CN112929816A

CN112929816A - Vehicle abnormal behavior recognition method, device, medium, and computer program product

Info

Publication number: CN112929816A
Application number: CN202110138747.3A
Authority: CN
Inventors: 蔡民超; 戴桂婷
Original assignee: Beijing Didi Infinity Technology and Development Co Ltd
Current assignee: Beijing Didi Infinity Technology and Development Co Ltd
Priority date: 2021-02-01
Filing date: 2021-02-01
Publication date: 2021-06-08
Anticipated expiration: 2041-02-01
Also published as: CN112929816B

Abstract

The present disclosure provides a vehicle abnormal behavior recognition method, apparatus, medium, and computer program product, the method comprising: determining a plurality of historical order tracks corresponding to the suspected vehicle and position information of a plurality of track points in each historical order track based on historical track information of the suspected vehicle used by a suspected user indicated by historical order data in a historical time period; determining track coincidence information of the suspected vehicle according to the position information of the plurality of track points in each historical order track; determining whether the suspected vehicle has abnormal behavior used for specifically serving the suspected user based on the trajectory coincidence information. The method is characterized in that the vehicle serving the same user in a specific way is provided with the characteristic of fixed-point commuting, whether the vehicle has abnormal behaviors or not is identified by comparing the coincidence degree of a plurality of historical order tracks generated by the vehicle used by the same user, the identification principle is practical and reliable, and the accuracy of the identification result is ensured.

Description

Vehicle abnormal behavior recognition method, device, medium, and computer program product

Technical Field

The present disclosure relates to the field of vehicle operation management, and in particular, to a method, an apparatus, a medium, and a computer program product for identifying abnormal behavior of a vehicle.

Background

With the deep popularization of shared vehicle (such as shared bicycle) services, the use of shared vehicles for traveling has become a common traveling mode for people. However, some users may privately occupy a certain vehicle for a long time in an irregular manner, so that the vehicle is used for a specific service for the same user, which may seriously harm the use rights and interests of other users on one hand, and also not be beneficial to normal operation of shared vehicle business on the other hand.

For the above reasons, the prior art provides some identification methods for private vehicles and/or private users, however, the identification accuracy of the existing identification methods is low, and a better identification effect cannot be achieved.

Disclosure of Invention

In view of the above, embodiments of the present disclosure provide a method, an apparatus, a medium, and a computer program product for identifying abnormal behavior of a vehicle, which at least partially solve the problems in the prior art.

In a first aspect, an embodiment of the present disclosure provides a vehicle abnormal behavior identification method, where the method includes:

determining a plurality of historical order tracks corresponding to the suspected vehicle and position information of a plurality of track points in each historical order track based on historical track information of the suspected vehicle used by a suspected user indicated by historical order data in a historical time period;

determining track coincidence information of the suspected vehicle according to the position information of the plurality of track points in each historical order track;

determining whether the suspected vehicle has abnormal behavior used for specifically serving the suspected user based on the trajectory coincidence information.

In a possible implementation, the track coincidence information includes the number of coincident track points; the determining the track coincidence information of the suspected vehicle according to the position information of the plurality of track points in each historical order track comprises the following steps:

and determining the number of the overlapped track points in each historical order track pair based on the position information of the track points of each historical order track in each historical order track pair aiming at least one historical order track pair corresponding to the historical order tracks.

In a possible implementation manner, the determining the trajectory coincidence information of the suspected vehicle according to the position information of the plurality of trajectory points in each historical order trajectory includes:

for each historical order track, according to the position information of a plurality of track points in the historical order track, duplicate removal is carried out on the track points with the same position information, and the track points reserved in the historical order track are reordered;

and matching the plurality of historical order tracks, and determining the number of overlapped track points in each historical order track pair based on the position information of the plurality of track points reserved after the duplication in each historical order track pair is removed.

In one possible embodiment, the determining whether the suspected vehicle has abnormal behavior used for specifically serving the suspected user based on the trajectory coincidence information includes:

determining the number of target track pairs with high contact ratio in at least one historical order track pair based on the number of overlapped track points in each historical order track pair;

determining whether the suspected vehicle has abnormal behavior used for specifically servicing the suspected user based on the number of target track pairs.

In a possible implementation, the determining, based on the number of overlapping track points in each historical order track pair, the number of target track pairs with high overlap ratio in the at least one historical order track pair includes:

determining the historical order track pairs with the number of overlapped track points larger than a third preset threshold value as target track pairs with high overlap ratio, and determining the number of the target track pairs;

or calculating a second ratio of the number of the overlapped track points in each historical order track pair to the total number of the track points in the historical order track pair, determining the historical order track pair with the second ratio being greater than a fourth preset threshold as a target track pair with high coincidence, and determining the number of the target track pair.

In one possible embodiment, the determining whether the suspected vehicle has abnormal behavior used for specifically serving the suspected user based on the number of target track pairs includes:

determining whether the number of the target track pairs is greater than a fifth preset threshold, and if so, determining that the suspected vehicle has abnormal behaviors used for specifically serving the suspected user;

or calculating a third ratio of the number of the target track pairs to the total number of the historical order track pairs, determining whether the third ratio is greater than a sixth preset threshold, and if so, determining that the suspected vehicle has abnormal behaviors used for specifically serving the suspected user.

In a possible implementation manner, before the determining the plurality of historical order tracks corresponding to the suspected vehicle and the position information of the plurality of track points in each historical order track, the method further includes: and screening suspected vehicles suspected to be privately occupied and suspected users suspected to be privately occupied on the suspected vehicles based on historical order data in a historical time period.

In a possible implementation manner, the screening out suspected private vehicles and suspected private users of the suspected private vehicles based on historical order data in a historical time period includes:

determining historical order information corresponding to each user in at least one user using the vehicle and historical order information corresponding to each vehicle in at least one vehicle from the obtained historical order data in the historical time period;

and screening suspected private vehicles and suspected users suspected to be private to the suspected vehicles according to the historical order information corresponding to each user and the historical order information corresponding to each vehicle.

In a possible implementation manner, the screening out suspected private vehicles and suspected private users who are suspected to occupy the suspected private vehicles according to the historical order information corresponding to each user and the historical order information corresponding to each vehicle includes:

determining the total vehicle using times of each user and the vehicle using time of each vehicle based on the historical order information corresponding to each user, and determining the number of the users using the vehicle based on the historical order information corresponding to each vehicle;

determining a candidate vehicle suspected to be privately occupied and a candidate user suspected to be privately occupied on the candidate vehicle based on the total number of times of using the vehicle corresponding to each user and the number of users corresponding to each vehicle;

and determining whether the candidate vehicle comprises a vehicle which is used by the candidate user for the last time or not according to the vehicle using time, and if so, determining that the candidate vehicle is a suspected private vehicle and the candidate user is a suspected private user of the suspected private vehicle.

In a possible implementation manner, the determining a candidate vehicle suspected of being privately occupied and a candidate user suspected of privately occupying the candidate vehicle based on the total number of times of using the vehicle corresponding to each user and the number of users corresponding to each vehicle includes:

for each user, determining whether a first ratio of the total vehicle utilization number of the user to the number of vehicles used by the user is greater than a first preset threshold value, if so, determining the vehicle used by the user as a primary vehicle, and determining the user as a primary user suspected to privately occupy the primary vehicle;

and determining whether the number of the users corresponding to the initially selected vehicle is smaller than a second preset threshold value or not for each initially selected vehicle corresponding to the initially selected user, if so, determining the initially selected vehicle as a candidate vehicle, and determining the initially selected user as a candidate user suspected to privately occupy the candidate vehicle.

In a second aspect, an embodiment of the present disclosure provides a vehicle abnormal behavior recognition apparatus, including:

the track data acquisition module is used for determining a plurality of historical order tracks corresponding to the suspected vehicle and position information of a plurality of track points in each historical order track based on historical track information of the suspected vehicle used by a suspected user indicated by historical order data in a historical time period;

the coincidence information determining module is used for determining the track coincidence information of the suspected vehicle according to the position information of a plurality of track points in each historical order track;

and the abnormal behavior determination module is used for determining whether the suspected vehicle has abnormal behavior used for specifically serving the suspected user or not based on the track coincidence information.

In a possible implementation, the track coincidence information includes the number of coincident track points; the coincidence information determining module is specifically configured to, when determining the trajectory coincidence information of the suspected vehicle according to the position information of the plurality of track points in each historical order trajectory:

In a possible implementation manner, when the coincidence information determining module is configured to determine the trajectory coincidence information of the suspected vehicle according to the position information of the plurality of trajectory points in each historical order trajectory, the coincidence information determining module is specifically configured to:

In a possible implementation, the abnormal behavior determination module, when configured to determine whether there is an abnormal behavior of the suspected vehicle used for specifically serving the suspected user based on the trajectory coincidence information, is specifically configured to:

In a possible implementation manner, the abnormal behavior determination module, when configured to determine, based on the number of overlapping track points in each historical order track pair, the number of target track pairs with high overlap ratio in the at least one historical order track pair, is specifically configured to:

In a possible implementation, the abnormal behavior determination module, when configured to determine whether there is abnormal behavior of the suspected vehicle used to specifically serve the suspected user based on the number of target track pairs, is specifically configured to:

In a possible implementation manner, the vehicle abnormal behavior identification device further includes a suspected object screening module, and the suspected object screening module is configured to: and screening suspected vehicles suspected to be privately occupied and suspected users suspected to be privately occupied on the suspected vehicles based on historical order data in a historical time period.

In a possible implementation manner, when the suspected object screening module is configured to screen out a suspected private vehicle and a suspected private user of the suspected private vehicle based on historical order data in a historical time period, the suspected object screening module is specifically configured to:

In a possible implementation manner, when the suspected object screening module is configured to screen out suspected private suspected vehicles and suspected users suspected to be private in the suspected vehicles according to the historical order information corresponding to each user and the historical order information corresponding to each vehicle, the suspected object screening module is specifically configured to:

In a possible implementation manner, when the suspected object screening module is configured to determine a candidate vehicle suspected to be privately occupied and a candidate user suspected to be privately occupied on the candidate vehicle based on the total number of vehicle uses corresponding to each user and the number of users corresponding to each vehicle, the suspected object screening module is specifically configured to:

In a third aspect, an embodiment of the present disclosure provides an electronic device, which includes a processor, a memory, and a bus; the memory stores machine-readable instructions executable by the processor, the processor and the memory communicate via a bus when the electronic device is running, and the machine-readable instructions are executed by the processor to perform the steps of the first aspect, or any one of the possible vehicle abnormal behavior recognition methods of the first aspect.

In a fourth aspect, the disclosed embodiments provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, performs the steps of the first aspect described above, or any one of the possible vehicle abnormal behavior identification methods in the first aspect.

In a fifth aspect, the disclosed embodiments provide a computer program product comprising computer instructions that, when executed by a processor, implement the steps of the first aspect described above, or any one of the possible vehicle abnormal behavior identification methods of the first aspect.

According to the method, the device, the medium and the computer program product for identifying the abnormal behaviors of the vehicle, which are provided by the embodiment of the disclosure, the characteristic that the vehicle which is specially served for the same user has fixed-point commuting is taken as a basis, whether the abnormal behaviors exist in the vehicle is identified by comparing the coincidence degree of a plurality of historical order tracks generated by the vehicle used by the same user, the identification principle is practical and reliable, and the correctness of the identification result is ensured; moreover, the coincidence degree of the historical order track is determined by the fine-grained information of the track point, so that the efficiency and the accuracy of determining the track coincidence information can be ensured, and the accuracy of the identification result is greatly improved.

In order to make the aforementioned objects, features and advantages of the present disclosure 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 disclosure, the drawings required for use in the embodiments will be briefly described below, and the drawings herein incorporated in and forming a part of the specification illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the technical solutions of the present disclosure. It is appreciated that the following drawings depict only certain embodiments of the disclosure and are therefore not to be considered limiting of its scope, for those skilled in the art will be able to derive additional related drawings therefrom without the benefit of the inventive faculty.

Fig. 1 is a flowchart of a method for identifying abnormal behavior of a vehicle according to an embodiment of the present disclosure;

fig. 2 is a flowchart illustrating a method for screening suspected vehicles and suspected users according to an embodiment of the present disclosure;

fig. 3 is a schematic diagram of a vehicle abnormal behavior recognition device according to an embodiment of the present disclosure;

fig. 4 is a second schematic diagram of a vehicle abnormal behavior recognition device according to an embodiment of the present disclosure;

fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions of the embodiments of the present disclosure will be described clearly and completely with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, not all of the embodiments. The components of the embodiments of the present disclosure, 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 disclosure, presented in the figures, is not intended to limit the scope of the claimed disclosure, but is merely representative of selected embodiments of the disclosure. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the disclosure without making creative efforts, shall fall within the protection scope of the disclosure.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.

The term "and/or" herein merely describes an associative relationship, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B, C, and may mean including any one or more elements selected from the group consisting of A, B and C.

Research shows that with the deep popularization of shared vehicle (such as shared bicycle) services, the use of shared vehicles for traveling has become a common traveling mode for people. However, some users may privately occupy a certain vehicle for a long time in an irregular manner, so that the vehicle is used for a specific service for the same user, which may seriously harm the use rights and interests of other users on one hand, and also not be beneficial to normal operation of shared vehicle business on the other hand. For the above reasons, the prior art provides some identification methods for private vehicles and/or private users, however, the identification accuracy of the existing identification methods is low, and a better identification effect cannot be achieved.

The inventor of the application finds that vehicles serving the same user have fixed-point commuting, namely when the user occupies one vehicle for a long time, the paths of the vehicles used by the user each time have high probability and have similarity. Based on the research, the embodiment of the disclosure provides a vehicle abnormal behavior identification method, which identifies whether the vehicle has abnormal behavior by comparing the coincidence degree of a plurality of historical order tracks generated by the vehicle used by the same user based on the characteristic that the vehicle serving the same user has fixed-point commuting, wherein the identification principle is reliable and the accuracy of the identification result is ensured; moreover, the coincidence degree of the historical order track is determined by the fine-grained information of the track point, so that the efficiency and the accuracy of determining the track coincidence information can be ensured, and the accuracy of the identification result is greatly improved.

The above-mentioned drawbacks are the results of the inventor after practical and careful study, and therefore, the discovery process of the above-mentioned problems and the solutions proposed by the present disclosure to the above-mentioned problems should be the contribution of the inventor in the process of the present disclosure.

To facilitate understanding of the present embodiment, first, a vehicle abnormal behavior recognition method disclosed in the embodiments of the present disclosure is described in detail, where an execution subject of the vehicle abnormal behavior recognition method provided in the embodiments of the present disclosure is generally a computer device with certain computing capability, and the computer device includes, for example: a terminal device, which may be a User Equipment (UE), a mobile device, a User terminal device, a cellular phone, a cordless phone, a Personal Digital Assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, or a server or other processing device. In some possible implementations, the vehicle abnormal behavior recognition method may be implemented by a processor calling computer readable instructions stored in a memory.

The following describes a vehicle abnormal behavior recognition method provided by the embodiment of the present disclosure, taking an execution subject as a terminal device as an example. In the embodiment of the application, when a user owns a vehicle, it means that the owned vehicle has an abnormal behavior used for a specific service for the same user.

Referring to fig. 1, a flowchart of a vehicle abnormal behavior identification method provided in an embodiment of the present disclosure is shown, where the method includes steps S110 to S130, where:

s110: based on historical track information of suspected vehicles used by suspected users indicated by historical order data in historical time periods, a plurality of historical order tracks corresponding to the suspected vehicles and position information of a plurality of track points in each historical order track are determined.

The historical time period may be any time period before the current time, the starting time and the ending time of the historical time period may be determined according to actual needs, and for example, 7 days before the current time may be used as the historical time period.

It can be understood that the vehicle abnormal behavior identification method provided by the embodiment of the disclosure can be applied to the field of vehicle rental, such as the field of shared vehicles. The vehicle used for vehicle rental can be, but is not limited to, a manual bicycle, an electric bicycle, a fuel vehicle, an electric vehicle, a tricycle, a scooter, a unicycle, and the like. When the user acts on the vehicle for rental (for example, the user unlocks and uses the shared bicycle), an order for the rental action of the user can be generated, and the order comprises related data generated in the process of renting the vehicle by the user.

As described above, when a user has a rental behavior for a vehicle, an order for the rental behavior of the user may be generated, and the history track corresponding to each order in the history time period is defined as the history order track, and the data of the driving track in the history time period is defined as the history track information.

It should be noted that, in step S110, the suspected user represents a user who is determined to be likely to occupy a vehicle, and the suspected vehicle represents a vehicle that has been used by the suspected user and is determined to be likely to have abnormal behavior used for specifically servicing the suspected user. The suspected user in this step may be any user in the historical order data, and the suspected vehicle may be any vehicle used by the suspected user in the historical order data. Alternatively, before this step S110, a suspected private vehicle and a suspected user of the suspected private vehicle may be screened out based on historical order data in a historical time period, and then step S110 may be executed for the screened suspected user and suspected vehicle. Here, the specific process of screening suspected users and suspected vehicles will be specifically described in the following.

After the suspected user and the suspected vehicle are determined, historical track information generated by the suspected user using the suspected vehicle can be determined in the historical order data. It is understood that the historical track information generated by the suspected user using the suspected vehicle may include data of a plurality of historical tracks generated by the suspected user using the suspected vehicle a plurality of times within a historical period of time.

Specifically, the user may periodically upload heartbeat messages while using the vehicle, e.g., the vehicle may upload heartbeat messages to the server every 3 seconds. The heartbeat messages comprise position information of the vehicle, the position information in one heartbeat message is used as the position information of one track point of the vehicle, and it can be understood that the position information of a plurality of track points of the driving track of the vehicle can be obtained along with the lapse of time. After the suspected user and the suspected vehicle are determined, historical track information generated by the suspected user using the suspected vehicle can be determined in the historical order data, and a plurality of historical order tracks corresponding to the suspected vehicle and position information of a plurality of track points in each historical order track can be determined from the historical track information.

S120: and determining track coincidence information of the suspected vehicle according to the position information of the plurality of track points in each historical order track.

As can be seen from the foregoing, the historical track information generated by the suspected user using the suspected vehicle may include data of a plurality of historical tracks generated by the suspected user using the suspected vehicle a plurality of times in a historical time period, and each historical order track includes location information of a plurality of track points. In this step, the trajectory coincidence information of the suspected vehicle may be determined by comparing, calculating, analyzing, or the like the position information of the plurality of trajectory points in each of the historical order trajectories, for example, detecting the degree of coincidence of the positions of the trajectory points of the two historical order trajectories, or the like.

In a possible implementation manner, the track overlapping information of the suspected vehicle may include the number of overlapping track points, and when determining the track overlapping information of the suspected vehicle, the number of overlapping track points in each history order track pair may be determined based on the position information of the plurality of track points of each history order track in each history order track pair for at least one history order track pair corresponding to the plurality of history order track pairs. The number of the coincident track points is used as track coincidence information, the coincidence degree of the historical order track is determined by the information of the fine granularity of the track points, and the efficiency and the accuracy of determining the track coincidence information can be guaranteed.

In embodiments of the present disclosure, the plurality of historical order traces may form at least one historical order trace pair, each historical order trace pair comprising any two of the plurality of historical order trace pairs. Alternatively, taking the user U1 as an example, assuming that the user U1 used the vehicle C1, the vehicle C2, the vehicle C3 and the vehicle C4 in a historical period of time, the vehicle C1 may be a suspected vehicle, and the user U1 is a suspected user who is suspected to be privy to the vehicle C1. Assuming that the user U1 generates 4 historical order tracks using the vehicle C1, the 4 historical order tracks may be paired two by two, and up to 6 historical order track pairs may be formed, and in the disclosed embodiment, the number of coincident track points in each historical order track pair may be determined for at least one of the 6 historical order track pairs.

It can be understood that in the same historical order track, there may be track points with the same location information. For example, when the position of the vehicle does not change within a period of time during the use of the vehicle by the user, the position information included in the heartbeat messages uploaded by the vehicle for multiple times within the period of time is the same, which may cause track points with the same position information to exist in the same historical order track. In order to ensure the accuracy of the number of the determined coincident track points in the historical order track pairs, the track points with the same position information in each historical order track can be deduplicated, and then the number of the coincident track points in at least one historical order track pair is determined.

Optionally, for each historical order track, according to the position information of the plurality of track points in the historical order track, duplicate removal can be performed on the track points with the same position information, and the track points reserved in the historical order track can be reordered; and matching the plurality of historical order tracks, and determining the number of overlapped track points in each historical order track pair based on the position information of the plurality of track points reserved after the duplication of each historical order track pair is removed.

It should be noted that the overlapped track points in the historical order track pair refer to track points with the same or similar positions in the two historical order tracks of the historical order track pair. For example, the historical order track pair includes a first historical order track and a second historical order track, the position of the 1 st track point in the first historical order track is the same as the position of the 1 st track point in the second historical order track, or the position error between the 1 st track point in the first historical order track and the 1 st track point in the second historical order track is smaller than a preset value, and then the 1 st track point in the first historical order track and the 1 st track point in the second historical order track can be determined to be the overlapped track point.

In the disclosed embodiment, the trajectory coincidence information of the suspected vehicle may be output based on the route repeat identification model. Specifically, data of a plurality of historical order tracks corresponding to the suspected vehicle is input to a route repeat identification model trained in advance, and track overlapping information of the suspected vehicle is output by using the route repeat identification model. The route repeated identification model can be based on a route repeated identification model of a corresponding space-time trajectory clustering algorithm, and the space-time trajectory clustering algorithm can be ST-DBSCAN.

Specifically, the position information of the plurality of track points of each historical order track may be input to a route repeated recognition model trained in advance, and the form of the position information of the plurality of track points of the historical order track may be: { (lat)₁,lon₁,n₁),(lat₂,lon₂,n₂),(lat_n,lon_n,n_n)}。

Each data set respectively represents a certain track point in the historical order track, and the latitude and longitude of the track point. To (lat)₁,lon₁,n₁) For example, n₁Indicating the 1 st track point, lat, in the historical order track₁Indicates the latitude, lon, of the 1 st trace point₁Representing the longitude of the 1 st track point.

It can be understood that before the position information of a plurality of track points of each historical order track is input into the route repeated recognition model trained in advance, the track points with the same position information in the historical order track can be deduplicated, and the track points reserved in the historical order track can be reordered. And then, inputting the position information of a plurality of track points reserved after the duplication removal in the historical order track pair into a route repeated recognition model trained in advance.

The route repeat identification model can output a point set of coincident track points for each historical order track pair, and the number of coincident track points included in the point set. For example, the point set of a certain output historical order track to the repeated track point is N ═ N₁,n₂,n₃…n_mAnd (5) the number of the overlapped track points in the point set N is m.

It can be understood that in order to improve the accuracy of the number of the coincident track points in the historical order track pairs output by the route repeated identification model, the route repeated identification model can be optimized. Taking the route repeated identification model based on the corresponding space-time trajectory clustering algorithm as an example, the space-time trajectory clustering algorithm involves multiple parameters in the calculation process, such as an eps1 parameter, an eps2 parameter and a min _ samples parameter in the ST-DBSCAN algorithm, wherein the eps1 parameter, the eps2 parameter and the min _ samples parameter respectively represent the space density threshold, the time threshold and the data point requirements of the high-density points of the cluster. The accuracy of the number of the coincident track points in the historical order track pair output by the route repeated identification model can be improved by adjusting the three parameters.

For example, in the training phase of the model, after the repeated route identification model can output the point set of the coincident track points of the historical order track pair, the point set can be verified by a method of checking heartbeats through a map. Specifically, the spatial positions of the coincident track points in the point set can be checked to be in the path track corresponding to the corresponding order, and whether the positions of partial track points of two historical order tracks in the historical order track pair are the same due to the fact that the heartbeat message uploaded by the vehicle is abnormal can be verified.

If the verification process indicates that the accuracy of the number of the coincident track points in the historical order track pair output by the repeated route identification model meets the expectation, the model does not need to be further optimized, and if the accuracy is low, the model can be optimized by adjusting relevant parameters of the algorithm, for example, at least one parameter among the eps1 parameter, the eps2 parameter and the min _ samples parameter can be adjusted.

Those skilled in the art can understand that factors such as weather conditions, vehicle using time periods and traffic conditions can also be used as the basis for optimizing the model, and based on the factors, the model is optimized by adjusting relevant parameters of the algorithm. For example, for rainy weather or traffic peak conditions, the eps1 parameter, the eps2 parameter, and the min samples parameter may be used. It is understood that a person skilled in the art can select an appropriate way to train and optimize the route repetitive recognition model according to actual conditions and expected effects, and the training and optimization process for the model is not further described here.

In step S120, continuing with the example of the user U1 and the vehicle C1, the user U1 forms 6 historical order track pairs using the 4 historical order tracks generated by the suspected vehicle, and determines the number of overlapping track points in the 6 historical order track pairs to be 5, 2, 3, 6, and 8, respectively, according to the position information of the track points of each historical order track pair in the 6 historical order track pairs.

S130: it is determined whether there is abnormal behavior of the suspected vehicle used for the particular service suspected user based on the trajectory coincidence information.

As described above, the track coincidence information includes the number of coincident track points, and therefore, it can be determined whether there is an abnormal behavior of the suspected vehicle used for the specific service suspected user according to whether the number of coincident track points satisfies a preset condition. In one possible implementation, the number of target track pairs with high contact ratio in at least one historical order track pair can be determined based on the number of overlapped track points in each historical order track pair; it is determined whether there is abnormal behavior of the suspected vehicle used for the particular service suspected user based on the number of target track pairs.

Alternatively, whether the historical order track pairs are target track pairs with high coincidence degree can be determined by determining whether the number of coincident track points in each historical order track pair meets a preset number condition, so that the number of the target track pairs with high coincidence degree can be determined. Specifically, the number of target track pairs with high coincidence may be determined by either:

mode a 1: and determining the historical order track pairs with the number of the overlapped track points larger than a third preset threshold value as target track pairs with high overlap ratio, and determining the number of the target track pairs.

Continuing with the example of user U1 and vehicle C1, the number of coincident track points in the 6 historical order track pairs of vehicle C1 may be 5, 2, 3, 6, 8, respectively. Assuming that the third preset threshold is 4, determining the historical order track pairs with the number of overlapped track points larger than 4 as target track pairs with high overlap ratio, thereby determining the number of the target track pairs as 4.

Mode a 2: and calculating a second ratio of the number of the overlapped track points in each historical order track pair to the total number of the track points in the historical order track pair, determining the historical order track pair with the second ratio being greater than a fourth preset threshold as a target track pair with high overlap ratio, and determining the number of the target track pairs.

Continuing with the example of user U1 and vehicle C1, the number of coincident track points in the 6 historical order track pairs of vehicle C1 may be 5, 2, 3, 6, 8, respectively. Taking the 1 st historical order track pair as an example, the number of the overlapped track points in the 1 st historical order track is 5, assuming that the total number of the track points in the historical order track pair is 25, and the fourth preset threshold value is 0.15.

And dividing the number of the overlapped track points in the 1 st historical order track pair by the total number of the track points in the 1 st historical order track pair to obtain a second ratio of 0.2, so that the target track pair with high coincidence degree with the 1 st historical order track pair can be determined. In the same manner, it can be determined whether other historical order track pairs are target track pairs with high contact ratio, so as to determine the number of the target track pairs.

Alternatively, it may be determined whether there is an abnormal behavior of the suspected vehicle used for a specific service suspected user by determining whether the number of target track pairs satisfies a preset number condition. Specifically, whether the suspected vehicle has abnormal behavior used for a specific service suspected user may be determined by any one of the following ways:

mode b 1: and determining whether the number of the target track pairs is greater than a fifth preset threshold, and if so, determining that the suspected vehicle has abnormal behaviors used for the specific service suspected user.

Continuing with the example of user U1 and vehicle C1, assuming that the fifth preset threshold is 3 and the number of target track pairs in the 6 historical order track pairs of vehicle C1 is 4, it may be determined that suspected vehicle C1 has abnormal behavior that is used to service the suspected user U1.

Mode b 2: and calculating a third ratio of the number of the target track pairs to the total number of the historical order track pairs, determining whether the third ratio is greater than a sixth preset threshold, and if so, determining that the suspected vehicle has abnormal behaviors used for specific service suspected users.

Continuing with the example of user U1 and vehicle C1, assume that the sixth preset threshold is 0.5 and the number of target track pairs in the 6 historical order track pairs of vehicle C1 is 4. Dividing the number 4 of target track pairs for vehicle C1 by the total number 6 of historical order tracks for vehicle C1 by a third ratio of approximately 0.66, it may be determined that suspected vehicle C1 is behaving abnormally for the particular service suspected user U1.

After the suspected vehicle is determined based on the number of vehicle uses of the user, the vehicle use time and the number of the users of the vehicle, whether the suspected vehicle is really occupied by the user or not is accurately identified according to the driving track of the suspected vehicle, and the accuracy and the reliability of a final identification result are ensured.

As described above, before this step S110, a suspected private vehicle and a suspected user of the suspected private vehicle may be screened out based on the historical order data in the historical time period, and then step S110 may be executed for the screened suspected user and suspected vehicle. The following describes a specific process for screening suspected users and vehicles.

As mentioned above, the historical time period may be any time period before the current time, and the starting time and the ending time of the historical time period may be determined according to actual needs, for example, 7 days before the current time may be used as the historical time period. The historical order data may include data related to orders in the historical time period, and in this step, suspected private vehicles and suspected users suspected to be private vehicles are screened out based on the data related to the orders.

In a possible implementation manner, historical order information corresponding to each user in at least one user using the vehicle and historical order information corresponding to each vehicle in at least one vehicle can be determined from the acquired historical order data in the historical time period; and screening suspected private vehicles and suspected users of the suspected private vehicles according to the historical order information corresponding to each user and the historical order information corresponding to each vehicle.

In the disclosed embodiment, the historical order data may be used to extract and/or count relevant data needed for use, for example, for a single user and a single vehicle. Specifically, at least one user who has used the vehicle may be determined from the historical order data, and data related to the user may be extracted and/or counted from the historical order data, with any user as an object, and the related data may be used as the historical order information corresponding to the user. And determining at least one used vehicle from the historical order data, taking any vehicle as an object, extracting and/or counting data related to the vehicle from the historical order data, and taking the related data as the historical order information corresponding to the vehicle. And then screening suspected vehicles suspected to be privately occupied and suspected users suspected to be privately occupied from the users and the vehicles contained in the historical order data according to the data related to each user and the data related to each vehicle. According to the method, the suspected vehicle and the suspected user are screened by using the historical order information corresponding to the user and the vehicle respectively, on one hand, the user and the vehicle can be prevented from being omitted to a greater extent, and on the other hand, the reliability and the accuracy of the screening result are also ensured.

Part of the historical order data may store related order data in the form of an order base table, and in particular, order data generated by a user using a vehicle may be recorded in the order base table, and the order data may include at least one of the following information: the order ID, the user ID, the vehicle ID, a starting point location of vehicle travel, an ending point location of vehicle travel, an order travel start time, and an order travel end time, wherein the starting point location and the ending point location may be represented by corresponding latitude and longitude.

In the embodiment of the present disclosure, historical order information corresponding to at least one user using a vehicle and each user, and historical order information corresponding to at least one vehicle and each vehicle may be determined based on the data stored in the order basis table.

Based on the historical order information corresponding to each user, at least one of the number of times that the user uses the vehicle for each used vehicle, the total number of times that the user uses the vehicle, the time that the user uses the vehicle for each used vehicle, the time period that the user uses the vehicle for each used vehicle, and the total time period that the user uses the vehicle can be determined, and of course, other data related to the user can be determined based on the historical order information, and are not listed here.

At least one of the number of users who used the vehicle and the total length of time the vehicle was used can be determined based on the historical order information corresponding to each vehicle, and of course, other data related to the vehicle can be determined based on the historical order information, which is not listed here.

In a possible implementation manner, suspected private vehicles and suspected users suspected to be private vehicles can be screened out according to at least one of the number of times of using the vehicles by the users for each used vehicle, the number of users corresponding to each vehicle and the time of using the vehicles by the users for each used vehicle. For example, the vehicles used by the user are sorted based on the number of vehicle uses of each used vehicle, and the vehicle with the number of vehicle uses arranged at the top N is determined as the primary vehicle, wherein N is a positive integer; and determining whether the number of users corresponding to each initially selected vehicle is greater than a preset value (such as 3.5). And determining the primarily selected vehicles with the corresponding number of users larger than a preset value as suspected private vehicles, and determining the users as suspected users suspected to be private vehicles.

In a possible implementation manner, suspected private vehicles and suspected users of suspected private vehicles can be screened out according to the vehicle using time length of each used vehicle, the total vehicle using time length of the user and the number of users corresponding to each vehicle.

For example, it may be determined whether the vehicle-used time of each vehicle used by the user exceeds a preset time (e.g., 10 hours) for any user, and the vehicle with the vehicle-used time exceeding the preset time is determined as the initially selected vehicle; and then determining whether the number of users corresponding to each primary vehicle is greater than a preset value (for example, 3.5), determining the primary vehicle with the corresponding number of users greater than the preset value as a suspected private vehicle, and determining the user as a suspected user suspected to be private to the suspected private vehicle.

In a possible implementation manner, suspected private vehicles and suspected users of suspected private vehicles can be screened out according to the vehicle using time length of each used vehicle, the total vehicle using time length of the user and the total vehicle using time length of each vehicle.

For example, it may be determined whether the vehicle-used time of each vehicle used by the user exceeds a preset time (e.g., 10 hours) for any user, and the vehicle with the vehicle-used time exceeding the preset time is determined as the initially selected vehicle; for each initially selected vehicle, determining the ratio of the vehicle using time length of the initially selected vehicle corresponding to the user to the total vehicle using time length of the initially selected vehicle, determining the initially selected vehicle with the ratio being greater than a preset ratio (such as 0.9) as a suspected private vehicle, and determining the user as a suspected private user of the suspected private vehicle.

In a possible implementation manner, suspected private vehicles and suspected private users of suspected private vehicles can be screened out according to the total number of times of using the vehicles corresponding to each user, the time of using each vehicle by each user and the number of users corresponding to each vehicle. Referring to fig. 2, a flowchart for screening suspected vehicles and suspected users provided in the embodiment of the present disclosure includes steps S1101 to S1103, where:

s1101: determining the total vehicle using times of each user and the vehicle using time of each vehicle based on the historical order information corresponding to each user; and determining the number of users who used the vehicle based on the historical order information corresponding to each vehicle pair.

Alternatively, taking the user U1 as an example, assuming that the user U1 used the vehicle C1, the vehicle C2, the vehicle C3 and the vehicle C4 in a historical period of time, the historical order information corresponding to the user U1 may include order information corresponding to the user U1 using the vehicle C1, the vehicle C2, the vehicle C3 and the vehicle C4. In this historical order information, the total number of times the user U1 used the vehicle for vehicles C1 through C4, and the time of use of the user U1 for each of the vehicles C1 through C4 may be determined.

It should be noted that the vehicle-use time determined in this step includes the vehicle-use time in the order generated by each use of the vehicle by the user U1. It is understood that the number of usage times of the user U1 for each of the vehicles C1 through C4 is the same as the total usage times of the user U1 for the vehicles C1 through C4, and the usage times may be order driving start time or order driving end time.

Taking the vehicle C1 as an example, assuming that the vehicle C1 was used by the users U1 to U6 in the historical time period, the historical order information corresponding to the user U1 may include order information corresponding to the vehicle C1 used by each of the users U1 to U6, and in the historical order information, the number of users who used the vehicle may be determined, and it is understood that the number of users of the vehicle C1 in the historical time period is 6 in the embodiment of the present disclosure.

S1102: and determining a candidate vehicle suspected to be privately occupied and a candidate user suspected to be privately occupied on the candidate vehicle based on the total number of times of using the vehicle corresponding to each user and the number of users corresponding to each vehicle.

In one possible implementation, it may be determined, for each user, whether a first ratio of the total number of vehicle uses of the user to the number of vehicles used by the user is greater than a first preset threshold, and if the first ratio is greater than the first preset threshold, the vehicle used by the user is determined as a primary vehicle, and the user is determined as a primary user suspected to be privy to the primary vehicle. Alternatively, if the first ratio is not greater than the first preset threshold, it may be determined that the user is not privy to the vehicle that the user uses.

After the primary selected vehicle and the primary selected users suspected to be privately occupying the primary selected vehicle are determined, whether the number of the users corresponding to the primary selected vehicle is smaller than a second preset threshold or not can be determined for each primary selected vehicle corresponding to the primary selected user, if the number of the users is smaller than the second preset threshold, the primary selected vehicle is determined as a candidate vehicle, and the primary selected user is determined as a candidate user suspected to be privately occupying the candidate vehicle. Alternatively, if the number of users is not less than the second preset threshold, it may be determined that the user does not privy the vehicle used by the user.

Continuing with the example of user U1, assume that the total number of uses by user U1 for vehicles C1 through C4 is 20, a first preset threshold of 2. Since the user U1 used the vehicle C1, the vehicle C2, the vehicle C3, and the vehicle C4 in the history period, the number of vehicles used by the user was 4. The total number of vehicle uses 20 is divided by the number of vehicles 4 to obtain a first ratio of 5, and since the first ratio 5 is greater than a first preset threshold 2, the vehicles C1 to C4 used by the user U1 are determined as primary vehicles, and the user U1 is determined as a primary user suspected to be privately occupying the primary vehicles.

After the vehicles C1 through C4 are determined as primary vehicles and the user U1 is determined as a primary user suspected to be privately occupying the primary vehicle, it may be determined, for each of the vehicles C1 through C4, whether the number of users corresponding to the vehicle is less than a second preset threshold, and if the number of users is less than the second preset threshold, the primary vehicle is determined as a candidate vehicle. Assuming that the second preset threshold is 3.5, the number of users corresponding to the vehicle C1 is 6, the number of users corresponding to the vehicle C2 is 4, the number of users corresponding to the vehicle C3 is 1, and the number of users corresponding to the vehicle C4 is 1, the vehicle C1 and the vehicle C2 are determined as candidate vehicles, and the user U1 is determined as a candidate user suspected of occupying the candidate vehicle.

S1103: and determining whether the candidate vehicle comprises a vehicle which is used by the candidate user for the last time or not according to the vehicle using time, and if so, determining that the candidate vehicle is a suspected private vehicle and the candidate user is a suspected private vehicle.

It is understood that the vehicle used by the user last time can be determined according to the vehicle using time of each vehicle used by the candidate user, so as to determine whether the candidate vehicles comprise the vehicle used last time; if the candidate vehicles comprise the vehicle which is used for the last time, determining all the candidate vehicles suspected to be privately occupied by the candidate user as suspected vehicles, and determining the candidate user as a suspected user suspected to be privately occupied by the suspected vehicle; or, if the candidate vehicle includes the vehicle that has been used last time, determining the vehicle that has been used last time as the suspected vehicle. Alternatively, if the candidate vehicle does not include the most recently used vehicle, it may be determined that the user is not privy to the vehicle that the user has used.

Continuing with the example of user U1, in step S1102, vehicle C1 and vehicle C2 are determined as candidate vehicles, and user U1 is determined as a candidate user suspected of privately occupying the candidate vehicle. From the time of use of the user U1 for each of the vehicles C1-C4, it may be determined that vehicle C1 is the vehicle most recently used by the U1 user, and it may be determined that the candidate vehicles suspected of being privately owned by user U1 (i.e., vehicle C1 and vehicle C2) include the vehicle most recently used by the U1 user. Thus, vehicle C1 and vehicle C2 may both be determined to be suspect vehicles (or, alternatively, vehicle C1 may only be determined to be suspect vehicles), and user U1 may be determined to be a suspect user suspected of privately occupying suspect vehicles. After the suspected private vehicles and the suspected users of the suspected private vehicles are screened out, the foregoing step S110 is continuously executed.

In the embodiment of the disclosure, each user is taken as an object, and the primary vehicle is determined according to the total vehicle using times of the vehicle used by each user, so that each user and each vehicle can be ensured to be in a screening range, and the vehicle using behavior of each user for the used vehicle is fully considered, and omission is avoided; after the primary selection vehicles are determined, the meaning vehicles are screened out again according to the number of the vehicles of each primary selection vehicle and the behavior of the user using the vehicles for the last time, and the accuracy of screening results is ensured.

In the embodiment of the present disclosure, a suspected private vehicle and a suspected user of the suspected private vehicle may be screened out according to historical order data, and then, based on historical track information generated by the suspected user using the suspected vehicle, it may be further determined that there is an abnormal behavior of the suspected vehicle used for a specific service suspected user. The process uses different data and identification processes to carry out preliminary screening and fine identification on the user and the vehicle respectively, and fine identification is carried out on the basis of a preliminary screening result, so that the identification efficiency can be ensured to a certain extent.

In the embodiment of the present disclosure, after determining whether the suspected vehicle has the abnormal behavior used for the suspected user of the specific service, the suspected user may be defined as a private user, the suspected vehicle private to the private user may be defined as a private vehicle, and the private vehicle has the abnormal behavior used for the suspected user of the specific service. After the private user is determined, warning and education can be performed on the private user, for example, warning and education information is sent to a terminal of the private user to remind the private user to stop the private behavior, so that the account of the private user can be frozen to forbid the lease right of the private user. After the private vehicles are determined, the information of vehicle recovery can be sent to the terminals of the related workers so as to guide the workers to recover the private vehicles.

It will be understood by those skilled in the art that in the method of the present invention, the order of writing the steps does not imply a strict order of execution and any limitations on the implementation, and the specific order of execution of the steps should be determined by their function and possible inherent logic.

Based on the same inventive concept, the embodiment of the present disclosure further provides a vehicle abnormal behavior recognition device corresponding to the vehicle abnormal behavior recognition method, and as the principle of solving the problem of the vehicle abnormal behavior recognition device in the embodiment of the present disclosure is similar to that of the vehicle abnormal behavior recognition method in the embodiment of the present disclosure, the implementation of the device may refer to the implementation of the method, and repeated details are not repeated.

Referring to fig. 3, a vehicle abnormal behavior recognition apparatus 300, which is one of schematic diagrams of a vehicle abnormal behavior recognition apparatus provided in an embodiment of the present disclosure, includes a trajectory data acquisition module 310, a coincidence information determination module 320, and an abnormal behavior determination module 330.

The trajectory data obtaining module 310 is configured to determine, based on historical trajectory information of the suspected vehicle used by the suspected user indicated by the historical order data in the historical time period, a plurality of historical order trajectories corresponding to the suspected vehicle and position information of a plurality of trajectory points in each historical order trajectory.

And the coincidence information determining module 320 is configured to determine the trajectory coincidence information of the suspected vehicle according to the position information of the plurality of track points in each historical order trajectory.

An abnormal behavior determination module 330, configured to determine whether there is an abnormal behavior used for a specific service suspected user for the suspected vehicle based on the trajectory coincidence information.

In one possible implementation, the track coincidence information includes the number of coincident track points; when the coincidence information determining module 320 is configured to determine the trajectory coincidence information of the suspected vehicle according to the position information of the plurality of track points in each historical order trajectory, specifically, the coincidence information determining module is configured to:

and determining the number of the coincident track points in each historical order track pair based on the position information of the track points of each historical order track in each historical order track pair aiming at least one historical order track pair corresponding to the historical order tracks.

In a possible implementation, the coincidence information determining module 320, when configured to determine the trajectory coincidence information of the suspected vehicle according to the position information of the plurality of trajectory points in each historical order trajectory, is specifically configured to:

and matching the plurality of historical order tracks, and determining the number of overlapped track points in each historical order track pair based on the position information of the plurality of track points reserved after the duplication of each historical order track pair is removed.

In one possible implementation, the abnormal behavior determination module 330, when configured to determine whether there is an abnormal behavior used for a specific service suspected user for a suspected vehicle based on the trajectory coincidence information, is specifically configured to:

it is determined whether there is abnormal behavior of the suspected vehicle used for the particular service suspected user based on the number of target track pairs.

In a possible implementation, the abnormal behavior determination module 330, when configured to determine the number of target track pairs with high overlap ratio in at least one historical order track pair based on the number of overlapping track points in each historical order track pair, is specifically configured to:

determining the historical order track pairs with the number of the overlapped track points larger than a third preset threshold value as target track pairs with high overlap ratio, and determining the number of the target track pairs;

or calculating a second ratio of the number of the overlapped track points in each historical order track pair to the total number of the track points in the historical order track pair, determining the historical order track pair with the second ratio being greater than a fourth preset threshold as a target track pair with high overlap ratio, and determining the number of the target track pairs.

In one possible implementation, the abnormal behavior determination module 330, when configured to determine whether there is abnormal behavior of a suspected vehicle used for a particular service suspected user based on the number of target track pairs, is specifically configured to:

determining whether the number of the target track pairs is larger than a fifth preset threshold value, and if so, determining that abnormal behaviors used for a specific service suspected user exist in the suspected vehicle;

or calculating a third ratio of the number of the target track pairs to the total number of the historical order track pairs, determining whether the third ratio is greater than a sixth preset threshold, and if so, determining that the suspected vehicle has abnormal behaviors used for specific service suspected users.

In a possible implementation manner, referring to fig. 4, which is a second schematic diagram of a vehicle abnormal behavior recognition apparatus provided in an embodiment of the present disclosure, the vehicle abnormal behavior recognition apparatus 300 further includes a suspected object screening module 340 on the basis of the trajectory data obtaining module 310, the coincidence information determining module 320, and the abnormal behavior determining module 330. The suspected object filtering module 340 is configured to: and screening suspected private vehicles and suspected users of the suspected private vehicles based on historical order data in the historical time period.

In a possible implementation manner, the suspected object screening module 340, when configured to screen out a suspected private suspected vehicle and a suspected user of the suspected private suspected vehicle based on historical order data in a historical time period, is specifically configured to:

and screening suspected private vehicles and suspected users of the suspected private vehicles according to the historical order information corresponding to each user and the historical order information corresponding to each vehicle.

In a possible implementation manner, when the suspected object screening module 340 is configured to screen out suspected private suspected vehicles and suspected users of suspected private suspected vehicles according to the historical order information corresponding to each user and the historical order information corresponding to each vehicle, specifically, the suspected object screening module is configured to:

determining a suspected private candidate vehicle and a suspected private candidate vehicle based on the total number of vehicle uses corresponding to each user and the number of users corresponding to each vehicle;

and determining whether the candidate vehicle comprises a vehicle which is used by the candidate user for the last time or not according to the vehicle using time, and if so, determining that the candidate vehicle is a suspected private vehicle and the candidate user is a suspected private vehicle.

In a possible implementation manner, the suspected object screening module 340, when configured to determine, based on the total vehicle usage number corresponding to each user and the number of users corresponding to each vehicle, a candidate vehicle suspected to be privately occupied and a candidate user suspected to be privately occupied of the candidate vehicle, is specifically configured to:

The embodiment of the disclosure provides a vehicle abnormal behavior recognition device, which recognizes whether the vehicle has abnormal behavior by comparing the coincidence degree of a plurality of historical order tracks generated by the vehicle used by the same user according to the characteristic that the vehicle specially serving the same user has fixed-point commuting, and the recognition principle is practical and reliable, so that the correctness of the recognition result is ensured; moreover, the coincidence degree of the historical order track is determined by the fine-grained information of the track point, so that the efficiency and the accuracy of determining the track coincidence information can be ensured, and the accuracy of the identification result is greatly improved.

In addition, the device firstly screens out suspected private vehicles and suspected users of the suspected private vehicles according to historical order data, and then further determines that the suspected vehicles have abnormal behaviors used for specific service suspected users based on historical track information generated by the suspected users using the suspected vehicles. The process uses different data and identification processes to carry out preliminary screening and fine identification on the user and the vehicle respectively, and fine identification is carried out on the basis of a preliminary screening result, so that the identification efficiency can be ensured to a certain extent.

The description of the processing flow of each module in the device and the interaction flow between the modules may refer to the related description in the above method embodiments, and will not be described in detail here.

Based on the same inventive concept, a vehicle abnormal behavior identification method corresponding to the electronic map in fig. 1 further provides an electronic device, and as shown in fig. 5, the electronic device provided by the embodiment of the present disclosure is a schematic structural diagram. The electronic device 500 comprises a processor 51, a memory 52 and a bus 53. The memory 52 is used for storing instructions for execution and includes a memory 521 and an external memory 522. The memory 521 is also referred to as an internal memory, and is used for temporarily storing the operation data in the processor 51 and the data exchanged with the external memory 522 such as a hard disk, the processor 51 exchanges data with the external memory 522 through the memory 521, and when the electronic device 500 operates, the processor 51 communicates with the memory 52 through the bus 53, so that the processor 51 executes the following instructions:

Based on the same inventive concept, the disclosed embodiments also provide a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, performs the steps of the vehicle abnormal behavior identification method described in the above method embodiments. The storage medium may be a volatile or non-volatile computer-readable storage medium.

The embodiment of the present disclosure further provides a computer program product, which includes computer instructions, and the computer instructions, when executed by a processor, implement the steps of the above-mentioned vehicle abnormal behavior identification method. The computer program product may be any product capable of implementing the above-mentioned abnormal vehicle behavior identification method, and all or part of the solutions in the computer program product that contribute to the prior art may be embodied in the form of a Software product (e.g., Software Development Kit (SDK)), which may be stored in a storage medium and causes an associated device or processor to execute all or part of the steps of the above-mentioned abnormal vehicle behavior identification method through included computer instructions.

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 disclosure, 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 disclosure 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 solution of the present disclosure 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 method according to the embodiments of the present disclosure. 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.

Finally, it should be noted that: the above-mentioned embodiments are merely specific embodiments of the present disclosure, which are used for illustrating the technical solutions of the present disclosure and not for limiting the same, and the scope of the present disclosure is not limited thereto, and although the present disclosure is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive of the technical solutions described in the foregoing embodiments or equivalent technical features thereof within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present disclosure, and should be construed as being included therein. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.

The embodiment of the disclosure provides a method, a device, a storage medium and a computer program product for identifying abnormal behaviors of a vehicle, which specifically comprise:

TS1, a vehicle abnormal behavior recognition method, characterized in that the method includes:

TS2, the method of claim TS1, wherein the track coincidence information includes a number of coincident track points; the determining the track coincidence information of the suspected vehicle according to the position information of the plurality of track points in each historical order track comprises the following steps:

The method of TS3 and TS2, wherein the determining track coincidence information of the suspected vehicle according to the position information of the plurality of track points in each historical order track comprises:

The method of claim TS2, TS4, wherein the determining whether the suspected vehicle has abnormal behavior used to specifically service the suspected user based on the trajectory coincidence information comprises:

TS5, the method according to claim TS4, wherein the determining the number of target track pairs with high contact ratio in the at least one historical order track pair based on the number of overlapping track points in each historical order track pair comprises:

The TS6, the method of claim TS4, wherein the determining whether the suspected vehicle has abnormal behavior used to specifically service the suspected user based on the number of target track pairs comprises:

The method of claim TS1, at TS7, wherein prior to the determining the plurality of historical order tracks for the suspect vehicle, and the location information for the plurality of track points in each historical order track, the method further comprises: and screening suspected vehicles suspected to be privately occupied and suspected users suspected to be privately occupied on the suspected vehicles based on historical order data in a historical time period.

The TS8 and the method of claim TS7, wherein the screening suspected private vehicles and suspected private users of the suspected private vehicles based on historical order data over a historical period of time comprises:

The TS9 and the method of claim TS8, wherein the screening suspected private vehicles and suspected private users of the suspected private vehicles according to the historical order information corresponding to each user and the historical order information corresponding to each vehicle includes:

The method of claim TS9, and TS10, wherein the determining the candidate vehicle suspected of being privately occupied and the candidate users suspected of privately occupied based on the total number of uses for each user and the number of users for each vehicle comprises:

TS11, an abnormal behavior recognition apparatus for a vehicle, comprising:

TS12, an electronic device, comprising: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor for communicating with the memory over the bus when the electronic device is operating, the machine-readable instructions when executed by the processor performing the steps of the vehicle abnormal behavior identification method of any one of claims TS 1-TS 10.

TS13, a computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when being executed by a processor, carries out the steps of the method for identifying abnormal behavior of a vehicle according to any one of claims 1 to 10.

TS14, a computer program product comprising computer instructions, characterized in that said computer instructions, when executed by a processor, implement the steps of a method for identifying abnormal behaviour in a vehicle according to any one of claims TS1 to TS 10.

Claims

1. A vehicle abnormal behavior recognition method, characterized by comprising:

2. The method of claim 1, wherein the track coincidence information includes a number of coincident track points; the determining the track coincidence information of the suspected vehicle according to the position information of the plurality of track points in each historical order track comprises the following steps:

3. The method of claim 2, wherein determining the number of coincident track points in each pair of historical order tracks based on the location information for the plurality of track points for each historical order track in the pair comprises:

4. The method of claim 2, wherein said determining whether the suspected vehicle has abnormal behavior used to specifically service the suspected user based on the trajectory coincidence information comprises:

5. The method of claim 4, wherein determining the number of target track pairs with high overlap in the at least one historical order track pair based on the number of coincident track points in each historical order track pair comprises:

6. The method of claim 4, wherein said determining whether the suspected vehicle has abnormal behavior used to specifically service the suspected user based on the number of target track pairs comprises:

7. An abnormal behavior recognition apparatus for a vehicle, characterized by comprising:

8. 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 via the bus when the electronic device is operating, the machine-readable instructions being executed by the processor to perform the steps of the vehicle abnormal behavior identification method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when being executed by a processor, carries out the steps of the vehicle abnormal behavior identification method according to any one of claims 1 to 6.

10. A computer program product comprising computer instructions, characterized in that said computer instructions, when executed by a processor, implement the steps of a vehicle abnormal behavior identification method according to any one of claims 1 to 6.