midpoint, or any calculated value of the candidate cluster point.

After each iteration of the first iterative operation, processing engine 112 (e.g., processor 220) may determine whether the candidate cluster (or candidate point) satisfies a first stop condition in operation 740. If the candidate cluster (or candidate point) satisfies the first stop condition, the processing engine 112 may proceed to operation 750. If the candidate cluster (or candidate point) does not satisfy the first stop condition, the processing engine 112 may proceed to the next iteration of the first iterative operation in flow 800, as shown in FIG. 8. For example, processing engine 112 may return to operation 810 to use the candidate point identified from operation 830 in the last iteration as the center point and the candidate cluster of points identified from operation 820 in the last iteration as the target cluster of points to continue the iteration in the first iteration operation until the candidate cluster (or candidate point) satisfies the first stop condition.

In some embodiments, the first stop condition may be that, during multiple iterations of the first iterative operation, the candidate cluster (or candidate point) generated in one iteration is the same as the candidate cluster (or candidate point) generated last time. For example, if the candidate clusters (or candidate points) for two consecutive iterations are the same, processing engine 112 may stop the first iteration operation to obtain a result cluster and/or a result point. In some embodiments, the first stop condition may be that the number of iterations in the first iterative operation is greater than a first iteration threshold. The first iteration threshold may be any value predetermined by the processing engine 112 or its user according to different application scenarios. For example, if the number of iterations in the first iterative operation is greater than 20, processing engine 112 may stop the first iterative operation to obtain a cluster of results and/or a point of results for the first iterative operation.

In operation 750, processing engine 112 (e.g., processor 220) may obtain a candidate cluster of points corresponding to the final iteration as a result cluster of the first iteration operation. The last iteration may be the last iteration before the candidate cluster (or candidate point) meets the first stopping condition. Processing engine 112 may designate the candidate cluster of points in the last iteration as the result cluster of the first iteration operation. In some embodiments, the result cluster may be the most dense cluster of the plurality of candidate clusters after the first iterative operation.

In operation 760, the processing engine 112 (or processor 220) may obtain a candidate point corresponding to the last iteration as a result point of the first iteration operation. The processing engine 112 may take the candidate point in the last iteration as the result point of the first iteration operation. In some embodiments, the result point may be the point closest to the average coordinate of the most closely clustered midpoints.

In some embodiments, processing engine 112 (or processor 220) may output the result point of the first iterative operation as a first result of the first clustering process. The result point of the first iterative operation may be the precise incident location associated with the target user terminal. For example, the result point is a point closest to the average coordinate of the midpoint of the closest cluster among a plurality of points corresponding to a plurality of positions of the user terminal. Since the result cluster is the most dense cluster among the plurality of candidate clusters, which indicates that a traffic accident is most likely to occur in the area of the corresponding result cluster, the result point may represent the most likely accident location where the target user terminal stays for the longest time. Thus, the processing engine 112 may take the result point as the precise incident location.

Fig. 9 is a flow diagram of an exemplary process for running a first clustering process according to some embodiments of the present application. The process 900 may be performed by the artificial intelligence system 100. For example, process 900 may be implemented with a set of instructions (e.g., an application program) stored in read only memory 230 or random access memory 240. Processor 220 may execute the set of instructions and, when executing the instructions, may perform flow 900. The operations of the processes shown below are merely illustrative. In some embodiments, flow 900 may be accomplished with one or more additional operations not described and/or without one or more of the operations discussed. Additionally, the order in which the process operations are illustrated in FIG. 9 and described below is not intended to be limiting.

In some embodiments, the processing engine 112 may execute the flow 900 of fig. 9 after the flow 600 of fig. 6 to further run the first clustering process. Processing engine 112 may determine a plurality of result points and a plurality of result clusters by running a first clustering process. In some embodiments, the result point determined in operation 620 of fig. 6 may be one of a plurality of result points and the result cluster determined in operation 620 of fig. 6 may be one of a plurality of result clusters.

In operation 910, the processing engine 112 (or the processor 220) may obtain a plurality of subsequent result points and a plurality of subsequent result clusters by executing a second iteration operation based on an output of the first iteration operation. In some embodiments, the second iterative operation may comprise a plurality of iterations.

FIG. 10 is a flow diagram of an exemplary process for running a second iterative operation according to some embodiments of the present application. The second iterative operation may include a plurality of iterations. Each of the plurality of iterations may include three processes of operations 1010-1030 in sequence.

In operation 1010, the processing engine 112 (or the processor 220) may update the plurality of points by removing from the plurality of points the cluster of results identified in the last iteration of the second iterative operation. In an initial step, the plurality of points may be updated by removing clusters of results identified in the first iteration (as shown in operation 760 in FIG. 7). Further, the plurality of points may be updated by removing clusters of results identified in the last iteration of the second iterative operation.

In process 1020, processing engine 112 (or processor 220) may determine subsequent clusters of results and subsequent points of results by performing a point identification operation based on the plurality of points updated, as shown in fig. 7-8. Subsequent clusters of results identified in an iteration of the second iteration operation may have a lesser density than clusters of results identified in a previous iteration of the second iteration operation. Thus, by performing a second iteration operation, i.e. by iteratively removing the result clusters identified from the previous iteration to update the plurality of points, one or more subsequent result clusters and one or more subsequent result points may be obtained. Further, one or more subsequent clusters of results identified in order during the iteration of the second iterative operation may be arranged in decreasing density order.

In process 920, processing engine 112 (or processor 220) may determine whether the second iterative operation satisfies a second stop condition. If the second iterative operation satisfies the second stop condition, the processing engine 112 may stop the second iterative operation. If the second iterative operation does not satisfy the second stop condition, the processing engine 112 may continue the iteration (e.g., operations 1010-1020) until the second iterative operation satisfies the second stop condition.

In some embodiments, the second stop condition may be that, during multiple iterations of the second iterative operation, the candidate cluster (or candidate point) generated in one iteration is the same as the candidate cluster (or candidate point) generated in the last iteration. For example, if the candidate clusters (or candidate points) of two consecutive iterations are the same, processing engine 112 may stop the second iteration operation. In some embodiments, the second stop condition may be that the number of iterations in the second iterative operation is greater than a second iteration threshold. The second iteration threshold may be any value predetermined by the processing engine 112 or its user according to different application scenarios. For example, if the number of iterations in the second iterative operation is greater than 10, processing engine 112 may stop the second iterative operation to obtain result points for a remaining portion of the plurality of result points and result clusters for a remaining portion of the plurality of result clusters.

Fig. 11 is a flow chart of an exemplary process for determining an accurate incident location according to some embodiments of the present application. The operations 1100 may be performed by the artificial intelligence system 100. For example, process 1100 may be implemented with a set of instructions (e.g., an application program) stored in read only memory 230 or random access memory 240. Processor 220 may execute the set of instructions and, when executing the instructions, may perform flow 1100. The operations of the processes shown below are merely illustrative. In some embodiments, flow 1100 may be accomplished with one or more additional operations not described and/or without one or more of the operations discussed. Additionally, the order of operations shown in FIG. 11 and described below is not intended to be limiting.

In operation 1110, for each of a plurality of result clusters, processing engine 112 (or processor 220) may determine a dwell time based on the number of points in the result cluster. The dwell time may be a duration of time that the target user terminal dwells at the area associated with the result cluster. For example, when the target user terminal stops at an area corresponding to a result cluster and acquires a point corresponding to one position every 5 seconds, and the number of points in the result cluster corresponding to the position of the target user terminal is 200. The processing engine may calculate that the dwell time associated with the result cluster is 1000 seconds (200 x 5).

In operation 1120, processing engine 112 (or processor 220) may determine whether a dwell time associated with the result cluster is greater than a time threshold. In some embodiments, the time threshold may be predetermined by the processing engine 112 or its user according to different application scenarios. For example, the time threshold may be determined based on traffic conditions on the road on which the vehicle is located. As another example, the time threshold may be determined based on a maximum wait time for a traffic signal light. In some embodiments, a determination that the dwell time is greater than the time threshold may result in the processing engine 112 removing clusters of results for vehicles with short dwells or simply waiting for traffic lights.

In some embodiments, if the dwell time associated with the result cluster is greater than the time threshold, processing engine 112 may proceed to operation 1130. If the dwell time associated with the result cluster is not greater than the time threshold, the processing engine 112 may proceed to operation 1140.

In operation 1130, the processing engine 112 (or the processor 220) may take the result point corresponding to the result cluster as the precise incident location. For example, when the vehicle remains in an area for a sufficient period of time, the processing engine 112 may predict that a traffic accident exists in the area. Thus, the processing engine 112 may take the result points corresponding to the result clusters as the precise accident site.

In operation 1140, the processing engine 112 (or the processor 220) may discard the corresponding incident record to proceed to another incident record to another target user terminal. For example, when the vehicle is only parked for a short time within an area, the processing engine 112 may predict that there is no traffic accident in the area. In some embodiments, the processing engine 112 may advance to another incident record for another target user terminal according to the methods described in fig. 6-11 herein.

Fig. 12 is a flow diagram of an exemplary process for determining at least one incident multi-occurrence segment according to some embodiments of the present application. The process 1200 may be performed by the artificial intelligence system 100. For example, process 1200 may be implemented with a set of instructions (e.g., an application program) stored in storage read only memory 230 or random access memory 240. Processor 220 may execute the set of instructions and, when executing the instructions, may be used to perform flow 1200. The operations of the processes shown below are merely illustrative. In some embodiments, flow 1200 may be accomplished with one or more additional operations not described and/or without one or more of the operations discussed. Additionally, the order of operations shown in FIG. 12 and described below is not intended to be limiting.

In operation 1210, the processing engine 112 (or the processor 220) may obtain a plurality of precise incident locations. In some embodiments, a plurality of precise accident sites may be determined by operating a first clustering process as described in fig. 6-11 herein. In some embodiments, the plurality of precise incident locations may be predetermined and stored in a storage medium (e.g., memory 140, read-only memory 230, random access memory 240, etc.) of the artificial intelligence system 100.

In operation 1220, the processing engine 112 (or the processor 220) may run a second clustering process to determine a plurality of result clusters, with a plurality of precise accident sites as inputs to the second clustering process.

In some embodiments, the second clustering process may be the same as the first clustering process. For example, the processing engine 112 may identify a plurality of points corresponding to a plurality of precise accident sites on a map. Processing engine 112 may determine the clusters of results through a point identification operation. For example, the processing engine 112 may select a candidate cluster from a plurality of points corresponding to a plurality of precise accident sites. The candidate cluster of points may include all of the plurality of points or a portion of the plurality of points. Processing engine 112 may select a candidate point from a candidate cluster of points. The candidate points may be any value calculated based on the points in the candidate cluster, such as average coordinates, weighted average coordinates, and the like, or any combination thereof. Processing engine 112 may perform a first iterative operation comprising a plurality of iterations until a first stop condition is satisfied. During each iteration of the first iterative operation, processing engine 112 may identify one of the clusters of targets within a predetermined distance from the center point as a candidate cluster for a point from the target clusters using the candidate point generated in the last iteration as the center point and using the candidate cluster generated in the last iteration as the target cluster for the point, and determine one of the candidate clusters for the point as the candidate point. The candidate cluster of points may be updated to a new one within a predetermined distance from the center point. In some embodiments, the preset distance may be predetermined by the processing engine 112 or a user thereof. For example, the preset distance may be determined based on an area of the corresponding precise accident location, a road type of the corresponding precise accident location, or the like, or any combination thereof. For example only, the preset distance may be 300 meters, 500 meters, 1000 meters, etc. If the candidate cluster of points identified in the last iteration of the first iterative operation satisfies the first stop condition, processing engine 112 may obtain the candidate cluster of points corresponding to the last iteration as the result cluster of the first iterative operation. In addition, processing engine 112 may perform a second iterative operation comprising a plurality of iterations until a second stop condition is satisfied to obtain a remaining portion of the plurality of result clusters. During each iteration of the second iterative operation, processing engine 112 may remove a result cluster of the points identified in the first iterative operation from the plurality of points to update the plurality of points and determine another cluster of the plurality of result clusters from the point identification operation described above. After determining the plurality of result clusters for the plurality of iterations, the processing engine 112 may obtain the clusters for the plurality of precise accident locations in descending order of density of the precise accident locations. The first cluster of results may be the cluster of the most dense accident sites, which may indicate that the traffic accident is more likely to occur on the road segment associated with the first cluster of results.

In operation 1230, for each of the plurality of result clusters, the processing engine 112 (or the processor 220) may treat the road segment associated with the result cluster as an incident-prone segment.

In some embodiments, the road segment may be a location or area on a road. In some embodiments, processing engine 112 may determine the road segments based on the result clusters. For example, the processing engine 112 may calculate a center point of a point in the result cluster and designate a location near the center point as an incident multi-occurrence segment. For another example, the processing engine 112 may treat the area within a preset distance from the center point as an incident multi-occurrence segment. The preset distance may be determined according to different application scenarios. For example, an area within 500 meters from the center point may be designated as a multi-incident zone.

Fig. 13 is a flow diagram of an exemplary process for determining at least one incident multi-occurrence segment according to some embodiments of the present application. The process 1300 may be performed by the artificial intelligence system 100. For example, process 1300 may be implemented with a set of instructions (e.g., an application program) stored in read only memory 230 or random access memory 240. The processor 220 may execute the set of instructions and, when executing the instructions, may be configured to perform the flow 1300. The operations of the processes shown below are merely illustrative. In some embodiments, flow 1300 may be accomplished with one or more additional operations not described and/or without one or more of the operations discussed. Additionally, the order of operations shown in FIG. 13 and described below is not intended to be limiting.

In operation 1310, for each of a plurality of result clusters, the processing engine 112 (or processor 220) may determine a number of points in the result cluster. In some embodiments, the number of points may indicate the frequency of traffic accidents. The greater the number of points, the higher the frequency of traffic accidents.

In operation 1320, the processing engine 112 (or the processor 220) may determine whether the number of points is greater than the density threshold. In some embodiments, the density threshold may be predetermined by the processing engine 112 or its user according to different application scenarios. For example, the density threshold may be determined based on the road type of the road corresponding to the result cluster. For another example, the density threshold value may be a value not less than 2. That is, if two or more precise traffic accident sites exist in the result cluster, the area corresponding to the result cluster may be an accident-prone area.

In some embodiments, if the number is greater than the density threshold, the processing engine 112 may proceed to operation 1330. If the number is not greater than the density threshold, the processing engine 112 may proceed to operation 1340.

In process 1330, processing engine 112 (or processor 220) may determine a road segment corresponding to the result cluster based on the points in the result cluster. For example, if the number of points in the result cluster is sufficiently high, indicating that the frequency of traffic accidents occurring on the road segment corresponding to the result cluster is high, the processing engine 112 may predict that the corresponding road segment is an accident-prone segment.

In process 1340, processing engine 112 (or processor 220) may skip the result cluster. For example, if the number of points in the result cluster is low, which indicates that the frequency of traffic accidents occurring on the road segment corresponding to the result cluster is low, the processing engine 112 may predict that the corresponding road segment is not a multi-accident road segment and then enter another result cluster to determine whether there is a multi-accident segment.

FIG. 14 is a flow diagram of an exemplary process for obtaining a plurality of incident records according to some embodiments of the present application. The process 1400 may be performed by the artificial intelligence system 100. For example, process 1400 may be implemented with a set of instructions (e.g., an application program) stored in read only memory 230 or random access memory 240. Processor 220 may execute the set of instructions and, when executing the instructions, may be configured to perform process 1400. The operations of the processes shown below are merely illustrative. In some embodiments, flow 1400 may be accomplished with one or more additional operations not described, and/or without one or more of the operations discussed. Additionally, the order of operations shown in FIG. 14 and described below is not intended to be limiting.

In operation 1410, the processing engine 112 (or the processor 220, the data consolidation module 450) may receive a plurality of incident reports. In some embodiments, each of the plurality of incident reports is associated with a corresponding target user terminal and includes a recorded incident time and a recorded incident location.

In some embodiments, when a traffic accident occurs, a user of the target user terminal (e.g., a driver of a vehicle in which the traffic accident occurred, passengers of the vehicle, workers of an insurance company handling the traffic accident, traffic police handling the traffic accident, or accident witnesses) may report the accident, seek insurance services, roadside assistance, ambulance services, fire truck assistance, and the like, or any combination thereof. The incident report may include a recorded incident time and a recorded incident location. The recorded time of the incident may be a time reported by a user of the user terminal. In some embodiments, the recorded accident time may be different from the actual accident time at which the traffic accident occurred. For example, the actual time of occurrence is 15:00 and the user reports an occurrence of an accident of about 15: 24. The recorded accident location may be a location reported by a user of the user terminal. In some embodiments, the recorded incident location may be different from the actual incident location reported by the user of the user terminal. For example, the actual accident location is the intersection of road No. 1 and road No. 2, and the recorded accident location is near road No. 1.

In operation 1420, the processing engine 112 (or the processor 220, the data merging module 450) may obtain a plurality of historical locations of the target user terminal.

In some embodiments, the target user terminal may include a device for acquiring positioning technology of a real-time location of the vehicle. For example, the target user terminal may be a mobile terminal of a passenger or a mobile terminal of a driver of the vehicle, a vehicle navigation system, a vehicle positioning system, etc., or any combination thereof. The real-time location may be stored as a plurality of historical locations in a storage medium (e.g., memory 140, read-only memory 230, random access memory 240, etc.) of the artificial intelligence system 100. For example, the target user terminal may acquire a location every preset period of time (e.g., every 5 seconds, every 10 seconds, every 30 seconds, etc.), and transmit the location and a time corresponding to the location to the storage medium.

In process 1430, for each of the plurality of incident reports, the processing engine 112 (or the processor 220, the data merging module 450) may merge the respective recorded incident time and the recorded incident location with the historical location of the respective target user terminal to obtain an incident record associated with the respective target user terminal.

When the processing engine 112 obtains a traffic accident report for the vehicle, the processing engine 112 may access the storage medium to obtain a plurality of locations of the target user terminal occurring around the recorded accident time and/or around the recorded accident location by matching the recorded accident location to the plurality of historical locations. The plurality of locations at which the target user terminal occurs around the time of recording the incident may include locations at which the user terminal occurs during a period from a first preset time period before the time of recording the incident to a second preset time after the time of recording the incident. The first and/or second preset time periods may be determined by the processing engine 112 and its user. For example, when the recorded incident time is 15:00, the processing engine 112 may: 00-16: 00 obtain multiple locations of a target user terminal. The plurality of positions where the target user terminal appears near the recorded accident site may include a position where the user terminal appears within a range of a preset distance from the recorded accident site. The preset distance may be determined by the processing engine 112 and its user. For example, the recorded accident location is intersection 1, and the processing engine 112 may acquire a plurality of positions of the target user terminal in an area within a range of 5 km from the intersection 1.

Having thus described the basic concept, it may become apparent to those skilled in the art upon reading this detailed application that the foregoing detailed application is intended to be illustrative only and not limiting. Various alterations, improvements, and modifications may occur and are intended to those skilled in the art, though not expressly stated herein. Such alterations, improvements, and modifications are intended to be suggested by this disclosure, and are within the spirit and scope of the exemplary embodiments of this disclosure.

In addition, certain terminology has been used to describe embodiments of the application. For example, the terms "one embodiment," "an embodiment," and/or "some embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Therefore, it is emphasized and should be appreciated that two or more references to "one embodiment," "an embodiment," or "an alternative embodiment" in various portions of this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined as suitable in one or more embodiments of the application.

Moreover, those skilled in the art will appreciate that aspects of the present application may be illustrated and described herein in any patentable category or context, including any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement. Accordingly, aspects of the present application may be implemented entirely in hardware, entirely in software (including firmware, resident software, micro-code, etc.) or in a combination of software and hardware, which may generally be referred to herein as a "block," module, "" engine, "" unit, "" component "or" system. Furthermore, aspects of the present application may take the form of a computer program product embodied in one or more computer-readable media having computer-readable program code embodied therein.

A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including electromagnetic, optical, and the like, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable signal medium may be transmitted using any appropriate medium, including wireless, wireline, optical fiber cable, radio frequency, etc., or any suitable combination of the foregoing.

Computer program code for carrying out operations for aspects of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C + +, C #, VB, etc., a "C" programming language such as Visual Basic, Fortran1703, Perl, COBOL 1702, PHP, ABAP, a dynamic programming language such as Python, Ruby, and Groovy, or other programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (e.g., through the internet using an internet service provider) or in a cloud computing environment or to provide a service, such as software as a service (SaaS).

Furthermore, the described order of processing elements or sequences or the use of numbers, letters, or other designations is not intended to limit the claimed processes and methods to any order except as may be specified in the claims. While the above application discusses what are presently considered to be various useful embodiments of the present application by way of various examples, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover modifications and equivalent arrangements that are within the spirit and scope of the claimed embodiments. For example, while the implementations of the various components described above may be embodied in a hardware device, they may also be implemented as a software-only solution, such as an installation on an existing server or mobile device.

Similarly, it should be appreciated that in the foregoing description of embodiments of the application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of the contents of a single application. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed subject matter requires more features than are expressly recited in each claim. Rather, claimed subject matter may lie in less than all features of a single foregoing application embodiment.

In some embodiments, numbers expressing quantities or attributes used to describe and claim certain embodiments of the application are to be understood as being modified in some instances by the term "about", "approximately" or "substantially". For example, unless otherwise specified, "about," "approximately," or "substantially" may mean a ± 20% variation of the value it describes. Accordingly, in some embodiments, the numerical parameters set forth in the written description and attached claims are approximations that may vary depending upon the desired properties sought to be obtained by a particular embodiment. In some embodiments, numerical parameters should be construed in light of the number of reported significant digits and by applying ordinary rounding techniques. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of some embodiments of the application are approximations, the numerical values set forth in the specific examples are reported as precisely as possible.

Each patent, patent application, publication of a patent application, and other material, such as articles, books, descriptions, publications, documents, things, etc., cited herein is hereby incorporated by reference, to the extent that any filing history associated therewith, any document identified as such or as a matter of conflict with this document, or any document that may have a limiting effect on the broadest scope of claims presently or later presented for use in connection with this document. For example, if there is any inconsistency or conflict between the terms associated with any of the incorporated materials and the terms associated with this document when describing, defining and/or using, the terms in this document shall prevail.

Finally, it should be understood that the embodiments of the application as filed herein are a schematic illustration of the embodiments of the present application. Other modifications may be employed within the scope of the present application. Thus, by way of example, and not limitation, alternative configurations of embodiments of the present application may be used in accordance with the teachings herein. Accordingly, embodiments of the present application are not limited to that as shown and described.

45页详细技术资料下载

上一篇：一种医用注射器针头装配设备

下一篇：一种无人控制机器人的惯性传感器加热方法

Artificial intelligence system and method for predicting traffic accident occurrence place

相关技术

网友询问留言