Vehicle-mounted device, travel state estimation method, server device, information processing method, and travel state estimation system
阅读说明:本技术 车载装置、行驶状态推算方法、服务器装置、信息处理方法和行驶状态推算系统 (Vehicle-mounted device, travel state estimation method, server device, information processing method, and travel state estimation system ) 是由 小窪浩明 度会则男 中山和宪 于 2019-01-31 设计创作,主要内容包括:本发明能够不使用各种各样的传感器,而基于驾驶员发出的声音来推算驾驶员的心理状态会影响到的车辆的行驶状态。车载装置的特征在于,包括:声音收集部,其用于收集驾驶员发出的声音;行驶状态收集部,其用于收集表示车辆的行驶状态的行驶状态信息;数据库生成部,其用于将所收集的所述行驶状态信息和与所收集的所述声音对应的声音信息相关联地记录,来生成数据库;学习部,其用于将所生成的所述数据库中记录的所述声音信息与所述行驶状态信息的信息对作为学习数据来学习推算模型;和推算部,其用于使用所述推算模型,基于所述驾驶员发出的声音,来推算所述驾驶员的心理状态会影响到的所述车辆的所述行驶状态。(The present invention can estimate the driving state of a vehicle that is affected by the psychological state of a driver based on the sound emitted by the driver without using various sensors. The in-vehicle device is characterized by comprising: a sound collection unit for collecting a sound emitted by a driver; a travel state collection unit for collecting travel state information indicating a travel state of a vehicle; a database generation unit configured to generate a database by recording the collected travel state information and sound information corresponding to the collected sound in association with each other; a learning unit configured to learn an estimation model using information pairs of the sound information and the travel state information recorded in the database as learning data; and an estimation unit configured to estimate the traveling state of the vehicle that is affected by the psychological state of the driver, based on the sound emitted by the driver, using the estimation model.)
1. An in-vehicle apparatus, characterized by comprising:
a sound collection unit for collecting a sound emitted by a driver;
a travel state collection unit for collecting travel state information indicating a travel state of a vehicle;
a database generation unit configured to generate a database by recording the collected travel state information and sound information corresponding to the collected sound in association with each other;
a learning unit configured to learn an estimation model by using information pairs of the sound information and the travel state information recorded in the database as learning data; and
an estimation unit configured to estimate the traveling state of the vehicle that is affected by a psychological state of the driver, based on a sound emitted by the driver, using the estimation model.
2. The in-vehicle apparatus according to claim 1, characterized in that:
the learning unit generates the estimation model by supervised learning using the sound information in the learning data as an input vector and the travel state information in the learning data as a teacher label.
3. The in-vehicle apparatus according to claim 1, characterized in that:
The database generation unit generates the database by recording the travel state information collected before and after the collection time of the sound and sound information corresponding to the collected sound in association with each other.
4. The in-vehicle apparatus according to claim 1, characterized in that:
the sound collection section converts a sound emitted by the driver into a feature vector,
the database generation unit records the feature vector, which is the sound information corresponding to the collected sound, in association with the collected travel state information, and generates the database.
5. The in-vehicle apparatus according to claim 1, characterized in that:
the running state collection portion collects the running state information based on output values of at least 1 sensor of an acceleration sensor, a gyro sensor, and a fuel consumption rate sensor.
6. The in-vehicle apparatus according to claim 1, characterized in that:
further, the vehicle driving system further includes a feedback generation unit that generates feedback to the driver in accordance with the estimated driving state.
7. The vehicle-mounted device according to claim 6, characterized in that:
further comprising a voice recognition portion for recognizing the collected voice of the driver,
The feedback generation unit generates the feedback to the driver in accordance with a voice recognition result of the voice of the driver and the estimated running state.
8. The in-vehicle apparatus according to claim 1, characterized in that:
also included is a vocalization facilitating portion for facilitating vocalization of the driver.
9. The vehicle-mounted device according to claim 8, characterized in that:
also comprises a driving state abnormity judging part for judging whether the driving state is abnormal or not,
the sound emission promoting unit promotes the driver to emit sound when the abnormal driving state is determined.
10. A travel state estimation method performed by an in-vehicle device, the method comprising:
a sound collection step of collecting a sound emitted by a driver;
a running state collection step of collecting running state information indicating a running state of a vehicle;
a database generation step of recording the collected travel state information and sound information corresponding to the collected sound in association with each other to generate a database;
a learning step of learning an estimation model by using information pairs of the sound information and the travel state information recorded in the database as learning data; and
An estimation step of estimating the running state of the vehicle, which is affected by the psychological state of the driver, based on the sound emitted by the driver, using the estimation model.
11. A travel state estimation system including an in-vehicle device and a server device connectable via a communication network, characterized in that:
the vehicle-mounted device includes:
a sound collection unit for collecting a sound emitted by a driver;
a travel state collection unit for collecting travel state information indicating a travel state of a vehicle; and
a 1 st communication unit for transmitting sound information corresponding to the collected sound and the travel state information to the server device,
the server apparatus includes:
a 2 nd communication unit configured to receive the sound information and the travel state information transmitted from the in-vehicle device;
a database generation unit configured to generate a database by recording the travel state information in association with the received sound information; and
a learning unit configured to learn an estimation model using information pairs of the sound information and the travel state information recorded in the database as learning data,
The vehicle-mounted device or the server device includes an estimation unit configured to estimate the traveling state of the vehicle that is affected by the psychological state of the driver, based on the sound emitted by the driver, using the estimation model.
12. A travel state estimation method of a travel state estimation system including an in-vehicle device and a server device connectable via a communication network, the travel state estimation method characterized by comprising:
a collection step, performed by the in-vehicle apparatus, of collecting a sound made by a driver and collecting traveling state information indicating a traveling state of a vehicle;
a transmission step performed by the in-vehicle device, of transmitting sound information corresponding to the collected sound and the travel state information to the server device;
a reception step performed by the server device, the reception step receiving the sound information and the travel state information transmitted from the in-vehicle device;
a database generation step performed by the server device to generate a database by recording the travel state information in association with the received sound information;
A learning step performed by the server device for learning an estimation model by using, as learning data, information pairs of the sound information and the travel state information recorded in the database; and
an estimation step performed by the in-vehicle device or the server device, using the estimation model, to estimate the running state of the vehicle that the psychological state of the driver may affect, based on the sound emitted by the driver collected by the in-vehicle device.
13. An in-vehicle apparatus that constitutes a travel state estimation system together with a server apparatus capable of receiving sound information corresponding to a sound of a driver and travel state information of a vehicle transmitted from the in-vehicle apparatus, generating a database in which the travel state information is recorded in association with the received sound information, and learning an estimation model using a pair of the sound information and the travel state information recorded in the generated database as learning data, the in-vehicle apparatus comprising:
a sound collection unit for collecting a sound emitted by a driver;
A running state collection unit for collecting the running state information indicating a running state of a vehicle;
a communication unit configured to transmit the sound information and the travel state information corresponding to the collected sound to the server device; and
an estimation unit configured to estimate the traveling state of the vehicle that is affected by the psychological state of the driver, based on the sound emitted by the driver, using the estimation model learned by the server device.
14. A running state estimation method for an in-vehicle apparatus that constitutes a running state estimation system together with a server apparatus capable of receiving sound information corresponding to a driver's voice and running state information of a vehicle transmitted from the in-vehicle apparatus, generating a database in which the running state information is recorded in association with the received sound information, and learning an estimation model using a pair of the sound information and the running state information recorded in the generated database as learning data, the running state estimation method comprising:
A sound collection step of collecting a sound emitted by a driver;
a running state collection step of collecting the running state information indicating a running state of a vehicle;
a transmission step of transmitting the sound information and the travel state information corresponding to the collected sound to the server apparatus; and
an estimation step of estimating the traveling state of the vehicle, which is affected by the psychological state of the driver, based on the sound emitted by the driver, using the estimation model learned by the server device.
15. A server device for constituting a running state estimation system together with an in-vehicle device capable of collecting a sound uttered by a driver and running state information indicating a running state of a vehicle, and transmitting sound information corresponding to the collected sound and the running state information, the server device characterized by comprising:
a communication unit configured to receive the sound information and the travel state information transmitted from the in-vehicle device;
a database generation unit configured to generate a database by recording the travel state information in association with the received sound information; and
And a learning unit configured to learn an estimation model by using information pairs of the sound information and the travel state information recorded in the database as learning data.
16. The server apparatus according to claim 15, wherein:
further comprising an estimation unit for estimating the running state of the vehicle that the psychological state of the driver may affect, based on the sound emitted by the driver, using the estimation model.
17. An information processing method of a server apparatus for constituting a travel state estimation system together with an in-vehicle apparatus capable of collecting a sound uttered by a driver and collecting travel state information indicating a travel state of a vehicle, and transmitting sound information corresponding to the collected sound and the travel state information, the information processing method characterized by comprising:
a reception step of receiving the sound information and the travel state information transmitted from the in-vehicle apparatus;
a database generation step of recording the travel state information in association with the received sound information to generate a database; and
A learning step of learning an estimation model by using information pairs of the sound information and the travel state information recorded in the database as learning data.
Technical Field
The invention relates to a vehicle-mounted device, a travel state estimation method, a server device, an information processing method, and a travel state estimation system. The present invention claims priority based on japanese laid-open application No. 2018-046788 filed on 3/14/2018, and the contents described in the above japanese application are incorporated by reference into the present application for a designated country where the incorporation by reference of documents is admitted.
Background
In recent years, dangerous driving by a driver of an automobile (hereinafter, referred to as a driver) has become a social problem, and various support functions for the driver during driving have been proposed.
For example, patent document 1 discloses a technique of estimating a psychological state of a driver from information on a driving operation of the driver and giving a warning to the driver in accordance with the estimated psychological state.
Disclosure of Invention
Technical problem to be solved by the invention
In general, as information for determining the psychological state of a driver, the movement of the driver, the frequency of blinking, the heart rate, and the like are known, but various sensors such as a camera and a biosensor are required to detect the information, and the installation cost and the installation space are problematic to ensure.
Further, the method disclosed in patent document 1 requires acquisition of information related to the driving operation of the driver, and therefore cannot be applied to a case where the driver does not participate in driving as a subject, such as automated driving which is expected to be widespread in the future. In the present situation, since the driver's attention obligation cannot be completely removed even during automatic driving, a technique capable of estimating the psychological state of the driver even during automatic driving is desired.
The present invention has been made in view of the above circumstances, and an object thereof is to enable estimation of a running state of a vehicle, which is influenced by a psychological state of a driver, based on a sound emitted by the driver without using various sensors.
Means for solving the problems
The present invention includes various means for solving at least part of the above-described technical problems, and the following can be exemplified. In order to solve the above-described problem, an in-vehicle device according to an aspect of the present invention includes: a sound collection unit for collecting a sound emitted by a driver; a travel state collection unit for collecting travel state information indicating a travel state of a vehicle; a database generation unit configured to generate a database by recording the collected travel state information and sound information corresponding to the collected sound in association with each other; a learning unit configured to learn an estimation model by using information pairs of the sound information and the travel state information recorded in the database as learning data; and an estimation unit configured to estimate the traveling state of the vehicle that is affected by the psychological state of the driver, based on the sound emitted by the driver, using the estimation model.
Effects of the invention
According to the present invention, the driving state of the vehicle, which is affected by the psychological state of the driver, can be estimated based on the sound emitted by the driver without using various sensors.
Technical problems, aspects, and effects other than those described above will become apparent from the following description of the embodiments.
Drawings
Fig. 1 is a block diagram showing a configuration example of an in-vehicle device according to a first embodiment of the present invention.
Fig. 2 is a diagram showing an example of a data structure of the voice-driving state database.
Fig. 3 is a diagram for explaining supervised learning.
Fig. 4 is a flowchart illustrating an example of the estimation model generation process.
Fig. 5 is a flowchart illustrating an example of the travel state estimation process.
Fig. 6 is a block diagram showing a configuration example of a traveling state estimation system according to a second embodiment of the present invention.
Fig. 7 is a block diagram showing a configuration example of a traveling state estimation system according to a third embodiment of the present invention.
Fig. 8 is a block diagram showing a first modification of the in-vehicle device according to the first embodiment of the present invention.
Fig. 9 is a block diagram showing a second modification of the in-vehicle device according to the first embodiment of the present invention.
Fig. 10 is a block diagram showing a third modification of the in-vehicle device according to the first embodiment of the present invention.
Fig. 11 is a diagram for explaining a method of determining an abnormality in the running state.
Fig. 12 is a block diagram showing a configuration example of a computer.
Detailed Description
Hereinafter, a plurality of embodiments of the present invention will be described based on the drawings. In all the drawings for describing the embodiments, the same components are denoted by the same reference numerals in principle, and redundant description thereof will be omitted. In the following embodiments, it is needless to say that the constituent elements (including the element steps) are not necessarily essential, except for the case where they are specifically illustrated and the case where they are considered to be obviously essential in principle. It goes without saying that when the expression "consisting of a", "having a", and "including a" is used, elements other than these elements are not excluded unless the case where only these elements are specifically indicated. Similarly, in the following embodiments, when referring to the shape, positional relationship, and the like of the constituent elements and the like, the case substantially similar to or similar to the shape and the like is included except for the case where it is specifically explicitly shown and the case where it is considered that it is obviously not the case in principle.
< correlation between sound emitted from driver and running state of vehicle >
First, the correlation between the sound emitted by the driver and the traveling state of the vehicle will be described.
Generally, a psychological state of a person has a correlation with a generated sound, and a person speaks fast and has a loud voice when being anxious, and the volume of the person becomes flat without fluctuation when being drowsy. The psychological state of the driver affects the driving of the driver, i.e., the driving state of the vehicle, and is easy to be confused to accelerate suddenly and to increase the steering wheel when the driver is anxious, and the driver is distracted to increase the sudden braking when the driver is drowsy. The present invention estimates a driving state of a vehicle that is affected by a psychological state of a driver, based on a sound emitted by the driver.
< example of Structure of in-vehicle device according to first embodiment of the present invention >
Fig. 1 shows a configuration example of an in-vehicle device according to a first embodiment of the present invention.
The in-vehicle device 10 collects a sound (utterance) emitted by a driver (user), and estimates a driving state of the driver based on the sound of the driver, in other words, estimates a traveling state of a vehicle in which the in-vehicle device 10 is mounted. The in-vehicle device 10 may be mounted in a vehicle such as an automobile as one device constituting a navigation system, an in-vehicle computer system, and the like. The estimated running state can be used for feedback such as warning the driver of attention.
Here, the voice generated by the driver is assumed to be a voice command generated by the driver to a navigation system or an in-vehicle computer system, for example. However, the collected voice of the driver is not limited to the voice command, and for example, conversation with a passenger or the like and self-speaking may be collected.
The in-vehicle device 10 includes a
The
In the estimation model generation process (to be described later), the
The microphone or the like used in the
The traveling
The DB generating
Fig. 2 shows an example of the data structure of the voice/traveling
In each data recorded in the voice/
The voice information field 1311 stores a feature vector of the voice input from the
In the traveling state information field 1312, a numerical value indicating the number of times of rapid acceleration or the like is recorded as traveling state information. Note that, instead of recording numerical values, evaluations such as "large", "normal", "small", "good", "bad", and the like, which are determined by comparing the number of times of rapid acceleration or the like with a predetermined threshold value, may be recorded.
Returning to fig. 1. The learning unit 14 generates the
The supervised learning by the learning section 14 is explained with reference to fig. 3. Fig. 3 is a schematic diagram of the feature vector of the audio signal of the teacher label marked with the driving state information drawn in the
The black circles in the figure indicate the distribution of the feature vectors of the teacher's voice in the travel state marked with "little rapid acceleration," little rapid braking, "and" good fuel consumption rate. The white triangles represent the distribution of feature vectors of the teacher's label sounds indicating a driving state with "little rapid acceleration," much rapid braking, "and" good fuel consumption. The black squares represent the distribution of feature vectors of the teacher's voice of the travel state marked with "much rapid acceleration," little rapid braking, "and" poor fuel consumption rate.
In the supervised learning by the learning unit 14, an
Therefore, in the
Returning to fig. 1. The
< estimation model creation processing by the in-vehicle device 10 >
Next, fig. 4 is a flowchart illustrating an example of the estimation model generation process performed by the in-vehicle device 10.
This estimation model generation process is started, for example, when the vehicle mounted with the in-vehicle device 10 starts running.
First, the
Next, the
Next, the learning unit 14 performs supervised learning using the learning data (information pair of the feature vector of the voice and the travel state information) recorded in the voice/
Thereafter, the in-vehicle device 10 returns the process to step S3, and repeats the steps from step S3 onward. By repeating the processing of steps S3 and S4, the learning unit 14 can perform supervised learning using a larger amount of learning data, and thus the accuracy of the generated
< traveling state estimation processing by the in-vehicle device 10 >
Next, fig. 5 is a flowchart illustrating an example of the travel state estimation process performed by the in-vehicle device 10.
The travel state estimation process is started when, for example, a vehicle mounted with the in-vehicle device 10 starts traveling, on the assumption that the
First, the
When determining that the feature vector of the sound has been input (YES in step S12), the
With the travel state estimation processing described above, the travel state of the vehicle that is affected by the psychological state of the driver can be estimated based on the voice produced by the driver without using a sensor that detects the movement of the driver, the frequency of blinking, the heart rate, or the like.
The purpose of the travel state information output from the in-vehicle device 10 is arbitrary, and an example thereof will be described in a modification example described later.
< example of configuration of travel state estimation system according to second embodiment of the present invention >
Next, fig. 6 shows a configuration example of a traveling state estimation system according to a second embodiment of the present invention.
The traveling state estimation system 20 is configured by a plurality of in-vehicle devices 30 and a server device 50 connected via a
In the in-vehicle device 30 and the server device 50, the components of the in-vehicle device 10 (fig. 1) are distributed, and the same components as those of the in-vehicle device 10 are denoted by the same reference numerals among the components of the in-vehicle device 30 and the server device 50, and the description thereof is appropriately omitted.
The in-vehicle device 30 has a configuration in which the
That is, the in-vehicle device 30 includes the
The
The travel
In the estimation model generation process, the communication unit 31 (corresponding to the 1 st communication unit of the present invention) associates the feature vector of the sound input from the
The server device 50 includes a
The
The learning unit 14 in the server device 50 generates the
The communication unit 51 (corresponding to the 2 nd communication unit of the present invention) receives the feature vector of the voice transmitted from each in-vehicle device 30 via the
In the travel state estimation system 20, the estimation model generation process is mainly executed by the server device 50, and the travel state estimation process is executed by the in-vehicle device 30. Since the server device 50 that mainly executes the estimation model generation process can be connected to a plurality of in-vehicle devices 30, it is easy to record more learning data than in the first embodiment in the sound/traveling
< example of configuration of travel state estimation system according to third embodiment of the present invention >
Next, fig. 7 shows a configuration example of a traveling state estimation system according to a third embodiment of the present invention.
The traveling
The components of the in-vehicle device 10 are distributed in the in-
The in-
That is, the in-
The
The travel
In the estimation model generation process, the communication unit 71 transmits the feature vector of the sound output by the
The
In the estimation model generation process, the
In the traveling
< first modification of the in-vehicle device according to the first embodiment of the present invention >
Next, fig. 8 shows a first modification of the in-vehicle device according to the first embodiment of the present invention.
The in-vehicle device 110 is obtained by adding a response generation unit 111 and an HMI (human machine Interface) unit 112 to the in-vehicle device 10 (fig. 1). Among the components of the in-vehicle device 110, the same components as those of the in-vehicle device 10 are denoted by the same reference numerals, and descriptions thereof are omitted as appropriate.
The response generation unit 111 (corresponding to a feedback generation unit of the present invention) receives the traveling state information output by the
The response according to the driving state of the vehicle in which the psychological state of the driver affects means that, for example, when "sudden braking is estimated as the driving state, the driver is low in wakefulness or high in the possibility of being distracted as the psychological state of the driver, and therefore, a message to remind the driver of" please pay attention to drive "or a message to suggest a break such as" take a lap near this "is output by outputting a sound from a speaker to the driver, or a message to suggest a break such as" take a break "is displayed in characters on a display.
Further, for example, when "rapid acceleration is large and fuel consumption is poor" is estimated as the driving state, since there is a high possibility of confusion or stress as the psychological state of the driver, a message to remind the driver to pay attention such as "please relax" is outputted by outputting a voice or a character, or a piece of music to be calmed down such as classical music or slow balladry is played.
With the in-vehicle device 110 described above, it is possible to estimate the driving state that the psychological state of the driver may affect based on the sound emitted by the driver without using various sensors, and it is possible to appropriately support the driver with feedback (response) according to the estimated driving state.
< second modification of the in-vehicle device according to the first embodiment of the present invention >
Next, fig. 9 shows a second modification of the in-vehicle device according to the first embodiment of the present invention.
The in-
However, in the travel state estimation process, the
The voice recognition unit 121 performs voice recognition processing on the voice signal of the driver input from the
The
The response according to the driving state and the utterance indicates that, for example, when the utterance of the driver is "music to be played", and the driving state is estimated as "rapid acceleration is high, fuel consumption is poor", the psychological state of the driver is estimated to be hurry or tense, and therefore, music such as classical music or slow balladry is selected and played in order to calm down the mood of the driver. On the other hand, when it is estimated that "sudden braking is excessive" as the traveling state, the psychological state of the driver can be estimated that there is a possibility that the awake state is low (drowsy state), and therefore, a fast-paced music that catches up with drowsiness is selected and played.
Further, for example, when the content of the voice of the driver is "search for a restaurant" and "no sudden acceleration or sudden braking (ordinary state)" is estimated as the traveling state, the psychological state of the driver can be estimated to be stable and sufficient in time, and therefore, a restaurant that meets the preset preference of the driver is searched for and the search result is output. On the other hand, when "the rapid acceleration is large and the fuel consumption rate is poor" is estimated as the traveling state, the psychological state of the driver can be estimated as anxiety and the time is not sufficient, and therefore, a restaurant that can arrive as quickly as possible is searched for with priority over the preference of the driver, and the search result is output.
With the in-
Further, with the in-
< third modification of the in-vehicle device according to the first embodiment of the present invention >
Next, fig. 10 shows a third modification of the in-vehicle device according to the first embodiment of the present invention.
The in-vehicle device 140 is obtained by adding a running state abnormality determination unit 141, a sound emission promotion unit 142, and an HMI unit 143 to the in-vehicle device 10 (fig. 1). Among the components of the in-vehicle device 140, the same components as those of the in-vehicle device 10 are denoted by the same reference numerals, and description thereof is omitted as appropriate.
However, the travel
The running state abnormality determination unit 141 detects an abnormal running state deviating from the normal running state based on the running state information input from the running
Fig. 11 shows a time-series change in the frequency of abnormal driving (sudden acceleration, sudden braking, sudden steering, etc.) used for the detection and determination of the abnormal driving state by the driving state abnormality determination unit 141, where the horizontal axis shows time and the vertical axis shows frequency.
The running state abnormality determination unit 141 counts the frequency of abnormal driving based on the running state information input from the running
The sound emission promoting unit 142 generates an inquiry message for promoting the driver to emit a sound, for example, "is there no time to take a break? "," will arrive at noon. This searches for restaurants asking me to tell what food you want to eat. "," listen to the music bar. Do you want to play an album of which singer? "and the like and outputs the inquiry word to the HMI unit 143. The inquiry message may be selected from previously prepared messages according to the driving state, time, and the like.
The HMI unit 143 presents the query generated by the sound emission promoting unit 142 to the driver as, for example, an audio message or a screen display using, for example, a speaker or a display (both not shown). The speaker or the like used in the HMI unit 143 may be provided for the in-vehicle device 140, or may be a speaker or the like provided in a vehicle.
With the in-vehicle device 140 described above, the voice of the driver is prompted when it is determined that the vehicle is in the abnormal driving state, and therefore, the voice of the driver can be collected actively, and the learning data of the supervised learning can be collected efficiently. Therefore, the accuracy of the generated
The first to third modifications described above may be combined as appropriate. That is, for example, the traveling state abnormality determination unit 141 and the sound emission promotion unit 142 in the third modification may be added to the first modification and the second modification.
The second and third embodiments of the present invention described above may be modified in the same manner as the first to third modified examples described above.
The in-
Fig. 12 is a block diagram showing a configuration example of hardware of a computer that realizes the in-vehicle device 10 and the like by a program.
In the computer 200, a CPU (Central Processing Unit) 201, a ROM (read Only Memory) 202, and a RAM (Random Access Memory) 203 are connected to each other via a
The
The input/
The
In the computer 200 configured as described above, the
The program executed by the computer 200(CPU 201) may be provided, for example, by being recorded in a
In the computer 200, the program may be installed to the
The program executed by the computer 200 may be a program that performs processing in time series in the order described in the present specification, or may be a program that performs processing in parallel or at a necessary timing such as calling.
The effects described in the present specification are merely exemplary and not restrictive, and other effects may be provided.
The present invention is not limited to the above-described embodiments, and includes various modifications. For example, the above embodiments have been described in detail to explain the present invention in an easily understandable manner, but the present invention is not necessarily limited to including all the components described. A part of the constituent elements of one embodiment may be replaced with the constituent elements of another embodiment, or the constituent elements of another embodiment may be added to the constituent elements of one embodiment. It is also possible to add, delete, or replace some of the components of the embodiments with other components.
A part or all of the above-described components, functions, processing units, processing methods, and the like may be realized by hardware by designing them with an integrated circuit, for example. The components, functions, and the like described above may be implemented by software by interpreting and executing a program that implements the respective functions by a processor. Information such as programs, tables, and files for realizing the respective functions can be stored in a memory, a storage device such as a hard disk or an SSD, or a recording medium such as an IC card, an SD card, or a DVD. In addition, regarding the control lines and the information lines, only portions considered necessary for the description are shown, and not all the control lines and the information lines on the product are necessarily shown. In practice, it is also considered that almost all the components are connected to each other.
The present invention can be provided not only in the form of an in-vehicle device, a travel state estimation method, a server device, and a travel state estimation system, but also in various forms such as a computer-readable program.
Description of the reference numerals
10 … … vehicle-mounted device, 11 … … sound collection section, 12 … … running state collection section, 13 … … DB generation section, 13 … … generation section, 14 … … learning section, 15 … … estimation model, 16 … … estimation section, 20 … … running state estimation system, 21 … … communication section, 30 … … vehicle-mounted device, 31 … … communication section, 40 … … communication network, 50 … … server device, 51 … … communication section, 60 … … running state estimation system, 70 … … vehicle-mounted device, 71 … … communication section, 80 … … server device, 81 … … communication section, 100 … … input vector space, 101 … … area, 102 … … area, 103 … … area, 104 … … identification plane, 105 … … identification plane, 110 … … vehicle-mounted device, 111 … … response generation section, 112 … … section, 120 … … vehicle-mounted device, 121 … … sound identification section, 122 … … response generation section, 123 … … HMI unit, 130 … … in-vehicle device, 140 … … in-vehicle device, 141 … … running state abnormality determination unit, 142 … … sound emission promotion unit, 143 … … HMI unit, 200 … … computer, 201 … … CPU, 202 … … ROM, 203 … … RAM, 204 … … bus, 205 … … input/output interface, 206 … … input unit, 207 … … output unit, 208 … … storage unit, 209 … … communication unit, 210 … … driver, 211 … … removable medium.
- 上一篇:一种医用注射器针头装配设备
- 下一篇:一种声源分离方法、装置及设备