CN111861627A

CN111861627A - Shared vehicle searching method and device, electronic equipment and storage medium

Info

Publication number: CN111861627A
Application number: CN202010261446.5A
Authority: CN
Inventors: 王毅星; 吴艳平; 周齐
Original assignee: Beijing Qisheng Technology Co Ltd
Current assignee: Beijing Qisheng Technology Co Ltd
Priority date: 2020-04-03
Filing date: 2020-04-03
Publication date: 2020-10-30

Abstract

The present application relates to the field of data processing technologies, and in particular, to a method and an apparatus for searching for a shared vehicle, an electronic device, and a storage medium. According to the method, through the acquired historical data of the vehicles searched by the multiple candidates and the trained discrimination model, the position confidence level of each candidate for searching the vehicles can be determined, the position confidence level of each candidate for searching the vehicles can be obtained, the vehicles to be searched can be screened out from the multiple candidates, and further, according to the positioning positions and the positioning confidence levels corresponding to the vehicles to be searched respectively, density clustering is carried out on the vehicles to be searched, the vehicle gathering area can be determined, further, the vehicle searching path is determined based on the vehicle gathering area, in this way, the vehicle searching process can be realized at one time, the vehicles to be searched as many as possible are found back, and the vehicle searching efficiency can be improved.

Description

Shared vehicle searching method and device, electronic equipment and storage medium

Technical Field

The present application relates to the field of data processing technologies, and in particular, to a method and an apparatus for searching for a shared vehicle, an electronic device, and a storage medium.

Background

The shared bicycle and the shared electric vehicle are used as a new travel mode, so that the travel life of people is greatly facilitated, users can conveniently take and place at any time and park at any time, and the shared bicycle and the shared electric vehicle have great freedom, so that the shared bicycle and the shared electric vehicle are popular among the users.

However, the freedom degree is a one-handle double-blade sword, which is convenient for users to go out, and meanwhile, the conditions that the vehicles are parked in remote areas and are gradually silenced or even disconnected occur inevitably occur, generally, silent shared vehicles are searched, and the searched shared vehicles are dispatched to a hot area, so that the utilization rate of shared vehicle resources is improved. Therefore, how to efficiently find out more silent shared vehicles is a problem to be solved.

Disclosure of Invention

In view of this, embodiments of the present application at least provide a method and an apparatus for finding a shared vehicle, an electronic device, and a storage medium, which can find as many vehicles to be found as possible in one vehicle finding process, and can improve vehicle finding efficiency.

The application mainly comprises the following aspects:

in a first aspect, an embodiment of the present application provides a method for finding a shared vehicle, where the method for finding includes:

Acquiring historical data of a plurality of candidate searched vehicles, and determining the position reliability of each candidate searched vehicle according to the historical data of each candidate searched vehicle and the trained discrimination model;

screening out vehicles to be searched from the candidate searched vehicles according to the position credibility of each candidate searched vehicle;

according to the positioning position and the positioning confidence degree which are respectively corresponding to each vehicle to be searched, performing density clustering on each vehicle to be searched, and determining a vehicle aggregation area;

determining a vehicle finding path based on the vehicle gathering area.

In one possible embodiment, the finding method further comprises determining candidate finding vehicles according to the following steps:

counting the use times of each shared vehicle within a preset historical time;

and determining the shared vehicle with the use frequency less than or equal to the preset frequency as a candidate searching vehicle.

In one possible embodiment, the determining the position reliability of each candidate search vehicle according to the historical data of each candidate search vehicle and the trained discriminant model includes:

extracting characteristic information of each candidate vehicle from the historical data of each candidate vehicle;

And inputting the characteristic information of each candidate searched vehicle into the trained discriminant model, and determining the position reliability of each candidate searched vehicle.

In a possible embodiment, the finding method further includes generating a trained discriminant model according to the following steps:

taking historical data of candidate searched vehicles with positioning errors smaller than or equal to preset errors as positive samples, and taking historical data of candidate searched vehicles with positioning errors larger than the preset errors as negative samples;

and training an initial discrimination model according to the positive sample and the negative sample to generate a trained discrimination model.

In a possible embodiment, the screening out the vehicle to be searched from the candidate searched vehicles according to the position reliability of each candidate searched vehicle includes:

determining the vehicle searching priority of each candidate searched vehicle according to the position credibility of each candidate searched vehicle;

and determining the candidate searched vehicle with the vehicle searching priority greater than or equal to the preset priority as the vehicle to be searched.

In a possible implementation manner, the determining a vehicle aggregation area by performing density clustering on each vehicle to be searched according to a positioning position and a positioning confidence degree respectively corresponding to each vehicle to be searched includes:

According to the positioning position of each vehicle to be searched, carrying out position clustering on each vehicle to be searched to obtain a plurality of candidate gathering areas;

for each candidate gathering area in the plurality of candidate gathering areas, calculating the vehicle density of each candidate gathering area according to the total number of the vehicles to be searched in each candidate gathering area and the position reliability of each vehicle to be searched;

and determining the candidate gathering area with the vehicle density being greater than or equal to the preset density as the vehicle gathering area.

In one possible embodiment, the determining a vehicle-seeking path based on the vehicle gathering area includes:

counting the number of the determined regions of the vehicle gathering region;

if the number of the areas is larger than or equal to a preset threshold value, determining a first path among the vehicle gathering areas according to the area positions of the vehicle gathering areas, and determining a second path among the vehicles to be searched in each vehicle gathering area according to the positioning positions of the vehicles to be searched in each vehicle gathering area;

and determining the vehicle searching path according to the first path and the second path.

If the number of the areas is smaller than the preset threshold value, determining the vehicle searching path according to the area position of each vehicle gathering area, the positioning position of each vehicle to be searched in each vehicle gathering area, the positioning position of each vehicle scattered area and the positioning position of each vehicle to be searched in each vehicle scattered area;

the vehicle scattered area is a candidate gathering area with the vehicle density smaller than the preset density.

In one possible embodiment, after the determining the vehicle-seeking path based on the vehicle gathering area, the vehicle-seeking method further includes:

determining the capacity required for carrying the vehicles to be searched in the vehicle searching path according to the number of the vehicles to be searched in the vehicle searching path and the path length of the vehicle searching path;

if the capacity is larger than the preset capacity, segmenting the vehicle-searching path according to the preset capacity and the capacity to obtain at least two segmentation paths;

and generating a vehicle searching work order corresponding to each segmentation path according to each segmentation path.

In a possible implementation, the finding method further includes:

and performing vehicle searching once every preset time interval.

In one possible implementation, the historical data includes historical log data of each candidate search vehicle and historical travel data of each user using the candidate search vehicle;

wherein the history log data includes communication data between the candidate seeking vehicle and an external device; the historical trip data comprises trip place data, trip time data and trip duration data.

In a second aspect, an embodiment of the present application further provides a finding device for sharing a vehicle, where the finding device includes:

the first determining module is used for acquiring historical data of a plurality of candidate searched vehicles and determining the position reliability of each candidate searched vehicle according to the historical data of each candidate searched vehicle and the trained distinguishing model;

the screening module is used for screening the vehicles to be searched from the candidate searched vehicles according to the position credibility of each candidate searched vehicle determined by the first determining module;

the second determining module is used for performing density clustering on each vehicle to be searched according to the positioning position and the positioning confidence degree which are respectively corresponding to each vehicle to be searched, and determining a vehicle aggregation area;

and the third determination module is used for determining a vehicle searching path based on the vehicle gathering area determined by the second determination module.

In one possible embodiment, the first determination module is further configured to determine candidate sought vehicles according to the following steps:

counting the use times of each shared vehicle within a preset historical time;

In one possible implementation, the first determining module includes:

an extraction unit configured to extract feature information of each candidate search vehicle from history data of each candidate search vehicle;

and the first determining unit is used for inputting the characteristic information of each candidate searching vehicle into the trained discrimination model and determining the position reliability of each candidate searching vehicle.

In a possible embodiment, the finding device further comprises a training module; the training module is used for generating a trained discrimination model according to the following steps:

In one possible embodiment, the screening module comprises:

the second determining unit is used for determining the vehicle searching priority of each candidate searching vehicle according to the position reliability of each candidate searching vehicle;

and the third determining unit is used for determining the candidate vehicle to be searched, wherein the vehicle searching priority is greater than or equal to the preset priority.

In one possible implementation, the second determining module includes:

the generating unit is used for carrying out position clustering on each vehicle to be searched according to the positioning position of each vehicle to be searched to obtain a plurality of candidate gathering areas;

the calculation unit is used for calculating the vehicle density of each candidate gathering area according to the total number of the vehicles to be searched in each candidate gathering area and the position reliability of each vehicle to be searched in each candidate gathering area;

and a fourth determination unit configured to determine a candidate aggregation area, in which the density of the vehicle is greater than or equal to the preset density, as the vehicle aggregation area.

In one possible implementation, the third determining module includes:

the statistical unit is used for counting the number of the determined regions of the vehicle gathering region;

A fifth determining unit, configured to determine, if the number of the areas is greater than or equal to a preset threshold, a first path between the vehicle aggregation areas according to the area positions of the vehicle aggregation areas, and determine, according to the positioning position of each vehicle to be searched in each vehicle aggregation area, a second path between the vehicles to be searched in each vehicle aggregation area;

a sixth determining unit, configured to determine the vehicle-searching path according to the first path and the second path.

In a possible implementation, the third determining module is further configured to determine the vehicle-finding path according to the following steps:

In a possible implementation, the finding apparatus further includes a generating module; the generating module is used for generating a vehicle searching work order according to the following steps:

In a possible implementation, the finding apparatus further includes an executing module; the execution module is configured to:

and performing vehicle searching once every preset time interval.

In a third aspect, an embodiment of the present application further provides an electronic device, including: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is operated, the processor and the memory communicate with each other through the bus, and the machine-readable instructions are executed by the processor to perform the steps of the shared vehicle finding method according to the first aspect or any one of the possible embodiments of the first aspect.

In a fourth aspect, the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and the computer program is executed by a processor to perform the steps of the shared vehicle finding method described in the first aspect or any one of the possible implementation manners of the first aspect.

In the embodiment of the application, through the acquired historical data of a plurality of candidate searching vehicles and the trained discrimination model, the position confidence level of each candidate searching vehicle can be determined, and according to the position confidence level of each candidate searching vehicle, the vehicles to be searched can be screened out from the plurality of candidate searching vehicles, and further, according to the positioning position and the positioning confidence level corresponding to each vehicle to be searched respectively, density clustering is carried out on each vehicle to be searched, a vehicle gathering area can be determined, further, based on the vehicle gathering area, a vehicle searching path is determined, so that through the determined vehicle searching path, the vehicle searching process can be realized, as many vehicles to be searched as possible can be found, and the vehicle searching efficiency can be improved.

Further, the vehicle density of each candidate gathering area is calculated together according to the total number of the vehicles to be found in each candidate gathering area and the position reliability of each vehicle to be found, and then the candidate gathering area with the vehicle density larger than or equal to the preset density is determined as the vehicle gathering area.

In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.

FIG. 1 is a flow chart illustrating a method for finding a shared vehicle according to an embodiment of the present disclosure;

FIG. 2 is a flow chart illustrating another method for finding a shared vehicle according to an embodiment of the present disclosure;

FIG. 3 is a functional block diagram of a shared vehicle locating device according to an embodiment of the present disclosure;

FIG. 4 illustrates a functional block diagram of the first determination module of FIG. 3;

FIG. 5 is a second functional block diagram of a shared vehicle locating device according to an embodiment of the present disclosure;

FIG. 6 is a functional block diagram of the screening module of FIG. 5;

FIG. 7 is a functional block diagram of the second determination block of FIG. 5;

FIG. 8 is a functional block diagram of the third determination block of FIG. 5;

fig. 9 shows a schematic structural diagram of an electronic device provided in an embodiment of the present application.

Detailed Description

To make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it should be understood that the drawings in the present application are for illustrative and descriptive purposes only and are not used to limit the scope of protection of the present application. Additionally, it should be understood that the schematic drawings are not necessarily drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be performed out of order, and that steps without logical context may be performed in reverse order or concurrently. One skilled in the art, under the guidance of this application, may add one or more other operations to, or remove one or more operations from, the flowchart.

In addition, the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.

To enable those skilled in the art to use the present disclosure in conjunction with a particular application scenario "find vehicle to be sought", the following embodiments are presented to enable those skilled in the art to apply the general principles defined herein to other embodiments and application scenarios without departing from the spirit and scope of the present disclosure.

The following method, apparatus, electronic device or computer-readable storage medium in the embodiments of the present application may be applied to any scenario where a shared vehicle needs to be found, and the embodiments of the present application do not limit a specific application scenario, and any scheme using the method and apparatus for finding a shared vehicle provided in the embodiments of the present application is within the scope of protection of the present application.

It should be noted that, before the present application is proposed, there is a method for searching shared vehicles in a carpet manner by means of area division, specifically, by performing grid division on areas in a map according to geographical locations, allocating manpower according to the size of the grid areas, and finding back silent shared vehicles by traversing streets.

In view of the above problems, in the embodiment of the present application, through the acquired historical data of multiple candidate vehicles to be searched and the trained discriminant model, the location confidence of each candidate vehicle to be searched can be determined, and according to the location confidence of each candidate vehicle to be searched, the vehicles to be searched can be screened out from the multiple candidate vehicles to be searched, and further, according to the location position and the location confidence respectively corresponding to each vehicle to be searched, density clustering is performed on each vehicle to be searched, a vehicle aggregation area can be determined, and further, a vehicle searching path is determined based on the vehicle aggregation area, so that in one vehicle searching process, as many vehicles to be searched as possible can be found out through the determined vehicle searching path, and the vehicle searching efficiency can be improved.

For the convenience of understanding of the present application, the technical solutions provided in the present application will be described in detail below with reference to specific embodiments.

Fig. 1 is a flowchart of a method for finding a shared vehicle according to an embodiment of the present disclosure. As shown in fig. 1, a method for finding a shared vehicle provided in an embodiment of the present application includes the following steps:

s101: and acquiring historical data of a plurality of candidate searched vehicles, and determining the position reliability of each candidate searched vehicle according to the historical data of each candidate searched vehicle and the trained discrimination model.

In a specific implementation, historical data of candidate search vehicles is obtained, where the candidate search vehicles are shared vehicles that have been rarely used by users in the recent period of time, for example, shared vehicles that are parked to remote areas and gradually silenced by users, where the shared vehicles include but are not limited to shared single vehicles and shared electric vehicles; the historical data of the candidate searched vehicles can represent the difficulty degree of the candidate searched vehicles to be found to a certain extent, and further, the position reliability of each candidate searched vehicle can be determined according to the historical data of each candidate searched vehicle and the trained discrimination model, namely, the position reliability of the candidate searched vehicle is determined. The discriminant model may be a neural network model, such as a Long-Short Term Memory artificial neural network (LSTM) model or a deep learning network.

Here, the history data includes history log data of each candidate search vehicle including communication data between the candidate search vehicle and the external device and history trip data of each user using the candidate search vehicle; the historical trip data comprises trip place data, trip time data and trip duration data.

In particular implementations, the historical log data for each candidate seek vehicle includes communication data between the candidate seek vehicle and the external device, the communication data may characterize to some extent how easily the candidate search vehicle is to be found, here, the external device includes, but is not limited to, a satellite device, a base station device, a server, and specifically, the communication data includes, but is not limited to, vehicle position information, vehicle positioning satellite information, vehicle positioning base station information, vehicle heartbeat time series information, and the like, the communication data may be generated when the candidate search vehicle communicates with the satellite device, when the candidate search vehicle communicates with the base station device, when the candidate search vehicle communicates with the server, or when the bluetooth lock of the candidate search vehicle broadcasts information.

Here, the historical travel data of each candidate search vehicle may characterize travel characteristics of a plurality of users using the candidate search vehicle, where the historical travel data includes travel location data, travel time data, and travel duration data.

Further, before obtaining the historical data of the candidate sought vehicles, the candidate sought vehicles need to be screened from a large number of shared single vehicles, that is, the candidate sought vehicles are determined according to the following steps:

Counting the use times of each shared vehicle within a preset historical time; and determining the shared vehicle with the use frequency less than or equal to the preset frequency as a candidate searching vehicle.

In the specific implementation, in the process that the user uses the shared vehicle, the shared vehicle can be used and parked at any time, so that the situation that the shared vehicle is parked in a remote area and is gradually silenced or even disconnected inevitably occurs, and for the situation, the silenced shared vehicle is searched, namely candidate searched vehicles in a large number of vehicles are searched, and the searched candidate searched vehicles are dispatched to a hot area, so that the utilization rate of the shared vehicle resources can be further improved. The following describes a process of screening candidate search vehicles from a large number of shared vehicles, and specifically, a statistical time length may be set in advance according to needs, for example, when a candidate search vehicle is selected, a time length closest to the current time length is selected, that is, a preset historical time length, the number of times of use of each shared vehicle is counted within the preset historical time length, and then, according to the number of times of use, whether the shared vehicle is a silent shared vehicle is determined, that is, whether the shared vehicle is a candidate search vehicle is determined, and if the number of times of use of the shared vehicle is less than or equal to the preset number of times, the shared vehicle is determined as the candidate search vehicle.

Further, the process of determining the position reliability of each candidate vehicle to be searched is expanded, that is, in step S101, the position reliability of each candidate vehicle to be searched is determined according to the historical data of each candidate vehicle to be searched and the trained discriminant model, and the method includes the following steps:

extracting characteristic information of each candidate vehicle from the historical data of each candidate vehicle; and inputting the characteristic information of each candidate searched vehicle into the trained discriminant model, and determining the position reliability of each candidate searched vehicle.

In specific implementation, for each candidate sought vehicle, when determining the location reliability of the candidate sought vehicle, feature information representing features of the candidate sought vehicle may be extracted from historical data of the candidate sought vehicle, and the feature information may represent the location accuracy of the candidate sought vehicle to a certain extent. The operation principle of the discrimination model is to determine the degree of similarity between each candidate sought vehicle and the accurately-positioned shared vehicle and the degree of similarity between the candidate sought vehicle and the inaccurately-positioned shared vehicle through the characteristic information of the candidate sought vehicle, and further determine the positioning accuracy of the candidate sought vehicle, that is, determine the position reliability of the candidate sought vehicle.

Further, the process of generating the trained discriminant model is explained, that is, the trained discriminant model is generated according to the following steps:

taking historical data of candidate searched vehicles with positioning errors smaller than or equal to preset errors as positive samples, and taking historical data of candidate searched vehicles with positioning errors larger than the preset errors as negative samples; and training the initial discrimination model according to the positive sample and the negative sample to generate a trained discrimination model.

In the specific implementation, before the discriminant model is trained, a large number of training samples need to be acquired, here, the historical data of the shared vehicle successfully found by real-time positioning within a period of time closest to the present time can be used as a positive sample, the historical data of the other shared vehicles can be used as negative samples, that is, the historical data of the candidate sought vehicle with the positioning error smaller than or equal to the preset error is used as a positive sample, the historical data of the candidate sought vehicle with the positioning error larger than the preset error is used as a negative sample, further, the initial discriminant model is trained through the positive sample and the negative sample to generate the trained discriminant model, and the credibility location of the candidate sought vehicle is determined through the discriminant model.

S102: and screening the vehicles to be searched from the candidate searched vehicles according to the position credibility of each candidate searched vehicle.

In the specific implementation, after the position confidence of each candidate searched vehicle is determined through the historical data and the discrimination model of each candidate searched vehicle, namely the difficulty degree of searching each candidate searched vehicle is determined, the vehicle to be searched can be directly screened out from a plurality of candidate searched vehicles through the size of the positioning confidence, namely the candidate searched vehicle which is relatively easy to find through the positioning information is screened out; the candidate searched vehicles with low position confidence degrees are removed firstly through the positioning confidence degrees, namely the candidate searched vehicles which are difficult to find through the positioning information are removed, and then the vehicles to be searched are screened out.

Further, after the position reliability of each candidate searched vehicle is determined, the priority of each candidate searched vehicle may be determined according to the position reliability, and then the vehicle to be searched is determined according to the priority, that is, in step S102, the vehicle to be searched is screened out from the plurality of candidate searched vehicles according to the position reliability of each candidate searched vehicle, including the following steps:

Determining the vehicle searching priority of each candidate searched vehicle according to the position credibility of each candidate searched vehicle; and determining the candidate searched vehicle with the vehicle searching priority greater than or equal to the preset priority as the vehicle to be searched.

In a specific implementation, the positioning confidence degrees with different sizes may be classified in advance according to the size of the positioning confidence degree, specifically, the candidate sought vehicles in one positioning confidence degree interval may be classified into one class, and in this way, the candidate sought vehicles corresponding to different positioning confidence degrees are classified into multiple classes, where the class may be a vehicle seeking priority. After the position confidence level of each candidate vehicle to be searched is determined, the vehicle searching priority corresponding to the position confidence level is determined, if the vehicle searching priority level of the candidate vehicle to be searched is greater than or equal to the preset priority level, the candidate vehicle to be searched can be determined as the vehicle to be searched, otherwise, the candidate vehicle to be searched is not taken as the vehicle to be searched next, namely, the vehicle which cannot be searched relatively is abandoned.

Here, in addition to the above-described manner of determining the vehicle to be searched by the vehicle searching priority, it may be determined whether each candidate searched vehicle is the vehicle to be searched directly according to the magnitude of the localization confidence of the candidate searched vehicle, specifically, a preset confidence threshold may be preset, and the candidate searched vehicle having the localization confidence greater than or equal to the preset confidence threshold may be determined as the vehicle to be searched.

S103: and performing density clustering on the vehicles to be searched according to the positioning positions and the positioning confidence degrees respectively corresponding to the vehicles to be searched, and determining a vehicle aggregation area.

In specific implementation, after a vehicle to be searched which is relatively easy to find is screened out from a plurality of candidate vehicles to be searched, for the determined vehicle to be searched, density clustering is performed on each vehicle to be searched by combining the positioning position and the positioning confidence of each vehicle to be searched, and then vehicle aggregation areas of the vehicles to be searched are determined, wherein the positioning position of each vehicle to be searched can be the current geographic position of the vehicle to be searched.

Here, a clustering model may be trained in advance, and a vehicle clustering area corresponding to each vehicle to be searched is determined by inputting the positioning position and the positioning reliability corresponding to each vehicle to be searched into the clustering model together, where the clustering model may be an unsupervised machine learning model.

S104: determining a vehicle finding path based on the vehicle gathering area.

In specific implementation, after the vehicle gathering areas of the vehicles to be searched are determined, the total vehicle searching path for searching the vehicles to be searched in the vehicle gathering areas can be determined based on the area positions of the vehicle gathering areas, wherein each vehicle gathering area contains a plurality of vehicles to be searched, so that the vehicles to be searched can be found back as many as possible in one vehicle searching process through the determined vehicle searching paths, and the vehicle searching efficiency can be improved.

In the embodiment of the application, the position confidence of each candidate vehicle can be determined through the acquired historical data of the candidate vehicles and the trained discriminant model, the vehicles to be searched can be screened out from the candidate vehicles according to the position confidence of each candidate vehicle, and further, density clustering can be performed on each vehicle to be searched according to the positioning position and the positioning confidence corresponding to each vehicle to be searched respectively, a vehicle gathering area can be determined, and further, a vehicle searching path can be determined based on the vehicle gathering area.

Fig. 2 is a flowchart of another shared vehicle searching method according to an embodiment of the present disclosure. As shown in fig. 2, the method for finding a shared vehicle provided in the embodiment of the present application includes the following steps:

s201: and acquiring historical data of a plurality of candidate searched vehicles, and determining the position reliability of each candidate searched vehicle according to the historical data of each candidate searched vehicle and the trained discrimination model.

S202: and screening the vehicles to be searched from the candidate searched vehicles according to the position credibility of each candidate searched vehicle.

S203: and according to the positioning position of each vehicle to be searched, performing position clustering on each vehicle to be searched to obtain a plurality of candidate gathering areas.

In the specific implementation, candidate sought vehicles with relatively high positioning confidence degrees are selected from the candidate sought vehicles, that is, candidate sought vehicles which are relatively easy to find through positioning positions are selected and determined as sought vehicles, furthermore, preliminary clustering is performed on each to-be-sought vehicle according to the positioning position of each to-be-sought vehicle to obtain a plurality of candidate gathering areas, wherein each candidate gathering area contains at least one to-be-sought vehicle, each candidate gathering area occupies an area in a preset range on the geographical position, and if one candidate area contains at least two to-be-sought vehicles, the distance between any two to-be-sought vehicles in the candidate gathering area is smaller than or equal to a preset distance.

S204: and aiming at each candidate aggregation area in the plurality of candidate aggregation areas, calculating the vehicle density of each candidate aggregation area according to the total number of the vehicles to be searched in each candidate aggregation area and the position reliability of each vehicle to be searched.

In the specific implementation, considering that the position reliability of each vehicle to be searched is different, that is, the positioning accuracy of each vehicle to be searched is different, so that the vehicles to be searched cannot be clustered completely depending on the positioning position, herein, two conditions of the positioning position and the positioning reliability are used together as density clustering for each vehicle to be searched, specifically, each vehicle to be searched is initially clustered through the positioning position to obtain a plurality of candidate clustering areas, and then, the candidate clustering areas are further screened through the vehicle density to determine a vehicle clustering area, wherein the vehicle density of each candidate clustering area is determined by the total number of the vehicles to be searched in the candidate clustering area and the position reliability of each vehicle to be searched in the candidate clustering area.

Here, the total number of the vehicles to be searched in each candidate aggregation area, that is, the total number of the vehicles to be searched belonging to the candidate aggregation area, may use the position reliability of the vehicles to be searched in the candidate aggregation area as a weight, and further, the vehicle density on each candidate aggregation area may be calculated according to the total number and the position reliability of each vehicle to be searched.

In one example, if the total number of the vehicles to be searched in the candidate aggregation area a is 100, where the position confidence degrees of 50 vehicles to be searched are all 90%, the position confidence degrees of 30 vehicles to be searched are all 80%, and the position confidence degrees of 20 vehicles to be searched are all 60%, the vehicle density is 50 × 90% +30 × 80% +20 × 60% ═ 81.

S205: and determining the candidate gathering area with the vehicle density being greater than or equal to the preset density as the vehicle gathering area.

In a specific embodiment, each vehicle to be searched is initially clustered through the positioning position to obtain a plurality of candidate clustering regions, and then the candidate clustering regions are further screened through vehicle density to determine vehicle aggregation regions.

Here, the candidate aggregation areas having a density of vehicles smaller than the preset density may be determined as vehicle scattered areas, where the number of vehicles to be searched included in the vehicle scattered areas is theoretically much smaller than the number of vehicles to be searched included in the vehicle aggregation areas.

S206: determining a vehicle finding path based on the vehicle gathering area.

The descriptions of steps S201, S202, and S206 may refer to the descriptions of steps S101, S102, and S104, and the same technical effect can be achieved, and therefore, no further explanation is provided here.

Further, the manner of determining the vehicle-seeking path may be determined according to the number of the areas of the vehicle aggregation area, specifically, the number of the areas of the determined vehicle aggregation area is counted first, here, a case that the number of the areas of the vehicle aggregation area is greater than or equal to a preset threshold is explained, that is, a first manner of determining the vehicle-seeking path is explained, and the step S206 of determining the vehicle-seeking path based on the vehicle aggregation area includes the following steps:

if the number of the areas is larger than or equal to a preset threshold value, determining a first path among the vehicle gathering areas according to the area positions of the vehicle gathering areas, and determining a second path among the vehicles to be searched in each vehicle gathering area according to the positioning positions of the vehicles to be searched in each vehicle gathering area; and determining the vehicle searching path according to the first path and the second path.

In the specific implementation, if the number of the areas of the vehicle gathering area is greater than or equal to the preset threshold value, which indicates that the vehicle gathering area with higher vehicle density is more, the vehicles to be searched in the vehicle gathering area can be directly searched, the scattered areas of the vehicles with lower vehicle density do not need to be considered, more vehicles to be searched can be found in one vehicle search, and the vehicle searching efficiency can be further improved by giving up the search for the vehicles to be searched in the scattered areas of the vehicles. Specifically, the area positions of the vehicle aggregation areas may be obtained first, then, a first path between the vehicle aggregation areas may be determined, and, for each vehicle aggregation area, a second path between the vehicles to be searched in the vehicle aggregation area may be determined according to the positioning positions of the vehicles to be searched in the vehicle aggregation area, further, a vehicle searching path may be determined according to the first path between the vehicle aggregation area and the second path between the vehicles to be searched in the vehicle aggregation area, where the first path and the second path are both optimal paths, and the optimal path refers to a path with the shortest distance or shortest time, so that the optimal paths between the vehicle aggregation areas are connected in series through the optimal first path and the optimal second path, and the optimal paths between the vehicles to be searched in each vehicle aggregation area are connected in series, to determine the optimal vehicle-seeking path.

Further, the manner of determining the vehicle-seeking path may be determined according to the number of the regions of the vehicle aggregation region, specifically, the number of the regions of the determined vehicle aggregation region is counted first, here, a case that the number of the regions of the vehicle aggregation region is smaller than a preset threshold is explained, that is, a second manner of determining the vehicle-seeking path is explained, and the step S206 determines the vehicle-seeking path based on the vehicle aggregation region includes the following steps:

if the number of the areas is smaller than the preset threshold value, determining the vehicle searching path according to the area position of each vehicle gathering area, the positioning position of each vehicle to be searched in each vehicle gathering area, the positioning position of each vehicle scattered area and the positioning position of each vehicle to be searched in each vehicle scattered area; the vehicle scattered area is a candidate gathering area with the vehicle density smaller than the preset density.

In specific implementation, if the number of the areas of the vehicle aggregation areas is smaller than the preset threshold, which indicates that the vehicle aggregation areas with higher vehicle density are fewer, the vehicle aggregation areas and the scattered areas of the vehicles need to be considered, so that more vehicles to be searched can be found in one vehicle search. Specifically, the area position of each vehicle gathering area, the positioning position of each vehicle to be searched in each vehicle gathering area, the positioning position of each vehicle scattered area, and the positioning position of each vehicle to be searched in each vehicle scattered area may be obtained first, and then the shortest path in each vehicle gathering area and the vehicle scattered area along the path are connected in series to determine the vehicle searching path.

Further, after the vehicle searching path is determined, it is further considered whether the capacity of the transportation capacity required by the vehicle to be searched in the carrier vehicle searching path exceeds the preset capacity of the carrier vehicle, and if so, multiple carrier vehicles need to be dispatched to perform vehicle searching, that is, after the vehicle searching path is determined based on the vehicle gathering area in step S206, the method further includes the following steps:

determining the capacity required for carrying the vehicles to be searched in the vehicle searching path according to the number of the vehicles to be searched in the vehicle searching path and the path length of the vehicle searching path; if the capacity is larger than the preset capacity, segmenting the vehicle-searching path according to the preset capacity and the capacity to obtain at least two segmentation paths; and generating a vehicle searching work order corresponding to each segmentation path according to each segmentation path.

In the specific implementation, after the vehicle searching path is determined, the capacity of the vehicles to be searched in the carrying vehicle searching path is further considered, and the vehicle searching worksheet is generated based on the capacity of the vehicles, specifically, the number of the vehicles to be searched in the vehicle searching path and the path length of the vehicle searching path are determined first, and further, the capacity of the vehicles to be searched in the carrying vehicle searching path is determined. Here, the number of carrier trucks to be dispatched, the number of persons to dispatch a vehicle, and the like can be determined by the capacity of capacity and the preset capacity.

Further, vehicle searching can be performed at preset time intervals, for example, after the vehicle is searched according to the vehicle searching path at this time, a new vehicle searching path is generated again after the preset time intervals, and the vehicle is searched according to the new vehicle searching path, so that the number of silent shared vehicles is reduced, and the utilization rate of the shared vehicles is improved.

Based on the same application concept, the embodiment of the present application further provides a shared vehicle searching device corresponding to the shared vehicle searching method provided by the embodiment, and as the principle of solving the problem of the device in the embodiment of the present application is similar to the shared vehicle searching method provided by the embodiment of the present application, the implementation of the device may refer to the implementation of the method, and repeated details are not repeated.

As shown in fig. 3 to 8, fig. 3 is a functional block diagram of a shared vehicle finding device 300 according to an embodiment of the present application; FIG. 4 illustrates a functional block diagram of the first determination module 310 of FIG. 3; fig. 5 shows a second functional block diagram of a shared vehicle searching apparatus 300 according to an embodiment of the present application; FIG. 6 illustrates a functional block diagram of the filter block 320 of FIG. 5; FIG. 7 illustrates a functional block diagram of the second determination module 330 of FIG. 5; fig. 8 shows a functional block diagram of the third determination module 340 in fig. 5.

As shown in fig. 3 and 5, the shared vehicle finding device 300 includes:

the first determining module 310 is configured to obtain historical data of a plurality of candidate sought vehicles, and determine a location reliability of each candidate sought vehicle according to the historical data of each candidate sought vehicle and a trained discrimination model;

a screening module 320, configured to screen out a vehicle to be searched from the multiple candidate searched vehicles according to the location reliability of each candidate searched vehicle determined by the first determining module 310;

the second determining module 330 is configured to perform density clustering on each vehicle to be searched according to the positioning position and the positioning confidence degree respectively corresponding to each vehicle to be searched, and determine a vehicle aggregation area;

A third determining module 340, configured to determine a vehicle finding path based on the vehicle gathering area determined by the second determining module 330.

In one possible implementation, as shown in fig. 3, the first determining module 310 is further configured to determine candidate vehicles according to the following steps:

counting the use times of each shared vehicle within a preset historical time;

In one possible implementation, as shown in fig. 4, the first determining module 310 includes:

an extracting unit 312, configured to extract feature information of each candidate sought vehicle from the history data of each candidate sought vehicle;

the first determining unit 314 is configured to input the feature information of each candidate vehicle to the trained discriminant model, and determine the location reliability of each candidate vehicle.

In one possible embodiment, as shown in fig. 5, the shared vehicle finding device 300 further includes a training module 350; the training module 350 is configured to generate a trained discriminant model according to the following steps:

In one possible implementation, as shown in fig. 6, the screening module 320 includes:

the second determining unit 322 is configured to determine the vehicle-searching priority of each candidate vehicle-searching according to the location reliability of each candidate vehicle-searching;

the third determining unit 324 is configured to determine a candidate vehicle to be searched, where the vehicle searching priority is greater than or equal to the preset priority.

In one possible implementation, as shown in fig. 7, the second determining module 330 includes:

the generating unit 332 is configured to perform position clustering on each vehicle to be searched according to the positioning position of each vehicle to be searched, so as to obtain a plurality of candidate aggregation areas;

a calculating unit 334, configured to calculate, for each candidate aggregation area in the plurality of candidate aggregation areas, a vehicle density of each candidate aggregation area according to the total number of vehicles to be searched in each candidate aggregation area and the location reliability of each vehicle to be searched;

a fourth determination unit 336 for determining a candidate aggregation area, in which the density of vehicles is greater than or equal to the preset density, as the vehicle aggregation area.

In one possible implementation, as shown in fig. 8, the third determining module 340 includes:

a counting unit 342 for counting the number of the determined vehicle aggregation areas;

a fifth determining unit 344, configured to determine, if the number of the areas is greater than or equal to a preset threshold, a first path between the vehicle aggregation areas according to the area positions of the vehicle aggregation areas, and determine, according to the location position of each vehicle to be searched in each vehicle aggregation area, a second path between the vehicles to be searched in each vehicle aggregation area;

a sixth determining unit 346, configured to determine the vehicle seeking path according to the first path and the second path.

In a possible implementation manner, as shown in fig. 8, the third determining module 340 is further configured to determine the vehicle-seeking path according to the following steps:

In one possible embodiment, as shown in fig. 5, the shared vehicle finding apparatus 300 further includes a generating module 360; the generating module 360 is configured to generate a vehicle searching work order according to the following steps:

In one possible embodiment, as shown in fig. 5, the shared vehicle finding device 300 further includes an executing module 370; the execution module 370 is configured to:

and performing vehicle searching once every preset time interval.

Based on the same application concept, referring to fig. 9, a schematic structural diagram of an electronic device 900 provided in an embodiment of the present application includes: a processor 910, a memory 920 and a bus 930, wherein the memory 920 stores machine-readable instructions executable by the processor 910, when the electronic device 900 is running, the processor 910 communicates with the memory 920 through the bus 930, and the machine-readable instructions are executed by the processor 910 to perform the steps of the method for finding a shared vehicle according to any of the above embodiments.

In particular, the machine readable instructions, when executed by the processor 910, may perform the following:

determining a vehicle finding path based on the vehicle gathering area.

Based on the same application concept, the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the shared vehicle searching method provided in the foregoing embodiments are executed.

Specifically, the storage medium can be a general storage medium, such as a mobile disk, a hard disk, and the like, when the computer program on the storage medium is run, the method for searching for the shared vehicle can be executed, and by determining the vehicle searching path, the vehicle to be searched can be found back as many as possible in one vehicle searching process, so that the vehicle searching efficiency can be improved.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for finding a shared vehicle, the method comprising:

determining a vehicle finding path based on the vehicle gathering area.

2. The method of finding as claimed in claim 1, further comprising determining candidate finding vehicles according to the steps of:

Counting the use times of each shared vehicle within a preset historical time;

3. The method of claim 1, wherein determining the location confidence for each candidate search vehicle based on the historical data for each candidate search vehicle and the trained discriminative model comprises:

4. The method of claim 1, further comprising generating a trained discriminant model according to the following steps:

5. The method according to claim 1, wherein the screening of the vehicles to be searched from the plurality of candidate searched vehicles according to the position credibility of each candidate searched vehicle comprises:

6. The finding method of claim 1, wherein the determining the vehicle clustering region by performing density clustering on each vehicle to be found according to the positioning position and the positioning confidence degree respectively corresponding to each vehicle to be found comprises:

7. The finding method according to claim 6, wherein the determining a vehicle finding path based on the vehicle gathering area includes:

counting the number of the determined regions of the vehicle gathering region;

8. The finding method according to claim 7, wherein the determining a vehicle finding path based on the vehicle gathering area includes:

9. The finding method according to claim 1, wherein after the determining of the vehicle finding path based on the vehicle gathering area, the finding method further comprises:

10. A shared vehicle search apparatus, comprising:

11. An electronic device, comprising: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating over the bus when the electronic device is operating, the machine-readable instructions being executable by the processor to perform the steps of the shared vehicle finding method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, performs the steps of the shared vehicle finding method according to any one of claims 1 to 9.