Vehicle-based scenic spot recommendation method, device, equipment, medium and program product

文档序号：1937594 发布日期：2021-12-07 浏览：16次中文

阅读说明：本技术 基于车辆的景点推荐方法、装置、设备、介质及程序产品 (Vehicle-based scenic spot recommendation method, device, equipment, medium and program product ) 是由杨广煜于 2021-09-15 设计创作，主要内容包括：本申请提供了一种基于车辆的景点推荐方法、装置、设备、存储介质及计算机程序产品,应用于车载场景；方法包括：获取车辆当前所处的地理位置,并获取所述车辆当前所处环境的环境图像；确定与所述地理位置相对应的景点,并获取所述景点的至少一张景观图像；将所述环境图像分别与各所述景观图像进行匹配,得到相应的匹配度；当基于得到的所述匹配度,确定匹配条件得到满足时,将所述景点确定为目标景点；获取所述目标景点对应的景点推荐信息,并通过所述车载终端,输出所述景点推荐信息；通过本申请,能够提高景点推荐的精确度。(The application provides a vehicle-based scenic spot recommendation method, device, equipment, storage medium and computer program product, which are applied to a vehicle-mounted scene; the method comprises the following steps: acquiring the current geographical position of a vehicle, and acquiring an environment image of the current environment of the vehicle; determining a sight spot corresponding to the geographic position, and acquiring at least one landscape image of the sight spot; matching the environment image with each landscape image respectively to obtain corresponding matching degree; when the matching condition is determined to be met based on the obtained matching degree, determining the scenic spot as a target scenic spot; obtaining scenic spot recommendation information corresponding to the target scenic spot, and outputting the scenic spot recommendation information through the vehicle-mounted terminal; through the application, the accuracy of scenic spot recommendation can be improved.)

1. The vehicle-based scenic spot recommendation method is applied to a vehicle-mounted terminal, and comprises the following steps:

acquiring the current geographical position of a vehicle, and acquiring an environment image of the current environment of the vehicle;

determining a sight spot corresponding to the geographic position, and acquiring at least one landscape image of the sight spot;

matching the environment image with each landscape image respectively to obtain corresponding matching degree;

when the matching condition is determined to be met based on the obtained matching degree, determining the scenic spot as a target scenic spot;

and obtaining the sight spot recommendation information corresponding to the target sight spot, and outputting the sight spot recommendation information through the vehicle-mounted terminal.

2. The method of claim 1, wherein said obtaining a current geographic location of a vehicle comprises:

positioning the vehicle through a global positioning system chip arranged in the vehicle to obtain first positioning information;

the vehicle is positioned through a Location Based Service (LBS) to obtain second positioning information;

and determining the current geographic position of the vehicle by combining the first positioning information and the second positioning information.

3. The method of claim 1, wherein said obtaining an environmental image of an environment in which the vehicle is currently located comprises:

in the running process of the vehicle, an environment image of the current environment of the vehicle is acquired through a camera arranged on the vehicle.

4. The method of claim 1, wherein said obtaining an environmental image of an environment in which the vehicle is currently located comprises:

obtaining a sight spot position corresponding to at least one candidate sight spot;

determining a distance between each of the candidate sights and the vehicle based on each of the sight locations and the geographic location;

when the distance between at least one candidate sight point and the vehicle is lower than a distance threshold value, acquiring an environment image of the environment where the vehicle is located currently.

5. The method of claim 1, wherein the determining the sights corresponding to the geographic locations comprises:

obtaining a scenery spot area range corresponding to at least one candidate scenery spot;

determining a target scenery spot area range where the vehicle is located currently based on each scenery spot area range and the geographic position;

and determining the candidate scenery spot corresponding to the target scenery spot area range as the scenery spot corresponding to the geographic position.

6. The method of claim 1, wherein the determining the sights corresponding to the geographic locations comprises:

obtaining a sight spot position corresponding to at least one candidate sight spot;

determining a distance between each of the candidate sights and the vehicle based on each of the sight locations and the geographic location;

and determining the candidate scenic spots with the distance between the candidate scenic spots and the vehicle meeting the distance condition as the scenic spots corresponding to the geographic position.

7. The method of claim 1, wherein said matching the environment image with each of the landscape images to obtain a corresponding degree of matching comprises:

extracting the features of the environment images to obtain corresponding environment image features, and extracting the features of the landscape images to obtain corresponding landscape image features;

matching the environmental image features with the landscape image features respectively to obtain corresponding feature matching degrees;

and taking the feature matching degree of the environment image features and each landscape image feature as the matching degree of the environment image and each landscape image.

8. The method of claim 1, wherein said matching the environment image with each of the landscape images to obtain a corresponding degree of matching comprises:

the following processing is respectively executed for each landscape image:

inputting the landscape image and the environment image into a machine learning model;

and predicting the matching degree of the landscape image and the environment image through the machine learning model to obtain the matching degree between the landscape image and the environment image.

9. The method of claim 1, wherein the method further comprises:

when the number of the landscape images is multiple, acquiring the number of target landscape images, of the multiple landscape images, of which the matching degree with the environment image reaches a matching degree threshold value;

when the number reaches a target number, determining that the matching condition is satisfied.

10. The method of claim 1, wherein the obtaining the sight recommendation information corresponding to the target sight comprises:

acquiring a recommendation information template for generating scenic spot recommendation information and scenic spot recommendation content corresponding to the target scenic spot;

and generating the sight spot recommendation information corresponding to the target sight spot based on the sight spot recommendation content and the recommendation information template.

11. The method of claim 1, wherein the outputting, by the vehicle-mounted terminal, the attraction recommendation information comprises:

when a plurality of target scenic spots are available, acquiring a recommendation sequence corresponding to each target scenic spot;

and sequentially outputting the scenic spot recommendation information through the vehicle-mounted terminal according to the recommendation sequence.

12. The method of claim 1, wherein the method further comprises:

acquiring real-time scenery spot data in the target scenery spot;

and outputting corresponding sight spot prompt information based on the real-time sight spot data, wherein the sight spot prompt information is used for prompting the recommendation degree of going to the target sight spot.

13. The method of claim 1, wherein the method further comprises:

presenting navigation function items corresponding to the scenic spot recommendation information;

in response to a triggering operation for the navigation function item, presenting navigation information for guiding the vehicle from a current location to the target attraction.

14. The method of claim 1, wherein the outputting, by the vehicle-mounted terminal, the attraction recommendation information comprises:

through the audio output unit of the vehicle-mounted terminal, the scenic spot recommendation information in the audio format is played, and

and presenting the scenic spot recommendation information comprising at least one of text, image and video through a display unit of the vehicle-mounted terminal.

15. The utility model provides a sight spot recommendation device based on vehicle which characterized in that is applied to vehicle mounted terminal, the device includes:

the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring the current geographic position of a vehicle and acquiring an environment image of the current environment of the vehicle;

the first determination module is used for determining the scenic spot corresponding to the geographic position and acquiring at least one landscape image of the scenic spot;

the matching module is used for matching the environment image with each landscape image respectively to obtain corresponding matching degree;

the second determination module is used for determining the scenic spot as a target scenic spot when the matching condition is determined to be met based on the obtained matching degree;

and the output module is used for acquiring the scenic spot recommendation information corresponding to the target scenic spot and outputting the scenic spot recommendation information through the vehicle-mounted terminal.

16. An electronic device, characterized in that the electronic device comprises:

a memory for storing executable instructions;

a processor configured to implement the vehicle-based attraction recommendation method of any of claims 1-14 when executing executable instructions stored in the memory.

17. A computer readable storage medium storing executable instructions, wherein the executable instructions, when executed by a processor, implement the vehicle-based attraction recommendation method of any one of claims 1-14.

18. A computer program product comprising a computer program or instructions, wherein the computer program or instructions, when executed by a processor, implement the vehicle-based attraction recommendation method of any one of claims 1-14.

Technical Field

The present application relates to the field of information processing technologies, and in particular, to a vehicle-based scenic spot recommendation method, apparatus, device, storage medium, and computer program product.

Background

In the related art, when recommending sights, generally, a position of a current position of a user is located, and then sights corresponding to the located position (for example, sights near the located position) are recommended to the user. However, since the positioning processing has a certain blind area, for example, the accurate positioning cannot be realized in the indoor, in-car, under cloudy conditions, etc., the positioning of the user position is inaccurate, so that when the scenic spot recommendation is performed based on the positioning position, the recommended scenic spot is not accurate enough, and the situation of invalid recommendation exists.

Disclosure of Invention

The embodiment of the application provides a vehicle-based scenic spot recommendation method, device, equipment, storage medium and computer program product, which can improve accuracy of scenic spot recommendation.

The technical scheme of the embodiment of the application is realized as follows:

the embodiment of the application provides a scenic spot recommendation method based on a vehicle, which is applied to a vehicle-mounted terminal and comprises the following steps:

acquiring the current geographical position of a vehicle, and acquiring an environment image of the current environment of the vehicle;

determining a sight spot corresponding to the geographic position, and acquiring at least one landscape image of the sight spot;

matching the environment image with each landscape image respectively to obtain corresponding matching degree;

when the matching condition is determined to be met based on the obtained matching degree, determining the scenic spot as a target scenic spot;

and obtaining the sight spot recommendation information corresponding to the target sight spot, and outputting the sight spot recommendation information through the vehicle-mounted terminal.

The embodiment of the application further provides a scenic spot recommendation device based on the vehicle, is applied to the vehicle mounted terminal, includes:

the first determination module is used for determining the scenic spot corresponding to the geographic position and acquiring at least one landscape image of the scenic spot;

the matching module is used for matching the environment image with each landscape image respectively to obtain corresponding matching degree;

the second determination module is used for determining the scenic spot as a target scenic spot when the matching condition is determined to be met based on the obtained matching degree;

In the above scheme, the obtaining module is further configured to perform positioning processing on the vehicle through a global positioning system chip arranged in the vehicle to obtain first positioning information;

the vehicle is positioned through a Location Based Service (LBS) to obtain second positioning information;

and determining the current geographic position of the vehicle by combining the first positioning information and the second positioning information.

In the above scheme, the obtaining module is further configured to collect an environment image of an environment where the vehicle is currently located through a camera provided on the vehicle during a driving process of the vehicle.

In the above scheme, the obtaining module is further configured to obtain a scenery spot position corresponding to at least one candidate scenery spot;

determining a distance between each of the candidate sights and the vehicle based on each of the sight locations and the geographic location;

In the above scheme, the first determining module is further configured to obtain a scenic spot area range corresponding to at least one candidate scenic spot;

determining a target scenery spot area range where the vehicle is located currently based on each scenery spot area range and the geographic position;

and determining the candidate scenery spot corresponding to the target scenery spot area range as the scenery spot corresponding to the geographic position.

In the above scheme, the first determining module is further configured to obtain a sight spot position corresponding to at least one candidate sight spot;

determining a distance between each of the candidate sights and the vehicle based on each of the sight locations and the geographic location;

In the above scheme, the matching module is further configured to perform feature extraction on the environment images to obtain corresponding environment image features, and perform feature extraction on each landscape image to obtain corresponding landscape image features;

matching the environmental image features with the landscape image features respectively to obtain corresponding feature matching degrees;

and taking the feature matching degree of the environment image features and each landscape image feature as the matching degree of the environment image and each landscape image.

In the foregoing solution, the matching module is further configured to perform the following processing for each of the landscape images:

inputting the landscape image and the environment image into a machine learning model;

In the above scheme, the second determining module is further configured to, when the number of the landscape images is multiple, obtain the number of target landscape images of the multiple landscape images whose matching degree with the environment image reaches a matching degree threshold;

when the number reaches a target number, determining that the matching condition is satisfied.

In the above scheme, the output module is further configured to obtain a recommendation information template for generating the scenic spot recommendation information and scenic spot recommendation content corresponding to the target scenic spot;

and generating the sight spot recommendation information corresponding to the target sight spot based on the sight spot recommendation content and the recommendation information template.

In the above scheme, the output module is further configured to, when a plurality of target scenic spots are available, obtain a recommendation sequence corresponding to each of the target scenic spots;

and sequentially outputting the scenic spot recommendation information through the vehicle-mounted terminal according to the recommendation sequence.

In the above scheme, the output module is further configured to obtain real-time scenery spot data in the target scenery spot;

In the above scheme, the output module is further configured to present a navigation function item corresponding to the scenic spot recommendation information;

in response to a triggering operation for the navigation function item, presenting navigation information for guiding the vehicle from a current location to the target attraction.

In the above scheme, the output module is further configured to play the scenic spot recommendation information in an audio format through an audio output unit of the vehicle-mounted terminal, and the output module is further configured to play the scenic spot recommendation information in an audio format

And presenting the scenic spot recommendation information comprising at least one of text, image and video through a display unit of the vehicle-mounted terminal.

An embodiment of the present application further provides an electronic device, including:

a memory for storing executable instructions;

and the processor is used for realizing the vehicle-based sight spot recommendation method provided by the embodiment of the application when the executable instructions stored in the memory are executed.

The embodiment of the application also provides a computer-readable storage medium, which stores executable instructions, and when the executable instructions are executed by a processor, the vehicle-based scenic spot recommendation method provided by the embodiment of the application is realized.

The embodiment of the present application further provides a computer program product, which includes a computer program or an instruction, and when the computer program or the instruction is executed by a processor, the vehicle-based sight spot recommendation method provided in the embodiment of the present application is implemented.

The embodiment of the application has the following beneficial effects:

the method comprises the steps of firstly obtaining a current geographic position of a vehicle and an environment image of the environment, obtaining at least one landscape image of a scenery spot corresponding to the geographic position, then determining the matching degree of the environment image of the environment where the vehicle is located and each landscape image of the scenery spot corresponding to the geographic position, determining the scenery spot as a target scenery spot when determining that the matching condition is met based on the matching degree, and further obtaining and outputting scenery recommendation information corresponding to the target scenery spot to realize recommendation of the target scenery spot.

When the scenic spot recommendation is performed, the current geographic position of the vehicle is combined with the environment image of the environment, and the obtained geographic position of the vehicle is ensured to be accurate when the matching condition is determined to be met based on the matching degree of the environment image and the scenic image of the scenic spot corresponding to the geographic position, so that the scenic spot corresponding to the geographic position is recommended as the target scenic spot, and the accuracy of scenic spot recommendation is improved.

Drawings

FIG. 1 is an architectural diagram of a vehicle-based attraction recommendation system 100 provided by an embodiment of the present application;

fig. 2 is a schematic structural diagram of an electronic device 500 for implementing a vehicle-based attraction recommendation method according to an embodiment of the present application;

FIG. 3 is a schematic flow chart of a vehicle-based sight recommendation method according to an embodiment of the present disclosure;

FIG. 4 is a schematic flow chart illustrating a process for determining sights corresponding to geographic locations according to an embodiment of the present application;

fig. 5 is a schematic flowchart of determining a matching degree between an environment image and each landscape image according to an embodiment of the present application;

FIG. 6 is a schematic diagram of scenic spot recommendation information provided in an embodiment of the present application;

fig. 7 is a schematic diagram of a procedure for generating the scenic spot recommendation information according to the embodiment of the present application;

FIG. 8 is a schematic representation of a navigation function provided by an embodiment of the present application;

FIG. 9 is a schematic flow chart of a vehicle-based sight recommendation method according to an embodiment of the present application;

fig. 10 is a schematic flowchart of a vehicle-based sight recommendation method according to an embodiment of the present application.

Detailed Description

In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be described in further detail with reference to the attached drawings, the described embodiments should not be considered as limiting the present application, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict.

In the following description, references to the terms "first \ second \ third" are only to distinguish similar objects and do not denote a particular order, but rather the terms "first \ second \ third" are used to interchange specific orders or sequences, where appropriate, so as to enable the embodiments of the application described herein to be practiced in other than the order shown or described herein.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the present application only and is not intended to be limiting of the application.

Before further detailed description of the embodiments of the present application, terms and expressions referred to in the embodiments of the present application will be described, and the terms and expressions referred to in the embodiments of the present application will be used for the following explanation.

1) The terminal comprises a client and an application program running in the terminal and used for providing various services, such as an instant messaging client and a video playing client.

2) In response to the condition or state on which the performed operation depends, one or more of the performed operations may be in real-time or may have a set delay when the dependent condition or state is satisfied; there is no restriction on the order of execution of the operations performed unless otherwise specified.

3) The Global Positioning System (GPS) is a high-precision radio navigation Positioning System based on artificial earth satellites, and can provide accurate geographic position, vehicle speed and precise time information anywhere in the world and in the near-earth space.

4) Location Based Service (LBS), Location Based Service Based on base station, and through telecommunication, mobile operator's radio communication network (such as GSM network, CDMA network) or external Location mode (such as GPS), obtain terminal user's Location Information (including Geographic coordinates, geodetic coordinates, etc.), under the support of Geographic Information System (GIS) platform, provide a value added Service of corresponding Service for user.

5) An Intelligent System (IBS) is a location service System constructed based on LBS, which also obtains location Information (including Geographic coordinates, geodetic coordinates, etc.) of a terminal user through a telecommunication network, a radio communication network of a mobile operator (such as a GSM network, a CDMA network) or an external location mode (such as GPS), and provides a value-added service of corresponding services for the user under the support of a Geographic Information System (GIS) platform.

6) A Geographic Information System (GIS), also called a Geographic Information System, is a specific and very important spatial Information System, which is a technical System for collecting, storing, managing, operating, analyzing, displaying and describing relevant Geographic distribution data in the whole or part of the space of the earth's surface layer (including the atmosphere) with the support of computer hardware and software systems.

7) Scale-invariant feature transform (SIFT), which is a local feature of an image, maintains invariance to rotation, Scale scaling, and brightness change, and also maintains a certain degree of stability to view angle change, affine transformation, and noise; the information quantity is rich, and the method is suitable for fast and accurate matching in a massive characteristic database.

Based on the above explanations of terms and terms involved in the embodiments of the present application, the following describes a vehicle-based sight recommendation system provided by the embodiments of the present application. Referring to fig. 1, fig. 1 is a schematic structural diagram of a vehicle-based attraction recommendation system 100 according to an embodiment of the present application, in order to support an exemplary application, a vehicle-mounted terminal 400 is connected to a server 200 through a network 300, where the network 300 may be a wide area network or a local area network, or a combination of the two, and data transmission is implemented using a wireless or wired link.

The vehicle-mounted terminal 400 is used for acquiring the current geographic position of the vehicle and acquiring an environment image of the current environment of the vehicle; sending the geographical location and the environment image to the server 200;

a server 200 for receiving the geographical position and the environment image transmitted by the in-vehicle terminal 400; determining a sight spot corresponding to the geographic position, and acquiring at least one landscape image of the sight spot; matching the environment image with each landscape image respectively to obtain corresponding matching degree; when the matching condition is determined to be satisfied based on the obtained matching degree, determining the scenic spot as a target scenic spot; obtaining sight spot recommendation information corresponding to a target sight spot, and sending the sight spot recommendation information corresponding to the target sight spot to the vehicle-mounted terminal 400;

and the vehicle-mounted terminal 400 is configured to receive the sight spot recommendation information corresponding to the target sight spot, and output the sight spot recommendation information corresponding to the target sight spot.

In practical application, the server 200 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a network service, cloud communication, a middleware service, a domain name service, a security service, a CDN, a big data and artificial intelligence platform, and the like. The in-vehicle terminal 400 and the server 200 may be directly or indirectly connected by a wired or wireless communication method, and the present application is not limited thereto.

Referring to fig. 2, fig. 2 is a schematic structural diagram of an electronic device 500 for implementing a vehicle-based attraction recommendation method according to an embodiment of the present application. In practical application, the electronic device 500 may be a server or a vehicle-mounted terminal shown in fig. 1, and the electronic device 500 is taken as the vehicle-mounted terminal shown in fig. 1 as an example to explain an electronic device implementing the vehicle-based sight spot recommendation method according to the embodiment of the present application, where the electronic device 500 provided in the embodiment of the present application includes: at least one processor 510, memory 550, at least one network interface 520, and a user interface 530. The various components in the electronic device 500 are coupled together by a bus system 540. It is understood that the bus system 540 is used to enable communications among the components. The bus system 540 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled as bus system 540 in fig. 2.

The Processor 510 may be an integrated circuit chip having Signal processing capabilities, such as a general purpose Processor, a Digital Signal Processor (DSP), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like, wherein the general purpose Processor may be a microprocessor or any conventional Processor, or the like.

The user interface 530 includes one or more output devices 531 enabling presentation of media content, including one or more speakers and/or one or more visual display screens. The user interface 530 also includes one or more input devices 532, including user interface components to facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons and controls.

The memory 550 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid state memory, hard disk drives, optical disk drives, and the like. Memory 550 optionally includes one or more storage devices physically located remote from processor 510.

The memory 550 may comprise volatile memory or nonvolatile memory, and may also comprise both volatile and nonvolatile memory. The nonvolatile memory may be a Read Only Memory (ROM), and the volatile memory may be a Random Access Memory (RAM). The memory 550 described in embodiments herein is intended to comprise any suitable type of memory.

In some embodiments, memory 550 can store data to support various operations, examples of which include programs, modules, and data structures, or subsets or supersets thereof, as exemplified below.

An operating system 551 including system programs for processing various basic system services and performing hardware-related tasks, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks;

a network communication module 552 for communicating to other computing devices via one or more (wired or wireless) network interfaces 520, exemplary network interfaces 520 including: bluetooth, wireless compatibility authentication (WiFi), and Universal Serial Bus (USB), etc.;

a presentation module 553 for enabling presentation of information (e.g., a user interface for operating peripherals and displaying content and information) via one or more output devices 531 (e.g., a display screen, speakers, etc.) associated with the user interface 530;

an input processing module 554 to detect one or more user inputs or interactions from one of the one or more input devices 532 and to translate the detected inputs or interactions.

In some embodiments, the vehicle-based attraction recommendation device provided by the embodiments of the present application may be implemented in software, and fig. 2 shows a vehicle-based attraction recommendation device 555 stored in a memory 550, which may be software in the form of programs and plug-ins, and the like, and includes the following software modules: the obtaining module 5551, the first determining module 5552, the matching module 5553, the second determining module 5554 and the output module 5555 are logical modules, and thus may be arbitrarily combined or further split according to the implemented functions, and the functions of the respective modules will be described below.

In other embodiments, the vehicle-based attraction recommendation Device provided in the embodiments of the present Application may be implemented by a combination of hardware and software, and as an example, the vehicle-based attraction recommendation Device provided in the embodiments of the present Application may be a processor in the form of a hardware decoding processor, which is programmed to execute the vehicle-based attraction recommendation method provided in the embodiments of the present Application, for example, the processor in the form of the hardware decoding processor may be implemented by one or more Application Specific Integrated Circuit (ASIC), DSP, Programmable Logic Device (PLD), Complex Programmable Logic Device (CPLD), Field Programmable Gate Array (FPGA), or other electronic components.

In some embodiments, the vehicle-mounted terminal or the server may implement the vehicle-based sight recommendation method provided in the embodiments of the present application by running a computer program. For example, the computer program may be a native program or a software module in an operating system; can be a local (Native) application program (APP), i.e. a program that needs to be installed in an operating system to run, such as a scenic spot recommended APP; or may be an applet, i.e. a program that can be run only by downloading it to the browser environment; but also an applet that can be embedded into any APP. In general, the computer programs described above may be any form of application, module or plug-in.

Based on the above description of the vehicle-based scenic spot recommendation system and the electronic device provided in the embodiment of the present application, the vehicle-based scenic spot recommendation method provided in the embodiment of the present application is described below. In some embodiments, the vehicle-based sight spot recommendation method provided by the embodiment of the present application may be implemented by a server or a vehicle-mounted terminal alone, or implemented by a server and a vehicle-mounted terminal in a cooperative manner, and the vehicle-based sight spot recommendation method provided by the embodiment of the present application is described below by taking the vehicle-mounted terminal as an example.

Referring to fig. 3, fig. 3 is a schematic flow chart of the vehicle-based sight spot recommendation method provided in the embodiment of the present application, and the vehicle-based sight spot recommendation method provided in the embodiment of the present application includes:

step 101: the vehicle-mounted terminal acquires the current geographic position of the vehicle and acquires an environment image of the current environment of the vehicle.

Here, the vehicle-mounted terminal is installed in the vehicle, and in practical application, the vehicle-mounted terminal may be provided with a client or an applet for scenic spot recommendation, and based on this, the user may implement the recommendation of the scenic spot by running the client or the applet on the vehicle-mounted terminal.

In the embodiment of the application, when the scenic spot recommendation is performed based on the vehicle, the vehicle-mounted terminal acquires the current geographic position of the vehicle, and the geographic position can be represented by a geographic coordinate, a geodetic coordinate and the like. Meanwhile, the vehicle-mounted terminal can also acquire an environment image of the current environment of the vehicle, for example, the environment image can be acquired through an image acquisition device (such as a camera) arranged on the vehicle, and the environment image can also be acquired from a background service through network connection, wherein the background service can store the environment image of the environment of the vehicle acquired in real time. In practical applications, the vehicle-mounted terminal may acquire an environment image of the environment around the current environment of the vehicle in each direction, or may acquire an environment image of a specified direction, such as an environment image in front of the vehicle in the driving direction.

In practical application, the vehicle-mounted terminal can acquire the geographic position and the environment image when the vehicle stops at a certain place in the process of acquiring the geographic position and the environment image, and can also acquire the geographic position and the environment image in the process of driving the vehicle, so that the scenic spot recommendation is performed in the process of driving the vehicle, and the requirements of a self-driving tour user are met conveniently.

In some embodiments, the in-vehicle terminal may obtain the current geographic location of the vehicle by: positioning the vehicle through a global positioning system chip arranged in the vehicle to obtain first positioning information; the method comprises the steps that location processing is carried out on a vehicle through a Location Based Service (LBS) to obtain second location information; and determining the current geographic position of the vehicle by combining the first positioning information and the second positioning information.

Here, when acquiring the current geographic position of the vehicle, the in-vehicle terminal may perform positioning processing on the vehicle. In the embodiment of the application, the positioning processing aiming at the vehicle can be realized by combining a Global Positioning System (GPS) and a location-based service (LBS) so as to improve the accuracy of the vehicle position positioning and avoid the condition of inaccurate positioning caused by large blind areas due to the fact that only the GPS is used for positioning. Firstly, a vehicle-mounted terminal carries out positioning processing based on a global positioning system on a vehicle through a global positioning system chip arranged in the vehicle to obtain first positioning information corresponding to the vehicle, and the first positioning information can be expressed in a geographic coordinate mode, a geodetic coordinate mode and the like; then the vehicle-mounted terminal carries out positioning processing based on a wireless communication network on the vehicle through a Location Based Service (LBS) to obtain second positioning information corresponding to the vehicle, and the second positioning information can also be expressed in the modes of geographic coordinates, geodetic coordinates and the like; and finally, determining the current geographic position of the vehicle by combining the first positioning information and the second positioning information.

In some embodiments, the in-vehicle terminal may acquire an environment image of an environment in which the vehicle is currently located by: in the running process of the vehicle, an environment image of the current environment of the vehicle is acquired through a camera arranged on the vehicle.

Here, the vehicle-mounted terminal carries out environment image acquisition in the driving process of the vehicle, so that scenic spot recommendation can be carried out in the driving process of the vehicle, and better self-driving travel experience is provided for a user. Specifically, the vehicle is provided with a camera for image acquisition, and during the running process of the vehicle, the vehicle-mounted terminal acquires an environment image of the current environment of the vehicle in real time or periodically through the camera arranged on the vehicle, for example, the vehicle-mounted terminal can acquire environment images in all directions around the current environment of the vehicle, and can also acquire an environment image in a specified direction, for example, an environment image in front in the running direction of the vehicle.

In some embodiments, the in-vehicle terminal may acquire an environment image of an environment in which the vehicle is currently located by: obtaining a sight spot position corresponding to at least one candidate sight spot; determining the distance between each candidate sight spot and the vehicle based on the position of each sight spot and the geographic position; when the distance between at least one candidate sight point and the vehicle is lower than the distance threshold value, an environment image of the environment where the vehicle is located is obtained.

Here, the vehicle-mounted terminal may collect the environment image when the vehicle reaches the vicinity of the sight spot, for example, when the distance to the sight spot is lower than the distance threshold, instead of collecting the environment image in real time or periodically, so as to reduce the hardware processing pressure. In practical application, each candidate sight spot and a sight spot position (such as a geographic coordinate of the sight spot) corresponding to each candidate sight spot may be stored in advance, and may be specifically stored in a background server, a vehicle-mounted terminal, or a database.

Since the sight often indicates an area range, the sight position of the sight can be indicated by an identification position within the sight area, and the identification position can be represented by geographic coordinates, longitude and latitude information, and the like. In some embodiments, the identified location of the attraction may be selected by: for each sight spot, an identification position is preset, for example, the position of the area center of the sight spot area may be used as the identification position, the positions of a preset number of points (for example, points in east-west-south-north directions) at the area edge of the sight spot area may be used as the identification position, or the positions of markers of the sight spot may be used as the identification position.

Based on this, when acquiring the environment image of the current environment of the vehicle, the vehicle-mounted terminal first acquires the scenery spot position corresponding to each candidate scenery spot, which may be the scenery spot position indicated by one identification position in the scenery spot area; the distance between each candidate sight and the vehicle is then determined, i.e., the distance between each candidate sight and the vehicle is calculated based on the geographic location of the vehicle and the sight location of each sight. After the distances between the candidate scenic spots and the vehicle are obtained through calculation, the number of the candidate scenic spots, the distances between the candidate scenic spots and the vehicle are lower than a distance threshold value, the number represents that when at least one candidate scenic spot exists, the distance between the candidate scenic spot and the vehicle is lower than the distance threshold value, the vehicle is indicated to be located nearby a certain scenic spot or is about to reach the certain scenic spot, and at the moment, in order to recommend the scenic spot, an environment image of the current environment of the vehicle is obtained. In practical implementation, the distance threshold may be preset, and when the distance between the vehicle and a certain attraction is lower than the distance threshold, the vehicle is considered to be currently near the attraction or to be about to reach the attraction.

Step 102: the method comprises the steps of determining a sight spot corresponding to a geographic position and acquiring at least one landscape image of the sight spot.

After acquiring the current geographic position of the vehicle and the environment image of the environment, the vehicle-mounted terminal determines a scenery spot corresponding to the geographic position and acquires at least one landscape image of the scenery spot. In actual implementation, the landscape images of the candidate sights can be stored in advance, the landscape images are collected and stored in advance, updating can be performed according to actual changes of the sights, and the landscape images can be stored in a background server, a vehicle-mounted terminal or a database. After the scenic spot corresponding to the geographic position is determined based on the geographic position of the vehicle, at least one landscape image of the scenic spot is obtained from prestored scenic spot images.

In some embodiments, the in-vehicle terminal may determine the sights corresponding to the geographic locations by: obtaining a scenery spot area range corresponding to at least one candidate scenery spot; determining a target scenery spot area range where the vehicle is located currently based on each scenery spot area range and the geographic position; and determining candidate sights corresponding to the target sight area range as sights corresponding to the geographic position.

Here, the scenic spot area range corresponding to each candidate scenic spot may also be preset, and the scenic spot area range corresponding to each candidate scenic spot may be stored in the background server, the vehicle-mounted terminal, or the database, and may be updated according to the actual situation of the scenic spot (such as expansion or contraction of the scenic spot area). When determining the scenic spot corresponding to the geographic position of the vehicle, firstly, obtaining a scenic spot area range corresponding to each candidate scenic spot, and then determining a target scenic spot area range where the vehicle is currently located based on each scenic spot area range and the geographic position of the vehicle, so that the candidate scenic spot corresponding to the target scenic spot area range is determined as the scenic spot corresponding to the geographic position. In practical application, the scenic spot area range can be represented based on longitude and latitude information, specifically, a region range is represented by the longitude and latitude information, and the geographic position can also be represented based on the longitude and latitude information, so that when the current target scenic spot area range of the vehicle is determined based on each scenic spot area range and the geographic position, the fact that the longitude and latitude information of the geographic position is located in the region range represented by the longitude and latitude information corresponding to the scenic spot area range can be checked, and the current target scenic spot area range of the vehicle is determined.

In some embodiments, the in-vehicle terminal may determine the sights corresponding to the geographic locations by: referring to fig. 4, fig. 4 is a schematic flowchart of determining sights corresponding to a geographic location according to an embodiment of the present application, including: step 201, a vehicle-mounted terminal acquires a sight spot position corresponding to at least one candidate sight spot; step 202, determining the distance between each candidate sight spot and the vehicle based on the position of each sight spot and the geographic position; step 203, determining the candidate scenic spots with the distance between the candidate scenic spots and the vehicle meeting the distance condition as the scenic spots corresponding to the geographic position.

Here, each candidate sight spot and a sight spot position (such as a geographic coordinate of the sight spot) corresponding to each candidate sight spot may be stored in advance, and may be specifically stored in the background server, the vehicle-mounted terminal, or the database, and the stored sight spot position may be updated according to an actual situation.

Based on this, when determining the scenic spot corresponding to the geographic position where the vehicle is located, the vehicle-mounted terminal first acquires the scenic spot position corresponding to each candidate scenic spot, which may be the scenic spot position indicated by one identification position in the scenic spot area; the distance between each candidate sight and the vehicle is then determined, i.e., the distance between each candidate sight and the vehicle is calculated based on the geographic location of the vehicle and the sight location of each sight. After the distances between the candidate scenic spots and the vehicles are obtained through calculation, the candidate scenic spots with the distances meeting the distance condition between the candidate scenic spots and the vehicles are determined as the scenic spots corresponding to the geographic positions. In actual implementation, the distance condition may be to determine a candidate sight below a distance threshold as a sight corresponding to the geographic location, or to determine a closest candidate sight as a sight corresponding to the geographic location, and so on.

Step 103: and matching the environment image with each landscape image to obtain corresponding matching degree.

After the vehicle-mounted terminal acquires at least one landscape image of the scenery spot corresponding to the geographical position of the vehicle, the vehicle-mounted terminal respectively matches the environment image of the environment where the vehicle is located with each landscape image so as to determine whether the environment image of the environment where the vehicle is located is matched with the landscape image of the scenery spot corresponding to the geographical position where the vehicle is located, and therefore the corresponding matching degree is obtained.

In some embodiments, the vehicle-mounted terminal may match the environment image with each landscape image respectively to obtain a corresponding matching degree as follows: referring to fig. 5, fig. 5 is a schematic flowchart of determining a matching degree between an environment image and each landscape image according to an embodiment of the present application, including: step 1031, performing feature extraction on the environment image to obtain corresponding environment image features, and performing feature extraction on each landscape image to obtain corresponding landscape image features; step 1032, matching the environmental image features with the landscape image features respectively to obtain corresponding feature matching degrees; and 1033, taking the feature matching degree of the environment image features and the feature of each landscape image as the matching degree of the environment image and each landscape image.

Here, the images may be matched in an image feature matching manner to obtain matching degrees of the environment image and each landscape image. Firstly, the vehicle-mounted terminal extracts the features of the environment images to obtain the corresponding environment image features, and extracts the features of each landscape image to obtain the corresponding landscape image features; then, respectively carrying out feature matching on the environment image features and the landscape image features to obtain corresponding feature matching degrees; and finally, taking the feature matching degree of the environment image features and the feature matching degree of each landscape image feature as the matching degree of the environment image and each landscape image. In practical implementation, in the feature extraction, SIFT features may be extracted from the image.

In some embodiments, the vehicle-mounted terminal may match the environment image with each landscape image respectively to obtain a corresponding matching degree as follows: the following processing is respectively executed for each landscape image: inputting the landscape image and the environment image into a machine learning model; and predicting the matching degree of the landscape image and the environment image through a machine learning model to obtain the matching degree between the landscape image and the environment image.

Here, the matching degree of each of the environment images with each of the landscape images may also be calculated by a machine learning model. The machine learning model can be trained in advance, the machine learning model can be constructed based on network models such as a Convolutional Neural Network (CNN) and a Deep Neural Network (DNN), loss functions such as a cross entropy loss function and a logarithmic loss function can be set, after the initial machine learning model is constructed, the initial machine learning model can be trained based on training samples until the model converges, and the machine learning model which is trained finally and used for predicting the image matching degree is obtained.

Based on this, the vehicle-mounted terminal can respectively execute the following processing aiming at each landscape image so as to obtain the matching degree of each landscape image and the environment image: inputting the landscape image and the environment image into a machine learning model, and predicting the matching degree of the landscape image and the environment image through the machine learning model to obtain the matching degree between the landscape image and the environment image.

Step 104: and when the matching condition is determined to be satisfied based on the obtained matching degree, determining the scenic spot as the target scenic spot.

Here, when it is determined based on the matching degree that the matching condition is satisfied, it is considered that an environment image acquired on site (i.e., an environment where the vehicle is located) and a landscape image (pre-stored) of a sight spot corresponding to the located geographic position both belong to the same sight spot, and it is accurate to characterize the located geographic position of the vehicle, so it is considered that the vehicle is located in the sight spot, and sight spot recommendation for the sight spot can be performed, that is, the sight spot is determined as a target sight spot, so that the sight spot recommendation is more accurate; when the matching condition is determined not to be met based on the matching degree, the environment image acquired on site (namely the environment where the vehicle is located) and the landscape image (pre-stored) of the scenery spot corresponding to the located geographic position do not belong to the same scenery spot, the geographic position where the vehicle located is represented is inaccurate, and thus the scenery spot recommendation is not performed if the vehicle is determined not to be in the scenery spot.

In some embodiments, the in-vehicle terminal may determine whether the matching condition is satisfied by: when the number of the landscape images is multiple, acquiring the number of target landscape images, of the multiple landscape images, of which the matching degree with the environment image reaches a matching degree threshold value; when the number reaches the target number, it is determined that the matching condition is satisfied.

Here, when the number of the landscape images is plural, the number of target landscape images whose matching degree with the environment image reaches the matching degree threshold value among the plural landscape images may be acquired. When the number reaches the target number, it is determined that the matching condition is satisfied. In practical application, a ratio between the number and the total number of the landscape images can be calculated, and when the ratio reaches a ratio threshold value, it is determined that the matching condition is satisfied.

And when the matching condition is determined to be satisfied based on the obtained matching degree, determining the scenic spot as the target scenic spot.

Step 105: and obtaining the sight spot recommendation information corresponding to the target sight spot, and outputting the sight spot recommendation information through the vehicle-mounted terminal.

When the matching condition is determined to be met based on the matching degree of the environment image and the landscape image, the scenery spot corresponding to the landscape image meeting the matching condition is taken as the target scenery spot, at the moment, scenery spot recommendation information corresponding to the target scenery spot is obtained, and the scenery spot recommendation information is output through the vehicle-mounted terminal so as to recommend the scenery spot to the target scenery spot.

In some embodiments, the vehicle-mounted terminal may output the sight recommendation information by: the scenic spot recommendation information in the audio format is played through an audio output unit of the vehicle-mounted terminal, and the scenic spot recommendation information including at least one of text, image and video is presented through a display unit of the vehicle-mounted terminal.

Here, the in-vehicle terminal includes an audio output unit and a display unit. Specifically, the scenic spot recommendation information in the audio format is played through the audio output unit, for example, "you are about to enter XX scenic spot, XX scenic spot is 5A level, including scenic spot 1, scenic spot 2 … …" and the like is broadcasted; the scenic spot recommendation information, specifically, the scenic spot recommendation information in a text form, may also be presented through the display unit, for example, "XX scenic spot includes scenic spot 1 and scenic spot 2 … …"; presenting scenic spot recommendation information in the form of an image, such as a promotional picture of a scenic spot XX; the attraction recommendation information is presented in the form of a video, such as a promotional video of the attraction XX.

By way of example, referring to fig. 6, fig. 6 is a schematic diagram of the attraction recommendation information provided in the embodiment of the present application. Here, for example, the vehicle-mounted terminal displays the scenic spot recommendation information through the display unit, the vehicle-mounted terminal display area 1 displays the scenic spot recommendation information "XX scenic spot includes scenic spot 1 and scenic spot 2 … …" in a text form; the scene recommendation information in the form of an image, that is, the promotional picture of the scene XX is displayed in the display area 2.

In some embodiments, the vehicle-mounted terminal may obtain the sight recommendation information corresponding to the target sight through the following method: acquiring a recommendation information template for generating scenic spot recommendation information and scenic spot recommendation content corresponding to a target scenic spot; and generating the sight spot recommendation information corresponding to the target sight spot based on the sight spot recommendation content and the recommendation information template.

Here, when obtaining the scenic spot recommendation information, the vehicle-mounted terminal may generate the scenic spot recommendation content based on the recommendation information template and the target scenic spot. Firstly, acquiring a recommendation information template for generating scenic spot recommendation information, wherein the recommendation information template can be used for indicating the display positions of various types of scenic spot recommendation contents, the formats of fused audio recommendation contents and the like, for example, a literary font type scenic spot recommendation content is located in a display area 1, a pictorial type scenic spot recommendation content is located in a display area 2, and an audio type scenic spot recommendation content in an MP3 format needs to be fused; then, obtaining the recommended scenic spot content corresponding to the target scenic spot, wherein the recommended scenic spot content can comprise propaganda characters, propaganda videos, propaganda pictures, propaganda audios and the like; and finally, generating the scenery spot recommendation information corresponding to the target scenery spot based on the scenery spot recommendation content and the recommendation information template, specifically, filling the scenery spot recommendation content of the corresponding type into the corresponding display area according to the display area of each type of scenery spot recommendation content indicated by the recommendation information template to obtain intermediate scenery spot recommendation information, and further performing fusion processing on the audio type scenery spot recommendation content and the intermediate scenery spot recommendation information to obtain the scenery spot recommendation information corresponding to the target scenery spot.

By way of example, referring to fig. 7, fig. 7 is a schematic diagram of a generation flow of the sight recommendation information provided in the embodiment of the present application. Here, the recommendation information template is shown as a diagram a in fig. 7, and includes a presentation area 1 corresponding to the literal sight recommendation content and a presentation area 2 corresponding to the pictorial sight recommendation content; after the sight spot recommended content is obtained, filling the sight spot recommended content of the type corresponding to the sight spot recommended content into a corresponding display area to obtain intermediate sight spot recommended information, as shown in a diagram B in FIG. 7; and further carrying out fusion processing on the audio-type scenic spot recommendation content and the intermediate scenic spot recommendation information to obtain the scenic spot recommendation information corresponding to the target scenic spot.

In some embodiments, the vehicle-mounted terminal may output the sight recommendation information by: when a plurality of target scenic spots are available, acquiring a recommendation sequence corresponding to each target scenic spot; and sequentially outputting the scenic spot recommendation information through the vehicle-mounted terminal according to the recommendation sequence.

Here, when there are a plurality of target sights, the recommendation sequence corresponding to each target sight can also be obtained, so that the sight recommendation information corresponding to each target sight is sequentially output according to the recommendation sequence. In practical application, the recommendation sequence of each target sight spot can be determined based on sight spot comments, the matching degree with the user portrait, sight spot scores, the current pedestrian volume of the sight spots and other factors, for example, the target sight spots are sorted in a descending order according to the matching degree with the user portrait to obtain sorted target sight spots, and the sorted target sight spots correspond to the recommendation sequence, so that sight spot recommendation information corresponding to each target sight spot is sequentially output according to the sorted target sight spots; or sequencing the target scenic spots in a descending order according to the scenic spot scores of the target scenic spots to obtain sequenced target scenic spots, wherein the sequenced target scenic spots correspond to the recommendation order, so that the scenic spot recommendation information corresponding to each target scenic spot is sequentially output according to the sequenced target scenic spots.

In some embodiments, the vehicle-mounted terminal may obtain real-time sight data within the target sight; and outputting corresponding sight spot prompt information based on the real-time sight spot data, wherein the sight spot prompt information is used for prompting the recommendation degree of going to the target sight spot.

Here, the vehicle-mounted terminal may further obtain real-time scenery spot data in the target scenery spot, such as real-time people flow data, real-time remaining parking space data, score data of the target location (such as a food store, a landmark scenery spot, and the like), and the like. Therefore, based on the real-time scenery spot data, corresponding scenery spot prompt information is output, and the recommendation degree of going to the target scenery spot is prompted through the scenery spot prompt information. For example, when the obtained real-time scenic spot data represents that the pedestrian volume of the target scenic spot is too large or the parking space is insufficient, scenic spot prompt information of 'please carefully select to go' is output to prompt the user that the recommendation degree of the target scenic spot is low; when the obtained real-time scenic spot data represent that the traffic of people of the target scenic spot is small or the parking space is sufficient, scenic spot prompt information of 'can go to' is output to prompt a user that the recommended degree of the scenic spot is high.

In practical application, the vehicle-mounted terminal can play the scenic spot prompt information in an audio format and can also display the scenic spot prompt information in formats such as texts, images and the like.

In some embodiments, the vehicle-mounted terminal can present a navigation function item corresponding to the scenic spot recommendation information; and presenting navigation information for guiding the vehicle to reach the target scenic spot from the current position in response to the triggering operation for the navigation function item.

Here, when the vehicle-mounted terminal outputs the sight spot recommendation information of the target sight spot, a navigation function item corresponding to the sight spot recommendation information may be further displayed, and the user may trigger a route navigation function for going from the current position to the target sight spot through the navigation function item. When a trigger operation for the navigation function item is received, navigation information for guiding the vehicle to reach the target sight spot from the current position is presented in response to the trigger operation for the navigation function item.

By way of example, referring to fig. 8, fig. 8 is a presentation schematic diagram of a navigation function item provided by an embodiment of the present application. Here, the vehicle-mounted terminal displays the scenic spot recommendation information corresponding to the target scenic spot "scenic spot Y", and displays the navigation function item "navigation" corresponding to the scenic spot recommendation information, as shown in a diagram a in fig. 8; in response to a triggering operation for the navigation function item "navigation", navigation information for guiding the vehicle from the current position to the target attraction "attraction Y" is presented, as shown in fig. 8B.

By applying the embodiment of the application, the current geographic position of the vehicle and the environment image of the environment are firstly obtained, at least one landscape image of the scenery spot corresponding to the geographic position is obtained, then the matching degree of the environment image of the environment where the vehicle is located and each landscape image of the scenery spot corresponding to the geographic position is determined, when the matching condition is determined to be met based on the matching degree, the scenery spot is determined as the target scenery spot, and therefore the scenery recommendation information corresponding to the target scenery spot is obtained and output to realize recommendation for the target scenery.

Next, the vehicle-based sight spot recommendation method provided in the embodiment of the present application is continuously described, and the vehicle-based sight spot recommendation method provided in the embodiment of the present application may be cooperatively implemented by a vehicle-mounted terminal and a server. Referring to fig. 9, fig. 9 is a schematic flow chart of the vehicle-based sight spot recommendation method according to the embodiment of the present application, and the vehicle-based sight spot recommendation method according to the embodiment of the present application includes:

step 301: the vehicle-mounted terminal carries out positioning processing on the vehicle through a global positioning system chip arranged in the vehicle in the driving process of the vehicle to obtain first positioning information.

Step 302: and positioning the vehicle through the LBS based on the position to obtain second positioning information.

Step 303: and determining the current geographic position of the vehicle by combining the first positioning information and the second positioning information.

Step 304: in the running process of the vehicle, an environment image of the current environment of the vehicle is acquired through a camera arranged on the vehicle.

Step 305: and sending the current geographic position of the vehicle and the environment image of the current environment of the vehicle to a server.

Step 306: the server determines the current target sight spot area range of the vehicle based on the sight spot area ranges and the geographic positions.

Step 307: and determining candidate sights corresponding to the target sight spot area range as sights corresponding to the geographic position, and acquiring at least one landscape image of the sights.

Step 308: and matching the environment image with each landscape image to obtain corresponding matching degree.

Step 309: and when the matching condition is determined to be satisfied based on the obtained matching degree, determining the scenic spot as the target scenic spot.

Step 310: and obtaining the sight spot recommendation information corresponding to the target sight spot and sending the sight spot recommendation information to the vehicle-mounted terminal.

Step 311: and the vehicle-mounted terminal receives and outputs the sight spot recommendation information corresponding to the target sight spot.

An exemplary application of the embodiments of the present application in a practical application scenario will be described below.

Based on this, the embodiment of the application provides a scenic spot recommendation method based on a vehicle, and hardware devices such as a GPS chip, IBS, a front camera and the like are loaded in the vehicle, so that the current geographic position of the vehicle can be obtained by combining the hardware devices, and more accurate positioning is provided. Specifically, the method comprises the following steps:

1) the application client arranged on the vehicle-mounted terminal in the vehicle can refresh the geographical position of the application client at regular time, and hardware devices such as a GPS chip, IBS, a front camera and the like are loaded in the vehicle and are combined with each other to provide a more accurate positioning function.

2) And an application client arranged in the vehicle is connected to the service background through the Internet to pull the list of the scenic spot position ranges of the supported scenic spots.

3) And traversing the pulled list, and when the vehicle is determined to be in the position range of the scenic spot based on the geographic position of the positioned vehicle and the shot environment image, playing a voice prompt in the scenic spot according to the configuration of the server, and simultaneously displaying a landscape image or a promotional video of the scenic spot, so that a user can more conveniently confirm whether the current scenic spot is interested. Therefore, according to the accurate positioning, the scenic spot recommendation information of the related scenic spots can be pushed to the user more accurately.

4) The method comprises the steps of shooting an environment image of an environment through a camera arranged on an automobile, carrying out matching identification based on key landscape content configured by a server, and recommending the scenic spots if matching is successful, such as triggering voice introduction and broadcasting of the key landscape.

Referring to fig. 10, fig. 10 is a schematic flowchart of a vehicle-based sight recommendation method provided in an embodiment of the present application, including:

step 401: starting;

step 402: powering on a vehicle-mounted terminal system;

step 403: initializing a system;

step 404: acquiring a vehicle running state;

step 405: the GPS acquires the current positioning in real time to obtain first positioning information;

step 406: acquiring positioning data through IBS to obtain second positioning information;

step 407: the GPS and the IBS are combined to obtain accurate positioning, namely the geographic position of the vehicle;

step 408: detecting whether the geographical position data are normally acquired, if so, executing a step 409, otherwise, returning to the step 403;

step 409: uploading the collected geographic position to a scenic spot recommendation client;

step 410: the scenic spot recommendation client pulls the scenic spot position range;

step 411: starting a camera;

step 412: detecting whether the starting is normal, if so, executing step 413, otherwise, returning to step 411;

step 413: shooting an environment image of the environment, and matching the environment image with a landscape image corresponding to the geographical position;

step 414: if the matching is successful, go to step 415, if not, go back to step 413;

step 415: uploading the collected environment image and the information successfully matched to the scenic spot recommendation client;

step 416: pulling the data of the scenic spot camera through the scenic spot recommendation client;

step 417: judging whether the scenic spot people stream is normal, if so, executing a step 418, and if not, executing a step 421;

step 418: searching for a scenic spot or a gourmet spot;

step 419: judging whether the parking spaces of the card punching points are sufficient or not, if so, executing a step 420, otherwise, returning to the step 418;

step 420: under the premise that the scenic spot matching is successful, the scenic spot and the related introduction are broadcasted in a voice mode, the related picture video is broadcasted, and meanwhile navigation information of the scenic spot is provided;

step 421: continuously driving and replacing the target place;

step 422: and (6) ending.

Here, first, the in-vehicle terminal may refresh its own geographical location periodically. Here, because the GPS has a strong dependence on satellites (at least three satellites are captured), which results in many or very large blind areas, for example, accurate positioning cannot be achieved indoors, in a car, in a cloudy day, an IBS is also required in the embodiment of the present application, which has no blind area in the coverage area of the mobile phone network, and thus, the positioning data with very high accuracy can be obtained by combining the GPS and the IBS.

And secondly, an application client arranged on the vehicle-mounted terminal in the vehicle is connected to the list of the scenic spot position ranges of the scenic spots supported by the service background pull through the Internet.

Thirdly, an environment image of the environment is shot through a camera arranged on the automobile, matching identification is carried out on the basis of key landscape contents configured by the server, and the fact that the environment image contains the key landscape contents is determined; and (4) matching and comparing the environment image with a landscape image (pre-stored) corresponding to the geographical position of the positioned vehicle after identification, and if the matching and comparison are successful, determining that the positioning is accurate, and executing the step 4.

Fourthly, when the vehicle is determined to be in the position range of the scenic spot based on the geographic position of the positioned vehicle and the shot environment image, the voice prompt in the scenic spot is played according to the configuration of the service end, and meanwhile, the landscape image or the propaganda video of the scenic spot can be displayed, so that the user can conveniently confirm whether the current scenic spot is interested or not.

Fifthly, the flow of people in each area of the scenic spot is obtained by combining a camera arranged in the scenic spot, if the flow of people is too much, the voice is broadcasted to prompt that the current people flow too much, and cautious going is recommended; the popularity scenic spots and the delicatessens can also be recommended by combining the data of the popularity and the online scenic spot delicatessens and the like; meanwhile, a scenic spot parking space system can be accessed, so that whether the parking space of a user is nervous or not is informed in advance, and the situation that the user cannot park after arriving is avoided.

In the embodiment of the application, the GPS chip is directly arranged in the vehicle, a GPS receiving module is not required to be arranged in the vehicle, the cost is low, the structure is simple, the tone quality is clear, and the system compatibility and the expansibility are good; the used wireless transceiver module is in a receiving state at ordinary times, does not transmit signals and is not easy to generate frequency interference.

By applying the embodiment of the application, based on the GPS, the IBS and the camera, the position information can be acquired more accurately by multiple positioning, effective scenic spot recommendation is provided for a user, and the influence on travel experience caused by the fact that the user goes to an incorrect place due to positioning errors and information errors is reduced; meanwhile, real-time data of multiple scenic spots are combined to remind a user of real-time pedestrian flow, parking spaces and the like, and traveling experience of the user is improved.

Continuing with the exemplary architecture of the vehicle-based attraction recommendation device 555 implemented as a software module provided by embodiments of the present application, in some embodiments, as shown in FIG. 2, the software modules stored in the vehicle-based attraction recommendation device 555 in the memory 550 may include:

the obtaining module 5551 is configured to obtain a current geographic location of a vehicle, and obtain an environment image of a current environment of the vehicle;

a first determining module 5552, configured to determine a sight point corresponding to the geographic location, and acquire at least one landscape image of the sight point;

the matching module 5553 is configured to match the environment image with each of the landscape images, respectively, to obtain a corresponding matching degree;

a second determining module 5554, configured to determine the scenery spot as a target scenery spot when it is determined that a matching condition is satisfied based on the obtained matching degree;

the output module 5555 is configured to obtain the scenic spot recommendation information corresponding to the target scenic spot, and output the scenic spot recommendation information through the vehicle-mounted terminal.

In some embodiments, the obtaining module 5551 is further configured to perform positioning processing on the vehicle through a global positioning system chip disposed in the vehicle, so as to obtain first positioning information;

the vehicle is positioned through a Location Based Service (LBS) to obtain second positioning information;

and determining the current geographic position of the vehicle by combining the first positioning information and the second positioning information.

In some embodiments, the obtaining module 5551 is further configured to acquire an environment image of an environment where the vehicle is currently located through a camera provided on the vehicle during the driving of the vehicle.

In some embodiments, the obtaining module 5551 is further configured to obtain a sight position corresponding to at least one candidate sight;

determining a distance between each of the candidate sights and the vehicle based on each of the sight locations and the geographic location;

In some embodiments, the first determining module 5552 is further configured to obtain an attraction area range corresponding to at least one candidate attraction;

determining a target scenery spot area range where the vehicle is located currently based on each scenery spot area range and the geographic position;

and determining the candidate scenery spot corresponding to the target scenery spot area range as the scenery spot corresponding to the geographic position.

In some embodiments, the first determining module 5552 is further configured to obtain a sight location corresponding to at least one candidate sight;

determining a distance between each of the candidate sights and the vehicle based on each of the sight locations and the geographic location;

In some embodiments, the matching module 5553 is further configured to perform feature extraction on the environment images to obtain corresponding environment image features, and perform feature extraction on each of the landscape images to obtain corresponding landscape image features;

matching the environmental image features with the landscape image features respectively to obtain corresponding feature matching degrees;

and taking the feature matching degree of the environment image features and each landscape image feature as the matching degree of the environment image and each landscape image.

In some embodiments, the matching module 5553 is further configured to perform the following processing for each of the landscape images:

inputting the landscape image and the environment image into a machine learning model;

In some embodiments, the second determining module 5554 is further configured to, when the number of the landscape images is multiple, obtain the number of target landscape images, of the multiple landscape images, whose matching degree with the environment image reaches a matching degree threshold;

when the number reaches a target number, determining that the matching condition is satisfied.

In some embodiments, the output module 5555 is further configured to obtain a recommendation information template for generating the sight spot recommendation information and sight spot recommendation content corresponding to the target sight spot;

and generating the sight spot recommendation information corresponding to the target sight spot based on the sight spot recommendation content and the recommendation information template.

In some embodiments, the output module 5555 is further configured to, when there are a plurality of target sights, obtain a recommendation sequence corresponding to each of the target sights;

and sequentially outputting the scenic spot recommendation information through the vehicle-mounted terminal according to the recommendation sequence.

In some embodiments, the output module 5555 is further configured to obtain real-time sight data within the target sight;

In some embodiments, the output module 5555 is further configured to present a navigation function item corresponding to the attraction recommendation information;

in response to a triggering operation for the navigation function item, presenting navigation information for guiding the vehicle from a current location to the target attraction.

In some embodiments, the output module 5555 is further configured to play the scenic spot recommendation information in an audio format through an audio output unit of the vehicle-mounted terminal, and

and presenting the scenic spot recommendation information comprising at least one of text, image and video through a display unit of the vehicle-mounted terminal.

An embodiment of the present application further provides an electronic device, where the electronic device includes:

a memory for storing executable instructions;

Embodiments of the present application also provide a computer program product or a computer program comprising computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and executes the computer instructions, so that the computer device executes the vehicle-based sight recommendation method provided by the embodiment of the application.

The embodiment of the application further provides a computer-readable storage medium, which stores executable instructions, and when the executable instructions are executed by a processor, the vehicle-based scenic spot recommendation method provided by the embodiment of the application is realized.

In some embodiments, the computer-readable storage medium may be memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash, magnetic surface memory, optical disk, or CD-ROM; or may be various devices including one or any combination of the above memories.

In some embodiments, executable instructions may be written in any form of programming language (including compiled or interpreted languages), in the form of programs, software modules, scripts or code, and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

By way of example, executable instructions may correspond, but do not necessarily have to correspond, to files in a file system, and may be stored in a portion of a file that holds other programs or data, such as in one or more scripts in a hypertext Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub-programs, or portions of code).

By way of example, executable instructions may be deployed to be executed on one computing device or on multiple computing devices at one site or distributed across multiple sites and interconnected by a communication network.

The above description is only an example of the present application, and is not intended to limit the scope of the present application. Any modification, equivalent replacement, and improvement made within the spirit and scope of the present application are included in the protection scope of the present application.

31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：一种预测稳定步频的方法及装置

Vehicle-based scenic spot recommendation method, device, equipment, medium and program product

相关技术

网友询问留言