A method, device, electronic device and storage medium for searching a shared vehicle

Abstract

The present application relates to the field of data processing technology, and in particular to a method, device, electronic device and storage medium for searching for shared vehicles. The present application can determine the location reliability of each candidate vehicle through the historical data of multiple candidate vehicles and the trained discriminant model, and can screen out the vehicle to be found from multiple candidate vehicles according to the location reliability of each candidate vehicle, and then, according to the positioning position and location reliability corresponding to each vehicle to be found, density clustering is performed on each vehicle to be found, and the vehicle gathering area can be determined. Furthermore, based on the vehicle gathering area, the vehicle search path is determined. In this way, through the determined vehicle search path, as many vehicles to be found as possible can be found in one vehicle search process, which can improve the efficiency of vehicle search.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, electronic device and storage medium for finding a shared vehicle. Background Art

[0002] Shared bicycles and shared electric vehicles, as a new mode of transportation, have greatly facilitated people's travel life. Users can easily use and park them at any time, which gives them great freedom and is therefore widely welcomed by users.

[0003] However, freedom is a double-edged sword. While it facilitates users' travel, it is inevitable that some vehicles will be parked in remote areas and gradually become silent or even lose contact. Usually, silent shared vehicles will be searched and dispatched to hot areas to improve the utilization rate of shared vehicle resources. Therefore, how to efficiently find more silent shared vehicles is an urgent problem to be solved. Summary of the invention

[0004] In view of this, the embodiments of the present application at least provide a method, device, electronic device and storage medium for searching for a shared vehicle, which can realize the retrieval of as many vehicles as possible in one vehicle search process, thereby improving the efficiency of vehicle search.

[0005] This application mainly includes the following aspects:

[0006] In a first aspect, an embodiment of the present application provides a method for finding a shared vehicle, the method comprising:

[0007] Obtaining historical data of multiple candidate search vehicles, and determining the location reliability of each candidate search vehicle based on the historical data of each candidate search vehicle and the trained discriminant model;

[0008] Filtering a vehicle to be found from the plurality of candidate vehicles according to the location reliability of each candidate vehicle to be found;

[0009] According to the positioning positions and positioning confidences corresponding to the vehicles to be found, density clustering is performed on the vehicles to be found to determine the vehicle gathering area;

[0010] Based on the vehicle gathering area, a vehicle search path is determined.

[0011] In a possible implementation, the search method further includes determining a candidate search vehicle according to the following steps:

[0012] Count the number of times each shared vehicle is used within a preset historical period;

[0013] A shared vehicle that has been used less than or equal to a preset number of times is determined as a candidate vehicle to be searched.

[0014] In a possible implementation, determining the location reliability of each candidate vehicle to be searched for based on the historical data of each candidate vehicle to be searched for and the trained discriminant model includes:

[0015] Extracting characteristic information of each candidate vehicle from historical data of each candidate vehicle;

[0016] The characteristic information of each candidate vehicle is input into the trained discriminant model to determine the location reliability of each candidate vehicle.

[0017] In a possible implementation, the search method further includes generating a trained discriminant model according to the following steps:

[0018] Taking the historical data of the candidate vehicles for which the positioning error is less than or equal to the preset error as positive samples, and taking the historical data of the candidate vehicles for which the positioning error is greater than the preset error as negative samples;

[0019] The initial discriminant model is trained according to the positive samples and the negative samples to generate a trained discriminant model.

[0020] In a possible implementation manner, the step of selecting a vehicle to be found from the plurality of candidate vehicles to be found according to the location reliability of each candidate vehicle to be found includes:

[0021] Determine the vehicle search priority of each candidate vehicle search based on the location reliability of each candidate vehicle search;

[0022] The candidate search vehicles whose search priority is greater than or equal to the preset priority are determined as the vehicles to be searched.

[0023] In a possible implementation, density clustering of each to-be-found vehicle is performed according to the positioning positions and positioning confidences corresponding to each to-be-found vehicle to determine a vehicle gathering area, including:

[0024] According to the positioning positions of each vehicle to be found, each vehicle to be found is clustered to obtain multiple candidate clustering areas;

[0025] For each candidate gathering area among the multiple candidate gathering areas, according to the total number of vehicles to be found in each candidate gathering area and the location reliability of each vehicle to be found, calculate the vehicle density of each candidate gathering area;

[0026] A candidate gathering area with a vehicle density greater than or equal to a preset density is determined as a vehicle gathering area.

[0027] In a possible implementation, determining a vehicle search path based on the vehicle gathering area includes:

[0028] Counting the number of areas where vehicles are concentrated;

[0029] If the number of areas is greater than or equal to a preset threshold, determining a first path between each vehicle gathering area according to the area position of each vehicle gathering area, and determining a second path between each vehicle to be found in each vehicle gathering area according to the positioning position of each vehicle to be found in each vehicle gathering area;

[0030] The vehicle search path is determined according to the first path and the second path.

[0031] In a possible implementation, determining a vehicle search path based on the vehicle gathering area includes:

[0032] If the number of areas is less than the preset threshold, the vehicle search path is determined according to the area positions of each vehicle gathering area, the positioning positions of each vehicle to be found in each vehicle gathering area, the positioning positions of the vehicle scattered areas, and the positioning positions of each vehicle to be found in each vehicle scattered area;

[0033] Among them, the scattered vehicle area is a candidate gathering area where the vehicle density is less than the preset density.

[0034] In a possible implementation manner, after determining a vehicle search path based on the vehicle gathering area, the search method further includes:

[0035] Determining the transport capacity required for transporting the vehicles to be found in the vehicle-finding path according to the number of the vehicles to be found in the vehicle-finding path and the length of the vehicle-finding path;

[0036] If the transport capacity is greater than the preset capacity, the vehicle search path is segmented according to the preset capacity and the transport capacity to obtain at least two segmented paths;

[0037] According to each segmentation path, a vehicle search work order corresponding to each segmentation path is generated.

[0038] In a possible implementation manner, the searching method further includes:

[0039] The vehicle search is performed once at a preset time interval.

[0040] In a possible implementation, the historical data includes historical log data of each candidate vehicle to be searched and historical travel data of each user using the candidate vehicle to be searched;

[0041] Among them, the historical log data includes the communication data between the candidate search vehicle and the external device; the historical travel data includes travel location data, travel time data, and travel duration data.

[0042] In a second aspect, an embodiment of the present application further provides a device for finding a shared vehicle, the device comprising:

[0043] A first determination module is used to obtain historical data of multiple candidate search vehicles, and determine the location reliability of each candidate search vehicle based on the historical data of each candidate search vehicle and the trained discriminant model;

[0044] A screening module, configured to screen out a vehicle to be found from the plurality of candidate vehicles to be found according to the location reliability of each candidate vehicle to be found determined by the first determination module;

[0045] The second determination module is used to perform density clustering on each vehicle to be found according to the positioning positions and positioning confidences corresponding to each vehicle to be found, and determine the vehicle gathering area;

[0046] The third determination module is used to determine a vehicle search path based on the vehicle gathering area determined by the second determination module.

[0047] In a possible implementation manner, the first determination module is further configured to determine a candidate vehicle to be searched according to the following steps:

[0048] Count the number of times each shared vehicle is used within a preset historical period;

[0049] A shared vehicle that has been used less than or equal to a preset number of times is determined as a candidate vehicle to be searched.

[0050] In a possible implementation manner, the first determining module includes:

[0051] An extraction unit, used to extract characteristic information of each candidate vehicle from the historical data of each candidate vehicle;

[0052] The first determination unit is used to input feature information of each candidate vehicle to be searched into the trained discrimination model to determine the location reliability of each candidate vehicle.

[0053] In a possible implementation, the searching device further includes a training module; the training module is used to generate a trained discriminant model according to the following steps:

[0054] Taking the historical data of the candidate vehicles for which the positioning error is less than or equal to the preset error as positive samples, and taking the historical data of the candidate vehicles for which the positioning error is greater than the preset error as negative samples;

[0055] The initial discriminant model is trained according to the positive samples and the negative samples to generate a trained discriminant model.

[0056] In a possible implementation, the screening module includes:

[0057] A second determining unit is used to determine the vehicle search priority of each candidate vehicle to be searched according to the location reliability of each candidate vehicle to be searched;

[0058] The third determining unit is used to determine the candidate search vehicles whose search priority is greater than or equal to the preset priority as the vehicles to be searched.

[0059] In a possible implementation manner, the second determining module includes:

[0060] A generating unit, used for clustering the positions of the vehicles to be found according to the positioning positions of the vehicles to be found, and obtaining a plurality of candidate clustering areas;

[0061] A calculation unit, configured to calculate, for each of the plurality of candidate gathering areas, a vehicle density of each candidate gathering area according to a total number of vehicles to be found in each candidate gathering area and a location reliability of each vehicle to be found;

[0062] The fourth determination unit is used to determine a candidate gathering area with a vehicle density greater than or equal to a preset density as a vehicle gathering area.

[0063] In a possible implementation, the third determining module includes:

[0064] A statistical unit, used to count the number of areas in the determined vehicle gathering area;

[0065] a fifth determining unit, configured to determine, if the number of areas is greater than or equal to a preset threshold, a first path between each vehicle gathering area according to the area position of each vehicle gathering area, and a second path between each vehicle to be found in each vehicle gathering area according to the positioning position of each vehicle to be found in each vehicle gathering area;

[0066] A sixth determining unit is used to determine the vehicle search path according to the first path and the second path.

[0067] In a possible implementation manner, the third determination module is further configured to determine the vehicle search path according to the following steps:

[0068] If the number of areas is less than the preset threshold, the vehicle search path is determined according to the area positions of each vehicle gathering area, the positioning positions of each vehicle to be found in each vehicle gathering area, the positioning positions of the vehicle scattered areas, and the positioning positions of each vehicle to be found in each vehicle scattered area;

[0069] Among them, the scattered vehicle area is a candidate gathering area where the vehicle density is less than the preset density.

[0070] In a possible implementation, the searching device further includes a generating module; the generating module is used to generate a vehicle searching work order according to the following steps:

[0071] Determining the transport capacity required for transporting the vehicles to be found in the vehicle-finding path according to the number of the vehicles to be found in the vehicle-finding path and the length of the vehicle-finding path;

[0072] If the transport capacity is greater than the preset capacity, the vehicle search path is segmented according to the preset capacity and the transport capacity to obtain at least two segmented paths;

[0073] According to each segmentation path, a vehicle search work order corresponding to each segmentation path is generated.

[0074] In a possible implementation manner, the searching device further includes an execution module; the execution module is used to:

[0075] The vehicle search is performed once at a preset time interval.

[0076] In a possible implementation, the historical data includes historical log data of each candidate vehicle to be searched and historical travel data of each user using the candidate vehicle to be searched;

[0077] Among them, the historical log data includes the communication data between the candidate search vehicle and the external device; the historical travel data includes travel location data, travel time data, and travel duration data.

[0078] In the third aspect, an embodiment of the present application also provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and the machine-readable instructions are executed by the processor to execute the steps of the shared vehicle searching method described in the first aspect or any possible implementation manner of the first aspect.

[0079] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for searching for a shared vehicle described in the first aspect or any possible implementation manner of the first aspect are executed.

[0080] In an embodiment of the present application, by acquiring historical data of multiple candidate vehicles to be found and a trained discriminant model, the positioning reliability of each candidate vehicle to be found can be determined, and based on the positioning reliability of each candidate vehicle to be found, the vehicle to be found can be screened out from the multiple candidate vehicles to be found. Then, based on the positioning positions and positioning reliability corresponding to each vehicle to be found, each vehicle to be found is density clustered, and a vehicle gathering area can be determined. Furthermore, based on the vehicle gathering area, a vehicle search path can be determined. In this way, through the determined vehicle search path, as many vehicles to be found as possible can be retrieved in one vehicle search process, which can improve the efficiency of vehicle search.

[0081] Furthermore, the vehicle density of each candidate gathering area is calculated based on the total number of vehicles to be found in each candidate gathering area and the location reliability of each vehicle to be found. Then, the candidate gathering area with a vehicle density greater than or equal to a preset density is determined as a vehicle gathering area. In this way, it can be ensured that there are a sufficient number of vehicles to be found in the vehicle gathering area. By going to the vehicle gathering area to search for the vehicles to be found, it is possible to retrieve as many vehicles to be found as possible in one vehicle searching process, thereby improving the efficiency of vehicle searching.

[0082] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0084] Figure 1 A flow chart showing a method for finding a shared vehicle provided in an embodiment of the present application is shown;

[0085] Figure 2 A flowchart showing another method for finding a shared vehicle provided in an embodiment of the present application is shown;

[0086] Figure 3One of the functional module diagrams of a shared vehicle search device provided in an embodiment of the present application is shown;

[0087] Figure 4 Shows Figure 3 The functional module diagram of the first determination module;

[0088] Figure 5 A second functional module diagram of a shared vehicle search device provided in an embodiment of the present application is shown;

[0089] Figure 6 Shows Figure 5 Functional module diagram of the screening module;

[0090] Figure 7 Shows Figure 5 The functional module diagram of the second determination module;

[0091] Figure 8 Shows Figure 5 Functional module diagram of the third determination module;

[0092] Fig. 9 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0093] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art, under the guidance of the content of the present application, can add one or more other operations to the flowchart, or remove one or more operations from the flowchart.

[0094] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0095] In order to enable those skilled in the art to use the contents of this application, the following implementation methods are given in combination with the specific application scenario of "searching for a vehicle to be found". For those skilled in the art, the general principles defined here can be applied to other embodiments and application scenarios without departing from the spirit and scope of this application.

[0096] The following methods, devices, electronic devices or computer-readable storage media of the embodiments of the present application can be applied to any scenario that requires searching for a shared vehicle. The embodiments of the present application are not limited to specific application scenarios. Any solution using the shared vehicle searching method and device provided by the embodiments of the present application is within the protection scope of the present application.

[0097] It is worth noting that before the present application was proposed, there was a method of conducting a carpet search for shared vehicles by dividing the area. Specifically, the area in the map was divided into grids according to the geographical location, manpower was allocated according to the size of the grid area, and the silent shared vehicles were retrieved by traversing the streets. Although this method is simple and easy, it is a carpet search that not only requires a lot of manpower and material resources, but also there is a situation where only a few silent shared vehicles are found from many search areas. Therefore, the efficiency of finding vehicles by this method is low.

[0098] In response to the above problems, the embodiments of the present application can determine the positioning reliability of each candidate vehicle to be found by acquiring historical data of multiple candidate vehicles and a trained discriminant model, and can screen out the vehicle to be found from the multiple candidate vehicles based on the positioning reliability of each candidate vehicle to be found. Then, based on the positioning positions and positioning reliability corresponding to each vehicle to be found, each vehicle to be found is density clustered to determine the vehicle gathering area. Furthermore, based on the vehicle gathering area, a vehicle search path is determined. In this way, through the determined vehicle search path, as many vehicles to be found as possible can be found in one vehicle search process, thereby improving the efficiency of vehicle search.

[0099] To facilitate the understanding of the present application, the technical solution provided by the present application is described in detail below in conjunction with specific embodiments.

[0100] Figure 1 This is a flow chart of a method for finding a shared vehicle provided in an embodiment of the present application. Figure 1 As shown, the method for finding a shared vehicle provided in an embodiment of the present application includes the following steps:

[0101] S101: Acquire historical data of multiple candidate vehicles to be searched for, and determine the location reliability of each candidate vehicle to be searched for based on the historical data of each candidate vehicle to be searched for and a trained discriminant model.

[0102] In the specific implementation, the historical data of the candidate vehicles are first obtained. Here, the candidate vehicles are shared vehicles that have been rarely used by users in recent period of time, such as shared vehicles that have been parked in remote areas by users and gradually become silent, where shared vehicles include but are not limited to shared bicycles and shared electric vehicles; the historical data of the candidate vehicles can characterize the difficulty of finding the candidate vehicles to a certain extent, and then, according to the historical data of each candidate vehicle and the trained discriminant model, the positioning reliability of each candidate vehicle can be determined, that is, the reliability of the positioning of the candidate vehicle can be determined. The discriminant model can be a neural network model, such as a long short-term memory artificial neural network (Long-Short Term Memory, LSTM) model, a deep learning network.

[0103] Here, the historical data includes the historical log data of each candidate vehicle and the historical travel data of each user using the candidate vehicle, wherein the historical log data includes the communication data between the candidate vehicle and the external device; the historical travel data includes the travel location data, travel time data, and travel duration data.

[0104] In a specific implementation, the historical log data of each candidate vehicle includes communication data between the candidate vehicle and external devices. These communication data can, to a certain extent, characterize the difficulty of finding the candidate vehicle. Here, external devices include but are not limited to satellite devices, base station devices, and servers. Specifically, the communication data includes but is not limited to vehicle location information, vehicle positioning satellite information, vehicle positioning base station information, vehicle heartbeat information, vehicle heartbeat time series information, etc. These communication data can be generated when the candidate vehicle communicates with a satellite device, when the candidate vehicle communicates with a base station device, when the candidate vehicle communicates with a server, or when the Bluetooth lock of the candidate vehicle broadcasts information.

[0105] Here, the historical travel data of each candidate vehicle search can characterize the travel characteristics of multiple users using the candidate vehicle search, wherein the historical travel data includes travel location data, travel time data, and travel duration data.

[0106] Furthermore, before obtaining the historical data of candidate search vehicles, it is necessary to first screen out candidate search vehicles from a large number of shared bicycles, that is, determine the candidate search vehicles according to the following steps:

[0107] Within a preset historical period, the number of times each shared vehicle is used is counted; and shared vehicles whose number of uses is less than or equal to the preset number are determined as candidate search vehicles.

[0108] In the specific implementation, when users use shared vehicles, since they can be used and parked at any time, it is inevitable that shared vehicles will be parked in remote areas and gradually become silent or even lose contact. In this case, silent shared vehicles will be searched, that is, candidate search vehicles will be searched among a large number of vehicles, and the found candidate search vehicles will be dispatched to hot spots, which can further improve the utilization rate of shared vehicle resources. The following is an explanation of the process of screening candidate search vehicles from a large number of shared vehicles. Specifically, the statistical time can be set in advance according to needs. For example, when selecting candidate search vehicles, the closest time to the current distance is selected, that is, the preset historical time, and the number of times each shared vehicle is used is counted within the preset historical time. Then, according to the number of uses, it is determined whether the shared vehicle is a silent shared vehicle, that is, it is determined whether the shared vehicle is a candidate search vehicle. If the number of uses of the shared vehicle is less than or equal to the preset number, the shared vehicle is determined as a candidate search vehicle.

[0109] Further, the process of determining the location reliability of each candidate vehicle is elaborated, that is, in step S101, the location reliability of each candidate vehicle is determined according to the historical data of each candidate vehicle and the trained discriminant model, including the following steps:

[0110] Extract characteristic information of each candidate vehicle from historical data of each candidate vehicle; input the characteristic information of each candidate vehicle into a trained discriminant model to determine the location reliability of each candidate vehicle.

[0111] In a specific implementation, for each candidate vehicle, when determining the location reliability of the candidate vehicle, feature information that characterizes the characteristics of the candidate vehicle can be first extracted from the historical data of the candidate vehicle. The feature information can characterize the positioning accuracy of the candidate vehicle to a certain extent. Further, the feature information of the candidate vehicle is input into a trained discriminant model to obtain the location reliability of the candidate vehicle, that is, the positioning accuracy of the candidate vehicle. Here, the working principle of the discriminant model is to determine the similarity between the candidate vehicle and the accurately positioned shared vehicle, and the similarity between the candidate vehicle and the inaccurately positioned shared vehicle through the feature information of each candidate vehicle, and then determine the positioning accuracy of the candidate vehicle, that is, determine the location reliability of the candidate vehicle.

[0112] Furthermore, the process of generating the trained discriminant model is described, that is, the trained discriminant model is generated according to the following steps:

[0113] The historical data of candidate search vehicles with positioning errors less than or equal to the preset error are used as positive samples, and the historical data of candidate search vehicles with positioning errors greater than the preset error are used as negative samples; based on the positive samples and the negative samples, the initial discriminant model is trained to generate a trained discriminant model.

[0114] In the specific implementation, before training the discriminant model, a large number of training samples need to be obtained first. Here, the historical data of shared vehicles that have been successfully found through real-time positioning within the most recent period of time can be used as positive samples, and the historical data of the remaining shared vehicles can be used as negative samples. That is, the historical data of candidate search vehicles with a positioning error less than or equal to the preset error are used as positive samples, and the historical data of candidate search vehicles with a positioning error greater than the preset error are used as negative samples. Furthermore, the initial discriminant model is trained with positive samples and negative samples to generate a trained discriminant model, and the discriminant model is used to determine the positioning reliability of the candidate search vehicle.

[0115] S102: Filtering out a vehicle to be found from the plurality of candidate vehicles to be found according to the location reliability of each candidate vehicle to be found.

[0116] In a specific implementation, after determining the location reliability of each candidate vehicle through its historical data and discrimination model, that is, after determining the difficulty of finding each candidate vehicle, the vehicle to be found can be directly screened out from multiple candidate vehicles through the size of the location reliability, that is, the candidate vehicles that are relatively easy to find through positioning information can be screened out; or the candidate vehicles with lower location reliability can be eliminated first through the size of the location reliability, that is, the candidate vehicles that are difficult to find through positioning information can be eliminated, and then the vehicle to be found can be screened out. In this way, by eliminating candidate vehicles with lower location reliability and only searching for vehicles with relatively higher location reliability among multiple candidate vehicles, the efficiency of finding silent shared vehicles can be improved.

[0117] Further, after determining the location reliability of each candidate vehicle to be searched, the priority of each candidate vehicle to be searched can be determined according to the location reliability, and then the vehicle to be searched can be determined according to the priority. That is, in step S102, the vehicle to be searched is screened from the plurality of candidate vehicles to be searched according to the location reliability of each candidate vehicle to be searched, including the following steps:

[0118] The vehicle search priority of each candidate vehicle is determined according to the location reliability of each candidate vehicle; and the candidate vehicle whose vehicle search priority is greater than or equal to the preset priority is determined as the vehicle to be found.

[0119] In a specific implementation, different levels of location confidence can be divided into grades in advance according to the size of the location confidence. Specifically, candidate search vehicles in a location confidence interval can be divided into one grade. In this way, candidate search vehicles corresponding to different location confidences are divided into multiple grades, wherein the grade can be a vehicle search priority. Here, according to the location confidence of each candidate search vehicle, the vehicle search priority corresponding to the location confidence is determined. If the vehicle search priority of the candidate search vehicle is greater than or equal to the preset priority, the candidate search vehicle can be determined as the vehicle to be searched. Otherwise, the candidate search vehicle is not used as the next vehicle to be searched, that is, the relatively unfindable vehicle is abandoned.

[0120] Here, in addition to the above-mentioned method of determining the vehicle to be found by vehicle search priority, it is also possible to directly determine whether the candidate search vehicle is the vehicle to be found based on the size of the location confidence of each candidate search vehicle. Specifically, a preset confidence threshold can be set in advance, and the candidate search vehicle whose location confidence is greater than or equal to the preset confidence threshold is determined as the vehicle to be found.

[0121] S103: Density clustering is performed on each of the vehicles to be found according to the positioning positions and positioning confidences corresponding to each of the vehicles to be found, and a vehicle gathering area is determined.

[0122] In a specific implementation, after selecting relatively easy-to-find vehicles from multiple candidate vehicles, density clustering is performed on the determined vehicles based on their positioning positions and positioning confidences, and then the vehicle aggregation areas of these vehicles are determined, wherein the positioning position of each vehicle to be found can be the geographical location where the vehicle to be found is currently located.

[0123] Here, the clustering model can be pre-trained, and the vehicle gathering area corresponding to each vehicle to be found can be determined by inputting the positioning position and positioning confidence corresponding to each vehicle to be found into the clustering model, wherein the clustering model can be an unsupervised machine learning model.

[0124] S104: Determine a vehicle search path based on the vehicle gathering area.

[0125] In a specific implementation, after determining the vehicle gathering areas of each vehicle to be found, the total vehicle search path for finding the vehicle to be found in each vehicle gathering area can be determined based on the area position of each vehicle gathering area. Here, each vehicle gathering area contains multiple vehicles to be found. In this way, through the determined vehicle search path, it is possible to retrieve as many vehicles to be found as possible in one vehicle search process, thereby improving the efficiency of vehicle search.

[0126] In an embodiment of the present application, by acquiring historical data of multiple candidate vehicles and a trained discriminant model, the positioning reliability of each candidate vehicle can be determined, and based on the positioning reliability of each candidate vehicle, the vehicle to be found can be screened out from the multiple candidate vehicles. Then, based on the positioning positions and positioning reliability corresponding to each vehicle to be found, each vehicle to be found is density clustered, and the vehicle gathering area can be determined. Furthermore, based on the vehicle gathering area, the vehicle search path is determined. In this way, through the determined vehicle search path, it is possible to retrieve as many vehicles to be found as possible in one vehicle search process, which can improve the efficiency of vehicle search.

[0127] Figure 2 This is a flow chart of another method for finding a shared vehicle provided in an embodiment of the present application. Figure 2 As shown, the method for finding a shared vehicle provided in an embodiment of the present application includes the following steps:

[0128] S201: Obtain historical data of multiple candidate search vehicles, and determine the location reliability of each candidate search vehicle based on the historical data of each candidate search vehicle and the trained discriminant model.

[0129] S202: Filtering out a vehicle to be found from the plurality of candidate vehicles to be found according to the location reliability of each candidate vehicle to be found.

[0130] S203: Clustering the positions of the vehicles to be found according to their positioning positions to obtain a plurality of candidate clustering areas.

[0131] In a specific implementation, a candidate vehicle with a relatively high positioning confidence is selected from multiple candidate vehicles, that is, a candidate vehicle that is relatively easy to find through the positioning position is selected and determined as the vehicle to be found. Furthermore, each vehicle to be found is preliminarily clustered according to the positioning position of each vehicle to be found, and multiple candidate clustering areas are obtained, wherein each candidate clustering area contains at least one vehicle to be found, and each candidate clustering area occupies an area within a preset range in terms of geographical location. If a candidate area includes at least two vehicles to be found, the distance between any two vehicles to be found in the candidate clustering area is less than or equal to the preset distance.

[0132] S204: For each candidate gathering area among the multiple candidate gathering areas, the vehicle density of each candidate gathering area is calculated according to the total number of vehicles to be found in each candidate gathering area and the location reliability of each vehicle to be found.

[0133] In the specific implementation, considering that the positioning reliability of each vehicle to be found may be different, that is, the positioning accuracy of each vehicle to be found is different, it is not possible to completely rely on the positioning position to cluster the vehicles to be found. Here, the two conditions of positioning position and positioning reliability are used together to perform density clustering on each vehicle to be found. Specifically, each vehicle to be found is preliminarily clustered according to the positioning position to obtain multiple candidate clustering areas. Then, the candidate clustering areas are further screened according to the vehicle density to determine the vehicle gathering area, wherein the vehicle density of each candidate gathering area is determined by the total number of vehicles to be found in the candidate gathering area and the positioning reliability of each vehicle to be found in the candidate gathering area.

[0134] Here, the total number of vehicles to be found in each candidate clustering area, that is, the total number of vehicles to be found belonging to the candidate clustering area, can be used as a weight by the location reliability of the vehicles to be found in the candidate clustering area, and then the vehicle density in each candidate clustering area is calculated based on the total number and the location reliability of each vehicle to be found.

[0135] In one example, if the total number of vehicles to be found in the candidate gathering area A is 100, among which the location confidence of 50 vehicles to be found is 90%, the location confidence of 30 vehicles to be found is 80%, and the location confidence of 20 vehicles to be found is 60%, then the vehicle density is 50×90%+30×80%+20×60%=81.

[0136] S205: Determine the candidate gathering areas where the vehicle density is greater than or equal to the preset density as vehicle gathering areas.

[0137] In a specific embodiment, each vehicle to be found is first clustered preliminarily by positioning the position to obtain a plurality of candidate clustering areas, and then the candidate clustering areas are further screened by vehicle density to determine the vehicle gathering areas. Specifically, a preset density can be set in advance, and after determining the vehicle density of each candidate gathering area, the candidate gathering areas with vehicle density greater than or equal to the preset density are determined as vehicle gathering areas.

[0138] Here, the candidate gathering area with vehicle density less than the preset density can be determined as a scattered vehicle area, wherein theoretically the number of vehicles to be found contained in the scattered vehicle area is much smaller than the number of vehicles to be found contained in the gathering vehicle area.

[0139] S206: Determine a vehicle search path based on the vehicle gathering area.

[0140] Among them, the description of steps S201, S202, and S206 can refer to the description of steps S101, S102, and S104, and can achieve the same technical effects, which will not be elaborated here.

[0141] Further, the method of determining the vehicle search path can be determined according to the number of vehicle gathering areas. Specifically, the number of vehicle gathering areas determined is first counted. Here, the case where the number of vehicle gathering areas is greater than or equal to a preset threshold is described, that is, the first method of determining the vehicle search path is described. In step S206, the vehicle search path is determined based on the vehicle gathering areas, including the following steps:

[0142] If the number of areas is greater than or equal to a preset threshold, the first path between each vehicle gathering area is determined according to the area position of each vehicle gathering area, and the second path between each vehicle to be found in each vehicle gathering area is determined according to the positioning position of each vehicle to be found in each vehicle gathering area; the vehicle search path is determined according to the first path and the second path.

[0143] In a specific implementation, if the number of vehicle gathering areas is greater than or equal to a preset threshold, indicating that there are more vehicle gathering areas with higher vehicle density, the vehicles to be found in the vehicle gathering areas can be directly searched without considering the scattered vehicle areas with lower vehicle density. This can also ensure that more vehicles to be found can be found in one vehicle search. Moreover, by giving up the search for vehicles to be found in the scattered vehicle areas, the efficiency of vehicle search can be further improved. Specifically, the regional position of each vehicle gathering area can be obtained first, and then the first path between each vehicle gathering area can be determined. For each vehicle gathering area, the second path between each vehicle to be found in the vehicle gathering area can be determined according to the positioning position of each vehicle to be found in the vehicle gathering area. Further, the vehicle search path is determined according to the first path between the vehicle gathering areas and the vehicle gathering areas, and the second path between each vehicle to be found in each vehicle gathering area. Here, the first path and the second path are both optimal paths. The optimal path refers to the path with the shortest distance or the shortest time. In this way, the optimal path between each vehicle gathering area and the optimal path between each vehicle to be found in each vehicle gathering area are connected in series through the optimal first path and the optimal second path, so as to determine the optimal vehicle search path.

[0144] Further, the method of determining the vehicle search path can be determined according to the number of vehicle gathering areas. Specifically, the number of vehicle gathering areas determined is first counted. Here, the case where the number of vehicle gathering areas is less than a preset threshold is described, that is, the second method of determining the vehicle search path is described. In step S206, the vehicle search path is determined based on the vehicle gathering areas, including the following steps:

[0145] If the number of areas is less than the preset threshold, the vehicle search path is determined based on the area position of each vehicle gathering area, the positioning position of each vehicle to be found in each vehicle gathering area, the positioning position of the vehicle scattered area, and the positioning position of each vehicle to be found in each vehicle scattered area; wherein the vehicle scattered area is a candidate gathering area where the vehicle density is less than the preset density.

[0146] In a specific implementation, if the number of vehicle gathering areas is less than a preset threshold, it means that there are fewer vehicle gathering areas with higher vehicle density, and it is necessary to take into account both vehicle gathering areas and vehicle scattered areas to ensure that more vehicles to be found are found in one vehicle search. Specifically, the regional position of each vehicle gathering area, the positioning position of each vehicle to be found in each vehicle gathering area, the positioning position of the vehicle scattered area, and the positioning position of each vehicle to be found in each vehicle scattered area can be obtained first, and then the shortest path in each vehicle gathering area and the vehicle scattered areas along the way are connected in series to determine the vehicle search path.

[0147] Furthermore, after determining the vehicle search path, it is also necessary to consider whether the transport capacity required for the vehicle to be found in the carrier vehicle search path exceeds the preset capacity of the carrier truck. If it exceeds, it is necessary to dispatch multiple carrier trucks to search for the vehicle. That is, after determining the vehicle search path based on the vehicle gathering area in step S206, the following steps are also included:

[0148] According to the number of vehicles to be found in the vehicle search path and the path length of the vehicle search path, the transportation capacity required to transport the vehicles to be found in the vehicle search path is determined; if the transportation capacity is greater than the preset capacity, the vehicle search path is divided according to the preset capacity and the transportation capacity to obtain at least two divided paths; according to each divided path, a vehicle search work order corresponding to each divided path is generated.

[0149] In the specific implementation, after determining the vehicle search path, the transport capacity required for the vehicles to be found in the carrier vehicle search path must also be considered, and a vehicle search work order is generated based on the transport capacity. Specifically, the number of vehicles to be found in the vehicle search path and the path length of the vehicle search path are first determined, and then the transport capacity required for the vehicles to be found in the carrier vehicle search path is determined. Furthermore, if it is determined that the transport capacity is greater than the preset capacity, it means that the transport capacity has exceeded the capacity of a vehicle search team to find the vehicle. Therefore, it is necessary to determine the number of vehicle search paths to be divided and the divided paths based on the transport capacity and the preset capacity, and then generate a vehicle search work order for each divided path. Here, the transport capacity and the preset capacity can be used to determine the number of carrier trucks that need to be dispatched and the number of personnel dispatched to search for vehicles.

[0150] Furthermore, a vehicle search may be performed once at preset time intervals. For example, after searching for a vehicle according to the current vehicle search path, a new vehicle search path may be regenerated after a preset time interval, and the vehicle search may be performed according to the new vehicle search path, thereby reducing the number of silent shared vehicles and improving the utilization rate of shared vehicles.

[0151] In an embodiment of the present application, by acquiring historical data of multiple candidate vehicles and a trained discriminant model, the positioning reliability of each candidate vehicle can be determined, and based on the positioning reliability of each candidate vehicle, the vehicle to be found can be screened out from the multiple candidate vehicles. Then, based on the positioning positions and positioning reliability corresponding to each vehicle to be found, each vehicle to be found is density clustered, and the vehicle gathering area can be determined. Furthermore, based on the vehicle gathering area, the vehicle search path is determined. In this way, through the determined vehicle search path, it is possible to retrieve as many vehicles to be found as possible in one vehicle search process, which can improve the efficiency of vehicle search.

[0152] Based on the same application concept, the embodiments of the present application also provide a shared vehicle searching device corresponding to the shared vehicle searching method provided in the above embodiments. Since the principle of solving the problem by the device in the embodiments of the present application is similar to the shared vehicle searching method in the above embodiments of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0153] like Figures 3 to 8 As shown, Figure 3 One of the functional module diagrams of a shared vehicle search device 300 provided in an embodiment of the present application is shown; Figure 4 Shows Figure 3 Functional module diagram of the first determination module 310; Figure 5 The second functional module diagram of a shared vehicle search device 300 provided in an embodiment of the present application is shown; Figure 6 Shows Figure 5Functional module diagram of the screening module 320; Figure 7 Shows Figure 5 Functional module diagram of the second determination module 330; Figure 8 Shows Figure 5 340 is a functional module diagram of the third determination module 340.

[0154] like Figure 3 and Figure 5 As shown, the shared vehicle searching device 300 includes:

[0155] A first determination module 310 is used to obtain historical data of multiple candidate search vehicles, and determine the location reliability of each candidate search vehicle based on the historical data of each candidate search vehicle and the trained discriminant model;

[0156] A screening module 320, configured to screen a vehicle to be found from the plurality of candidate vehicles according to the location reliability of each candidate vehicle to be found determined by the first determining module 310;

[0157] The second determination module 330 is used to perform density clustering on each vehicle to be found according to the positioning positions and positioning confidences corresponding to each vehicle to be found, and determine the vehicle gathering area;

[0158] The third determination module 340 is used to determine a vehicle search path based on the vehicle gathering area determined by the second determination module 330.

[0159] In a possible implementation, Figure 3 As shown, the first determination module 310 is further used to determine the candidate search vehicle according to the following steps:

[0160] Count the number of times each shared vehicle is used within a preset historical period;

[0161] A shared vehicle that has been used less than or equal to a preset number of times is determined as a candidate vehicle to be searched.

[0162] In a possible implementation, Figure 4 As shown, the first determination module 310 includes:

[0163] An extraction unit 312 is used to extract characteristic information of each candidate vehicle from the historical data of each candidate vehicle;

[0164] The first determination unit 314 is used to input the feature information of each candidate vehicle to be searched into the trained discriminant model to determine the location reliability of each candidate vehicle.

[0165] In a possible implementation, Figure 5As shown, the shared vehicle search device 300 further includes a training module 350; the training module 350 is used to generate a trained discriminant model according to the following steps:

[0166] Taking the historical data of the candidate vehicles for which the positioning error is less than or equal to the preset error as positive samples, and taking the historical data of the candidate vehicles for which the positioning error is greater than the preset error as negative samples;

[0167] The initial discriminant model is trained according to the positive samples and the negative samples to generate a trained discriminant model.

[0168] In a possible implementation, Figure 6 As shown, the screening module 320 includes:

[0169] A second determining unit 322 is used to determine the vehicle search priority of each candidate vehicle search according to the location reliability of each candidate vehicle search;

[0170] The third determining unit 324 is used to determine the candidate search vehicles whose search priority is greater than or equal to the preset priority as the vehicles to be searched.

[0171] In a possible implementation, Figure 7 As shown, the second determination module 330 includes:

[0172] A generating unit 332 is used to cluster the positions of the vehicles to be found according to the positioning positions of the vehicles to be found, and obtain multiple candidate clustering areas;

[0173] A calculation unit 334 is used to calculate the vehicle density of each candidate gathering area according to the total number of vehicles to be found in each candidate gathering area and the location reliability of each vehicle to be found for each candidate gathering area among the multiple candidate gathering areas;

[0174] The fourth determining unit 336 is used to determine the candidate gathering area with a vehicle density greater than or equal to a preset density as a vehicle gathering area.

[0175] In a possible implementation, Figure 8 As shown, the third determination module 340 includes:

[0176] A counting unit 342, used to count the number of determined vehicle gathering areas;

[0177] A fifth determining unit 344 is configured to determine, if the number of areas is greater than or equal to a preset threshold, a first path between each vehicle gathering area according to the area position of each vehicle gathering area, and a second path between each vehicle to be found in each vehicle gathering area according to the positioning position of each vehicle to be found in each vehicle gathering area;

[0178] The sixth determining unit 346 is used to determine the vehicle search path according to the first path and the second path.

[0179] In a possible implementation, Figure 8 As shown, the third determination module 340 is further used to determine the vehicle search path according to the following steps:

[0180] If the number of areas is less than the preset threshold, the vehicle search path is determined according to the area positions of each vehicle gathering area, the positioning positions of each vehicle to be found in each vehicle gathering area, the positioning positions of the vehicle scattered areas, and the positioning positions of each vehicle to be found in each vehicle scattered area;

[0181] Among them, the scattered vehicle area is a candidate gathering area where the vehicle density is less than the preset density.

[0182] In a possible implementation, Figure 5 As shown, the shared vehicle search device 300 further includes a generation module 360; the generation module 360 ​​is used to generate a vehicle search work order according to the following steps:

[0183] Determining the transport capacity required for transporting the vehicles to be found in the vehicle-finding path according to the number of the vehicles to be found in the vehicle-finding path and the length of the vehicle-finding path;

[0184] If the transport capacity is greater than the preset capacity, the vehicle search path is segmented according to the preset capacity and the transport capacity to obtain at least two segmented paths;

[0185] According to each segmentation path, a vehicle search work order corresponding to each segmentation path is generated.

[0186] In a possible implementation, Figure 5 As shown, the shared vehicle search device 300 further includes an execution module 370; the execution module 370 is used to:

[0187] The vehicle search is performed once at a preset time interval.

[0188] In a possible implementation, the historical data includes historical log data of each candidate vehicle to be searched and historical travel data of each user using the candidate vehicle to be searched;

[0189] Among them, the historical log data includes the communication data between the candidate search vehicle and the external device; the historical travel data includes travel location data, travel time data, and travel duration data.

[0190] Based on the same application concept, see Fig. 9 As shown, it is a schematic diagram of the structure of an electronic device 900 provided in an embodiment of the present application, including: a processor 910, a memory 920 and a bus 930, the memory 920 stores machine-readable instructions executable by the processor 910, when the electronic device 900 is running, the processor 910 and the memory 920 communicate with each other through the bus 930, and the machine-readable instructions are executed by the processor 910 when running to perform the steps of the method for finding a shared vehicle as described in any of the above embodiments.

[0191] Specifically, when the machine-readable instruction is executed by the processor 910, the following processing may be performed:

[0192] Obtaining historical data of multiple candidate search vehicles, and determining the location reliability of each candidate search vehicle based on the historical data of each candidate search vehicle and the trained discriminant model;

[0193] Filtering a vehicle to be found from the plurality of candidate vehicles according to the location reliability of each candidate vehicle to be found;

[0194] According to the positioning positions and positioning confidences corresponding to the vehicles to be found, density clustering is performed on the vehicles to be found to determine the vehicle gathering area;

[0195] Based on the vehicle gathering area, a vehicle search path is determined.

[0196] Based on the same application concept, an embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the shared vehicle search method provided in the above embodiment are executed.

[0197] Specifically, the storage medium can be a general storage medium, such as a mobile disk, a hard disk, etc. When the computer program on the storage medium is run, it can execute the above-mentioned shared vehicle search method. By determining the vehicle search path, it is possible to retrieve as many vehicles as possible in one vehicle search process, thereby improving the efficiency of vehicle search.

[0198] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0199] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0200] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0201] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0202] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for finding a shared vehicle, characterized in that: The searching method comprises: Acquire historical data of multiple candidate vehicles, and determine the location reliability of each candidate vehicle according to the historical data of each candidate vehicle and the trained discriminant model, wherein the historical data at least includes historical log data and historical travel data of each candidate vehicle, the historical log data at least includes communication data between the candidate vehicle and an external device, the communication data at least includes vehicle location information, vehicle positioning satellite information, vehicle positioning base station information, vehicle heartbeat information, and vehicle heartbeat time series information, and the historical travel data at least includes travel location data, travel time data, and travel duration data; Determine the vehicle search priority of each candidate vehicle search based on the location reliability of each candidate vehicle search; Determine the candidate search vehicles whose search priority is greater than or equal to the preset priority as the vehicles to be searched; According to the positioning positions of each vehicle to be found, each vehicle to be found is clustered to obtain multiple candidate clustering areas; For each candidate gathering area among the multiple candidate gathering areas, according to the total number of vehicles to be found in each candidate gathering area and the location reliability of each vehicle to be found, calculate the vehicle density of each candidate gathering area; Determine a candidate gathering area where the vehicle density is greater than or equal to a preset density as a vehicle gathering area; Determining a vehicle search path based on the vehicle gathering area; Determining the transport capacity required for transporting the vehicles to be found in the vehicle-finding path according to the number of the vehicles to be found in the vehicle-finding path and the length of the vehicle-finding path; If the transport capacity is greater than the preset capacity, the vehicle search path is segmented according to the preset capacity and the transport capacity to obtain at least two segmented paths; According to each segmentation path, a vehicle search work order corresponding to each segmentation path is generated.

2. The searching method according to claim 1, characterized in that: The search method further includes determining candidate search vehicles according to the following steps: Count the number of times each shared vehicle is used within a preset historical period; A shared vehicle that has been used less than or equal to a preset number of times is determined as a candidate vehicle to be searched.

3. The searching method according to claim 1, characterized in that: The method of determining the location reliability of each candidate vehicle to be searched for based on the historical data of each candidate vehicle to be searched for and the trained discrimination model includes: Extracting characteristic information of each candidate vehicle from historical data of each candidate vehicle; The characteristic information of each candidate vehicle is input into the trained discriminant model to determine the location reliability of each candidate vehicle.

4. The searching method according to claim 1, characterized in that: The search method further comprises generating a trained discriminant model according to the following steps: Taking the historical data of the candidate vehicles for which the positioning error is less than or equal to the preset error as positive samples, and taking the historical data of the candidate vehicles for which the positioning error is greater than the preset error as negative samples; The initial discriminant model is trained according to the positive samples and the negative samples to generate a trained discriminant model.

5. The searching method according to claim 1, characterized in that: The determining of a vehicle search path based on the vehicle gathering area includes: Counting the number of areas where vehicles are concentrated; If the number of areas is greater than or equal to a preset threshold, determining a first path between each vehicle gathering area according to the area position of each vehicle gathering area, and determining a second path between each vehicle to be found in each vehicle gathering area according to the positioning position of each vehicle to be found in each vehicle gathering area; The vehicle search path is determined according to the first path and the second path.

6. The searching method according to claim 5, characterized in that: The determining of a vehicle search path based on the vehicle gathering area includes: If the number of areas is less than the preset threshold, the vehicle search path is determined according to the area positions of each vehicle gathering area, the positioning positions of each vehicle to be found in each vehicle gathering area, the positioning positions of the vehicle scattered areas, and the positioning positions of each vehicle to be found in each vehicle scattered area; Among them, the scattered vehicle area is a candidate gathering area where the vehicle density is less than the preset density.

7. A device for finding a shared vehicle, characterized in that: The searching device comprises: A first determination module is used to obtain historical data of multiple candidate search vehicles, and determine the location reliability of each candidate search vehicle according to the historical data of each candidate search vehicle and the trained discriminant model, wherein the historical data at least includes historical log data and historical travel data of each candidate search vehicle, the historical log data at least includes communication data between the candidate search vehicle and an external device, the communication data at least includes vehicle location information, vehicle positioning satellite information, vehicle positioning base station information, vehicle heartbeat information, and vehicle heartbeat time series information, and the historical travel data at least includes travel location data, travel time data, and travel duration data; A screening module is used to determine the vehicle search priority of each candidate vehicle according to the location reliability of each candidate vehicle; Determine the candidate search vehicles whose search priority is greater than or equal to the preset priority as the vehicles to be searched; The second determination module includes: A generating unit, used for clustering the positions of the vehicles to be found according to the positioning positions of the vehicles to be found, and obtaining a plurality of candidate clustering areas; A calculation unit, configured to calculate, for each of the plurality of candidate gathering areas, a vehicle density of each candidate gathering area according to a total number of vehicles to be found in each candidate gathering area and a location reliability of each vehicle to be found; A fourth determining unit, configured to determine a candidate gathering area having a vehicle density greater than or equal to a preset density as a vehicle gathering area; A third determining module, configured to determine a vehicle search path based on the vehicle gathering area determined by the second determining module; A generation module is used to determine the transportation capacity required to transport the vehicles to be found in the vehicle searching path according to the number of vehicles to be found in the vehicle searching path and the path length of the vehicle searching path; if the transportation capacity is greater than the preset capacity, the vehicle searching path is divided according to the preset capacity and the transportation capacity to obtain at least two divided paths; and according to each divided path, a vehicle searching work order corresponding to each divided path is generated.

8. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and the machine-readable instructions are executed by the processor to execute the steps of the method for finding a shared vehicle as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for finding a shared vehicle as described in any one of claims 1 to 6 are executed.

Images