Abnormal trajectory identification method, device, electronic device and storage medium

Abstract

The present application provides an abnormal trajectory identification method, device, electronic device and storage medium, which relates to the field of information processing technology and can accurately identify abnormal driving trajectories. The specific scheme includes: obtaining the travel data of the vehicle; the travel data includes: the starting position and the end position of the driving trajectory, and the length of the driving trajectory; according to the starting position and the end position, determining the length of the target planned path; the target planned path is the path from the starting position to the end position; determining the excess rate of the length of the driving trajectory compared to the length of the target planned path; if the excess rate is greater than the preset excess rate threshold, determining that the driving trajectory is abnormal.

Description

Technical Field

[0001] The present application relates to the field of information processing technology, and in particular to an abnormal trajectory recognition method, device, electronic device and storage medium. Background Art

[0002] At present, every time an online ride-hailing service completes an order, it can report travel data such as driving trajectory and vehicle information to the online ride-hailing platform. Then, the online ride-hailing platform can determine the mileage based on the driving trajectory, and then calculate the driving fee of the order based on the driving mileage. Among them, some online ride-hailing services will tamper with the driving trajectory in order to increase the driving fee. The mileage determined by the online ride-hailing platform based on the tampered mileage exceeds the actual mileage. As a result, the driving fee calculated based on the mileage exceeds the actual driving fee.

[0003] The related scheme calculates the average driving speed for each travel data using the mileage and total duration corresponding to the travel data. Then, it determines whether the average driving speed is greater than the preset speed threshold to determine whether the driving trajectory in the travel data is abnormal. Among them, if the speed threshold is set too high, some abnormal driving trajectories with lower driving speeds cannot be identified. If the speed threshold is set too low, some normal driving trajectories with higher driving speeds caused by vehicles driving on highways and expressways may be identified as abnormal. In summary, the related scheme cannot accurately determine whether the driving trajectory of the online car-hailing vehicle is abnormal. Summary of the invention

[0004] The present application provides a method, device, electronic device and storage medium for identifying an abnormal trajectory, which can accurately identify an abnormal driving trajectory.

[0005] In order to achieve the above technical objectives, this application adopts the following technical solutions:

[0006] In a first aspect, an embodiment of the present application provides a method for identifying an abnormal trajectory, the method comprising: first obtaining travel data of a vehicle; the travel data comprising: a starting position and an end position of the driving trajectory, and a length of the driving trajectory; then, determining the length of a target planned path based on the starting position and the end position; then determining an excess rate of the length of the driving trajectory compared to the length of the target planned path; if the excess rate is greater than a preset excess rate threshold, determining that the driving trajectory is abnormal.

[0007] The target planning path is the path from the starting position to the end position.

[0008] It can be understood that the electronic device determines the length of the target planning path according to the starting position and the end position in the driving trajectory; and then determines the excess rate of the length of the driving trajectory compared to the length of the target planning path. Among them, the high or low driving speed of the vehicle will not affect the length of the driving trajectory of the vehicle, that is, whether the vehicle is driving on a highway or a low-speed road, the length of the driving trajectory of the vehicle is the same. Then, the excess rate of the length of the driving trajectory compared to the length of the target planning path is also independent of the highway or low-speed road on which the vehicle is traveling. The size of the average driving speed in the relevant scheme is affected by the highway or low-speed road on which the vehicle is traveling. Therefore, the electronic device determines whether the driving trajectory of the vehicle is abnormal based on whether the excess rate is greater than the preset excess rate threshold, which is more accurate than judging whether the driving trajectory is abnormal based on the size of the average driving speed in the relevant scheme. In other words, the electronic device determines whether the driving trajectory of the vehicle is abnormal based on whether the excess rate is greater than the preset excess rate threshold, which improves the accuracy of identifying abnormal driving trajectories.

[0009] Secondly, the target planning path may refer to the actual path from the starting position to the terminal position, for example, the target planning path is the path from the starting position to the terminal position on the map. In other words, the target planning path is the actual driving path of the vehicle from the starting position to the terminal position. Then, the electronic device determines the excess rate of the length of the driving trajectory compared to the length of the target planning path. The excess rate is the excess rate of the length of the driving trajectory compared to the length of the actual driving path. Then, the larger the excess rate, the higher the possibility that the driving trajectory is abnormal. Therefore, the electronic device can more accurately determine that the driving trajectory is abnormal when the excess rate is greater than the preset excess rate threshold.

[0010] In a possible implementation, before determining the length of the target planned path according to the starting position and the end position, the method further includes: determining whether the length of the driving track is greater than a preset mileage threshold; the preset mileage threshold is determined based on a plurality of abnormal historical driving tracks. Determining the length of the target planned path according to the starting position and the end position includes: if the length of the driving track is greater than the preset mileage threshold, determining the length of the target planned path according to the starting position and the end position.

[0011] It is understandable that since most travel data with abnormal driving trajectories have the characteristic of high mileage, the electronic device can determine whether the length of the driving trajectory (i.e., mileage) in a travel data is greater than a preset mileage threshold. Among them, the preset mileage threshold is determined based on multiple abnormal historical driving trajectories, and the preset mileage threshold can satisfy that multiple abnormal historical driving trajectories are greater than the preset mileage threshold. Then, if the length of the driving trajectory is greater than the preset mileage threshold, it is characterized that the possibility of abnormality of the driving trajectory is high. At this time, the electronic device can further determine the length of the target planned path corresponding to the driving trajectory to further determine whether the driving trajectory is abnormal.

[0012] In another possible implementation, the travel data further includes: information about the initiating object of calling the vehicle. Before determining the length of the target planned path according to the starting point position and the end point position, the method further includes: determining whether the initiating object represented by the initiating object information belongs to a preset object. Determining the length of the target planned path according to the starting point position and the end point position includes: if the initiating object belongs to the preset object, determining the length of the target planned path according to the starting point position and the end point position.

[0013] It is understandable that since the initiating objects of calling vehicles in most travel data with abnormal driving trajectories are enterprises, the electronic device can determine whether the initiating object represented by the initiating object information in a travel data belongs to a preset object. The preset object may include an enterprise. If the initiating object represented by the initiating object information belongs to the preset object, the possibility of representing the driving trajectory as abnormal is high. At this time, the electronic device can further determine the length of the target planned path corresponding to the driving trajectory to further determine whether the driving trajectory is abnormal.

[0014] In another possible implementation, the method also includes: obtaining multiple normal historical travel data; one normal historical travel data includes: a first starting point position and a first end point position, and the length of a normal historical driving trajectory; for each normal historical travel data in the multiple normal historical travel data, determining the length of the first planned path according to the first starting point position and the first end point position; for each normal historical travel data in the multiple normal historical travel data, determining a first excess rate; and determining a preset excess rate threshold according to multiple first excess rates corresponding to the multiple normal historical travel data.

[0015] The first planned path is a path from the first starting point to the first end point. The first excess rate is an excess rate of the length of the normal historical driving trajectory compared to the length of the first planned path.

[0016] It can be understood that, compared with the excess rate of the length of the abnormal historical driving trajectory compared to the length of the corresponding planned path, the excess rate of the length of the normal historical driving trajectory compared to the length of the corresponding planned path is usually smaller. Then, the electronic device can set a preset excess rate threshold according to multiple first excess rates corresponding to multiple normal historical driving trajectories, and the preset excess rate threshold can satisfy that the multiple first excess rates are basically less than the preset excess rate threshold. Furthermore, if the excess rate of the length of the driving trajectory in the travel data compared to the length of the corresponding target planned path is greater than the preset excess rate threshold, the driving trajectory can be accurately determined to be abnormal.

[0017] In another possible implementation, the above-mentioned determination of a preset excess rate threshold based on multiple first excess rates corresponding to multiple normal historical travel data includes: for each reference excess rate threshold among multiple reference excess rate thresholds, counting at least one first proportion corresponding to the reference excess rate threshold; and determining the preset excess rate threshold from multiple reference excess rate thresholds based on at least multiple first proportions corresponding to the multiple reference excess rate thresholds.

[0018] Among them, each first proportion in at least one first proportion is the proportion of the number of second historical travel data with a first excess rate greater than a reference excess rate threshold in the number of multiple first historical travel data within the same mileage range. At least one first proportion corresponds to a different mileage range. The multiple first historical travel data belong to multiple normal historical travel data.

[0019] It can be understood that the first proportion corresponding to a reference excess rate threshold represents the proportion of the second historical travel data whose first excess rate is greater than the reference excess rate threshold among multiple first historical travel data within the same mileage range, and multiple first historical travel data and second historical travel data are all normal historical travel data. The smaller the first proportion is, the fewer normal historical travel data whose first excess rate is greater than the reference excess rate threshold is, that is, the first excess rate corresponding to more normal historical travel data is less than the reference excess rate threshold. Then, if the reference excess rate threshold corresponding to a smaller first proportion is determined as the preset excess rate threshold, it can be determined that the first excess rate corresponding to many normal historical travel data is less than the preset excess rate threshold. Furthermore, if the excess rate corresponding to a travel data is greater than the preset excess rate threshold, it can be determined that the driving trajectory in the travel data is likely to be abnormal. Therefore, the smaller the first proportion is, the higher the accuracy of the abnormal driving trajectory determined by the reference excess rate threshold corresponding to the first proportion is.

[0020] In another possible implementation, the method also includes: obtaining multiple abnormal historical travel data; one abnormal historical travel data includes: a second starting point position and a second end point position, and the length of the abnormal historical driving trajectory; for each abnormal historical travel data in the multiple abnormal historical travel data, determining the length of the second planned path according to the second starting point position and the second end point position; for each abnormal historical travel data in the multiple abnormal historical travel data, determining the second excess rate; for each reference excess rate threshold, counting at least one second proportion corresponding to the reference excess rate threshold.

[0021] The above-mentioned method of determining a preset excess rate threshold from multiple reference excess rate thresholds at least according to multiple first proportions corresponding to multiple reference excess rate thresholds includes: determining a preset excess rate threshold from multiple reference excess rate thresholds according to multiple first proportions corresponding to multiple reference excess rate thresholds and multiple second proportions corresponding to multiple reference excess rate thresholds.

[0022] Among them, the second planned path is the path from the second starting point position to the second end point position. The second excess rate is the excess rate of the length of the abnormal historical driving trajectory compared to the length of the second planned path. Each second proportion in at least one second proportion is the proportion of the number of fourth historical travel data with a second excess rate greater than the reference excess rate threshold in the number of multiple third historical travel data within the same mileage range. At least one second proportion corresponds to a different mileage range. Multiple third historical travel data belong to multiple abnormal historical travel data. The first proportion corresponding to the preset excess rate threshold is smaller than the second proportion corresponding to the preset excess rate threshold.

[0023] It can be understood that, since the second proportion corresponding to a reference excess rate threshold represents the proportion of the fourth historical travel data with a second excess rate greater than the reference excess rate threshold in the multiple third historical travel data within the same mileage range, and the multiple third historical travel data and the fourth historical travel data are all abnormal historical travel data, then the larger the second proportion, the more abnormal historical travel data with the corresponding second excess rate greater than the reference excess rate threshold, that is, the second excess rate corresponding to more abnormal historical travel data is greater than the reference excess rate threshold. Then, if the reference excess rate threshold corresponding to a larger second proportion is determined as the preset excess rate threshold, the preset excess rate threshold can be used to identify more travel data with abnormal driving trajectories. Therefore, the electronic device can determine the reference excess rate threshold corresponding to the larger second proportion as the preset excess rate threshold. Combined with the above analysis, the higher the accuracy of the abnormal driving trajectory determined by the reference excess rate threshold corresponding to the smaller first proportion, the electronic device can determine the reference excess rate threshold corresponding to the smaller first proportion and the larger second proportion as the preset excess rate threshold.

[0024] In a second aspect, the present application provides an abnormal trajectory recognition device, which includes modules for executing the method described in the first aspect or any possible design of the first aspect.

[0025] In a third aspect, the present application provides an electronic device, the electronic device comprising a memory and a processor. The memory and the processor are coupled. The memory is used to store a computer program code, the computer program code comprising a computer instruction. When the processor executes the computer instruction, the electronic device performs the method for identifying an abnormal trajectory as described in the first aspect and any possible design thereof.

[0026] In a fourth aspect, the present application provides a chip system, which is applied to an abnormal trajectory recognition device; the chip system includes one or more interface circuits and one or more processors. The interface circuit and the processor are interconnected through a line; the interface circuit is used to receive a signal from the memory of the abnormal trajectory recognition device and send a signal to the processor, the signal including a computer instruction stored in the memory. When the processor executes the computer instruction, the electronic device executes the abnormal trajectory recognition method as described in the first aspect and any possible design thereof.

[0027] In a fifth aspect, the present application provides a computer-readable storage medium storing computer instructions. When the computer instructions are executed on an electronic device, the electronic device executes the abnormal trajectory identification method as described in the first aspect and any possible design method thereof.

[0028] In a sixth aspect, the present application provides a computer program product, which includes computer instructions. When the computer instructions are executed on an electronic device, the electronic device executes the abnormal trajectory identification method as described in the first aspect and any possible design method thereof.

[0029] For the specific description of the second to sixth aspects and their various implementations in the present application, reference may be made to the detailed description in the first aspect and its various implementations; and for the beneficial effects of the second to sixth aspects and their various implementations, reference may be made to the beneficial effects analysis in the first aspect and its various implementations, which will not be repeated here.

[0030] These and other aspects of the present application will become more apparent from the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 Schematic diagram of the implementation environment involved in the abnormal trajectory identification method provided in the embodiment of the present application Figure 1 ;

[0032] Figure 2 Schematic diagram of the implementation environment involved in the abnormal trajectory identification method provided in the embodiment of the present application Figure 2 ;

[0033] Figure 3 Schematic diagram of the implementation environment involved in the abnormal trajectory identification method provided in the embodiment of the present application Figure 3 ;

[0034] Figure 4 A process of identifying an abnormal trajectory provided in an embodiment of the present application Figure 1 ;

[0035] Figure 5 A process of identifying an abnormal trajectory provided in an embodiment of the present application Figure 2 ;

[0036] Figure 6 A schematic diagram of the structure of an abnormal trajectory identification device provided in an embodiment of the present application;

[0037] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0038] In the following, the terms "first", "second", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, features defined as "first", "second", etc. may explicitly or implicitly include one or more of the features.

[0039] At present, in order to identify the tampered driving trajectory (which can be called an abnormal driving trajectory), the relevant scheme determines the average driving speed corresponding to the driving trajectory according to each travel data. Then, it is determined whether the average driving speed is greater than a preset speed threshold to determine whether the driving trajectory is abnormal.

[0040] Among them, if the vehicle has traveled on highways and expressways, the average driving speed will be higher. If the vehicle has only traveled on urban roads with lower speed limits, the average driving speed will be lower. In this case, if the speed threshold is set high, some abnormal driving trajectories with lower driving speeds cannot be identified. If the speed threshold is set low, some normal driving trajectories with higher driving speeds caused by vehicles traveling on highways and expressways may be identified as abnormal driving trajectories. Then, the relevant scheme cannot accurately determine whether the driving trajectory of the online car-hailing vehicle is abnormal through the preset speed threshold.

[0041] In the embodiment of the present application, by analyzing some travel data with abnormal driving trajectories, it can be found that the travel data with abnormal driving trajectories all have some characteristics. These characteristics may include: the characteristic of high mileage, the characteristic that the initiator of calling the vehicle is an enterprise, and the characteristic that the abnormal frequency of the same driver is high.

[0042] Specifically, the feature of high mileage may refer to: the mileage of abnormal driving trajectories is relatively large (i.e., greater than a mileage threshold), for example, the average mileage of these abnormal driving trajectories is equal to 47.9 kilometers (km). Moreover, the difference between the mileage of the abnormal driving trajectories and the length of the planned paths corresponding to each of these abnormal driving trajectories is relatively large. For example, the average excess rate of the mileage of these abnormal driving trajectories compared to the length of the planned paths corresponding to each of these abnormal driving trajectories is equal to 90.68%. Among them, the planned path corresponding to each abnormal driving trajectory is the path from the starting point of the abnormal driving trajectory to the end point of the abnormal driving trajectory. The planned path is an actual path, for example, the planned path may be a path on a map from the starting point of the abnormal driving trajectory to the end point of the abnormal driving trajectory.

[0043] Secondly, the feature that the initiator of calling the vehicle is an enterprise can mean that in the travel data with abnormal driving trajectories, the initiator of calling the vehicle is more likely to be an enterprise. The feature that the abnormal frequency of the same driver is high can mean that the number of abnormal driving trajectories of the same driver within a certain period of time is high (i.e., greater than a frequency threshold). For example, the number of abnormal driving trajectories of one driver in these travel data with abnormal driving trajectories is as high as 27 times in one month.

[0044] To summarize, in the embodiment of the present application, the electronic device can determine whether the driving trajectory in a travel data is abnormal based on the above characteristics.

[0045] Furthermore, in order to accurately determine whether a driving trajectory in a travel data is abnormal, the electronic device may also obtain the excess rate of the mileage of the normal driving trajectory compared to the length of the planned path corresponding to the normal driving trajectory. If the excess rate of the mileage of the normal driving trajectory compared to the length of the planned path corresponding to the normal driving trajectory is small, and combined with the fact that the mileage of the abnormal driving trajectory exceeds the length of the planned path corresponding to the abnormal driving trajectory, the electronic device may determine a preset excess rate threshold, and an excess rate corresponding to a travel data greater than the preset excess rate threshold indicates that the driving trajectory in the travel data is abnormal.

[0046] Specifically, the electronic device first obtains a plurality of normal historical travel data and a plurality of abnormal historical travel data. Among them, each normal historical travel data means that the historical driving trajectory in the normal historical travel data is normal. Each normal historical trajectory data includes: a first starting point position, a first end point position, and the length of the normal historical driving trajectory (which can be called a normal historical driving mileage). Each abnormal historical travel data means that the historical driving trajectory in the abnormal historical travel data is abnormal. Each abnormal historical trajectory data includes: a second starting point position, a second end point position, and the length of the abnormal historical driving trajectory (which can be called an abnormal historical driving mileage).

[0047] Then, for each normal historical travel data, the electronic device obtains the length of the actual path (which can be called the first planned path) from the first starting point to the first end point; and then calculates the excess rate (which can be called the first excess rate) of the length of the normal historical travel trajectory in the normal historical travel data compared to the length of the first planned path. Similarly, for each abnormal historical travel data, the electronic device obtains the length of the actual path (which can be called the second planned path) from the second starting point to the second end point; and then calculates the excess rate (which can be called the second excess rate) of the length of the abnormal historical travel trajectory in the abnormal historical travel data compared to the length of the second planned path.

[0048] Then, the electronic device can obtain multiple reference excess rate thresholds, for example, 10%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, 90%, 100%. The electronic device then counts the proportion of normal historical travel data whose first excess rate is greater than each reference excess rate threshold in multiple normal historical travel data (which can be called the first proportion) for multiple first excess rates corresponding to multiple normal historical travel data. Furthermore, the electronic device can obtain multiple first proportions corresponding to multiple reference excess rate thresholds. The electronic device also counts the proportion of abnormal historical travel data whose second excess rate is greater than each reference excess rate threshold in multiple abnormal historical travel data (which can be called the second proportion) for multiple second excess rates corresponding to multiple abnormal historical travel data. Furthermore, the electronic device can obtain multiple second proportions corresponding to multiple reference excess rate thresholds.

[0049] Finally, after the electronic device obtains multiple first proportions corresponding to multiple reference excess rate thresholds and multiple second proportions corresponding to multiple reference excess rate thresholds, if one of the multiple reference excess rate thresholds satisfies that its corresponding first proportion is less than the first preset ratio, and its corresponding second proportion is greater than the second preset ratio, the reference excess rate threshold can be determined to be the preset excess rate threshold. Among them, the first preset ratio is less than the second preset ratio. For example, the first preset ratio can be 3%, 4% or 5%, etc. The second preset ratio can be 40% or 50%, etc. The first proportion corresponding to the preset excess rate threshold is less than the first preset ratio, and the second proportion corresponding to the preset excess rate threshold is greater than the second preset ratio, indicating that the excess rate corresponding to most of the normal historical travel data is less than the preset excess rate threshold, and the excess rate corresponding to most of the abnormal historical travel data is greater than the preset excess rate threshold. Then, if the excess rate corresponding to a travel data is greater than the preset excess rate threshold, the electronic device can accurately determine that the driving trajectory in the travel data is abnormal.

[0050] The implementation of the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0051] Please refer to Figure 1 , which shows a schematic diagram of the implementation environment involved in a method for identifying abnormal trajectories provided in an embodiment of the present application. Figure 1 As shown, the implementation environment may include: a first server 100, a terminal 110, a plurality of collection devices 120 for collecting travel data of vehicles, and a second server 130. The plurality of collection devices 120 are respectively installed in different vehicles.

[0052] The first server 100 can receive the travel data of the vehicle from the collection device 120 in each vehicle. The travel data may include: the longitude and latitude of multiple track points in the driving trajectory and the collection time, the initiator information of the vehicle call, the driver information, and the vehicle information. The first server 100 can also determine the length of the driving trajectory (i.e., the mileage) based on the longitude and latitude of the multiple track points. Among them, the driving trajectory is composed of multiple track points collected from the boarding time to the getting off time, and the collection positions (such as longitude and latitude) of the multiple track points in the driving trajectory can represent the complete driving trajectory. The length of the driving trajectory may refer to the length of the line obtained by connecting the multiple track points in the order of the collection time. The multiple track points include the starting point and the end point of the driving trajectory.

[0053] The second server 130 may be a server for providing geographic information services. The geographic information service may include a path planning function. The path planning function refers to a function for determining an actual path (which may be referred to as a planned path) from a starting point to an end point. The planned path may include a path from a starting point to an end point on a map. The second server 130 provides an application programming interface (API) for calling the path planning function. The first server 100 may access the API to call the path planning function provided by the second server 130.

[0054] Exemplarily, each acquisition device 120 may include a GPS module, a timing module, and an input module (eg, a touch screen). Figure 1 The GPS module, timing module and input module in the acquisition module 120 are not shown. The GPS module is used to collect the longitude and latitude of multiple track points in the driving track. For example, the GPS module collects one track point every 5 seconds. The timing module is used to record the collection time of multiple track points. The input module is used to collect driver information, vehicle information, etc. input by the driver.

[0055] Specifically, Figure 2 As shown, the terminal 110 can receive a first operation input by a user, and the first operation is used to indicate a target area and / or a target vehicle type (such as an online car-hailing service, a taxi), etc. Then, in response to the first operation, the terminal 110 can obtain travel data of a vehicle belonging to the target vehicle type that is traveling in the target area from the first server 100. The terminal 110 can also send the starting position and the end position in the travel data to the second server 130; and then receive the planned path from the starting position to the end position and the length of the planned path sent by the second server 130. The terminal 110 can determine the excess rate of the mileage in the travel data compared to the length of the planned path (which can be called the excess rate corresponding to the driving trajectory in the travel data). The terminal 110 can determine whether the driving trajectory in the travel data is abnormal based on whether the excess rate corresponding to the driving trajectory is greater than a preset excess rate threshold, and whether the initiator of calling the vehicle in the travel data belongs to at least one of the enterprises. If the driving trajectory is abnormal, a prompt message can be issued, and the prompt message is used to characterize the abnormal driving trajectory of the vehicle. For example, the terminal 110 can display the prompt message through a display screen.

[0056] Or, if Figure 3As shown, in response to the first operation, the terminal 110 may send target information to the first server 100. The target information includes a target area and a target vehicle type, etc. The first server 100 may obtain travel data of vehicles of the target vehicle type traveling in the target area. The first server 100 may also send the starting position and the end position in the travel data to the second server 130; and then receive the planned path from the starting position to the end position and the length of the planned path sent by the second server 130. The first server 100 may determine the excess rate of the mileage in the travel data compared to the length of the planned path (which may be referred to as the excess rate corresponding to the driving trajectory in the travel data). The first server 100 may determine whether the driving trajectory in the travel data is abnormal according to whether the excess rate corresponding to the driving trajectory is greater than a preset excess rate threshold, and whether the initiator of calling the vehicle in the travel data belongs to at least one of the enterprises. If the driving trajectory is abnormal, the above-mentioned prompt information may be sent to the terminal 110. The terminal 110 may issue the prompt information.

[0057] Exemplarily, the terminal 110 in the embodiment of the present application may be a mobile phone, a tablet computer, a desktop, a laptop, a notebook computer, a netbook, etc. The embodiment of the present application does not impose any special limitation on the specific form of the terminal 110.

[0058] It should be noted that the method for identifying abnormal trajectories provided in the embodiment of the present application can be applied to the above-mentioned first server 100, can also be applied to the above-mentioned terminal 110, and can also be applied to the above-mentioned first server 100 and the terminal 110. The first server 100 and the terminal 110 can be collectively referred to as electronic devices. The executor of the method for identifying abnormal trajectories provided in the embodiment of the present application can also be an abnormal trajectory identification device. The identification device can be an electronic device; or, the device can be an application (application, APP) installed in the electronic device that provides an abnormal trajectory identification function; or, the device can be a central processing unit (Central Processing Unit, CPU) in the electronic device; or, the device can be a control module in the electronic device for executing the abnormal trajectory identification method.

[0059] The following describes in detail the abnormal trajectory recognition method provided by the embodiment of the present application by taking an electronic device as an example.

[0060] Please refer to Figure 4 , is a flow chart of a method for identifying abnormal trajectories provided in an embodiment of the present application. Figure 4 As shown, the method may include S201-S204.

[0061] S201. The electronic device obtains travel data of the vehicle; the travel data includes: a starting point and an end point of a driving track, and a length of the driving track.

[0062] The electronic device can obtain the travel data of any vehicle, or obtain the travel data of vehicles belonging to the target vehicle type. The target vehicle type may include: online car-hailing and / or taxi.

[0063] Among the multiple trajectory points, the trajectory point with the first collection time is the starting point of the driving trajectory, and the trajectory point with the last collection time is the end point of the driving trajectory. The starting point position of the driving trajectory refers to the collection position of the starting point. The end point position of the driving trajectory refers to the collection position of the end point. The collection position of each trajectory point can be the longitude and latitude of the trajectory point.

[0064] The travel data may also include: an order identifier, driver information, and vehicle information corresponding to the travel data, etc. The vehicle information may be a vehicle identifier, such as a vehicle number, a license plate number, and the like.

[0065] S202: The electronic device determines the length of the target planning path according to the starting position and the end position; the target planning path is the path from the starting position to the end position.

[0066] The electronic device may send the starting position and the end position to a server (e.g., the second server 230) that provides a path planning function. The electronic device then receives at least one planned path from the starting position to the end position sent by the server, and the length of each planned path in the at least one planned path. The electronic device may determine the target planned path and the length of the target planned path from the at least one planned path. Among them, the at least one planned path (including the target planned path) may all refer to the path from the starting position to the end position on the map.

[0067] Exemplarily, the electronic device may send the starting point location and the ending point location to the server through an API for calling a path planning function provided by the server.

[0068] Exemplarily, the target planning path may be the shortest path from the starting position to the ending position on the map.

[0069] It is understandable that after the electronic device obtains the travel data of the vehicle, it is no longer able to obtain the road conditions of the vehicle during its travel from the starting position to the end position (including the congestion conditions of each path on the map). Furthermore, the electronic device is also unable to obtain the planned path from the starting position to the end position on the map based on the road conditions. The electronic device can obtain the shortest path from the starting position to the end position on the map without considering the road conditions as the target planned path. The shortest path is available for reference under any road conditions.

[0070] In some embodiments, the electronic device can convert the starting point position into a starting point identifier (e.g., a starting point name) and the ending point position into an ending point identifier (e.g., a starting point name). The electronic device then sends the starting point identifier and the ending point identifier to a server providing a path planning function to obtain the target planning path and the length of the target planning path.

[0071] S203: The electronic device determines an excess rate of the length of the driving trajectory compared to the length of the target planned path.

[0072] The electronic device may obtain the excess rate by subtracting the length of the target planned path from the length of the driving trajectory and dividing the result by the length of the target planned path.

[0073] S204: If the excess rate is greater than a preset excess rate threshold, the electronic device determines that the driving trajectory is abnormal.

[0074] Among them, the preset excess rate threshold is determined based on multiple first excess rates and multiple second excess rates; the first excess rate refers to the excess rate of the length of the normal historical driving trajectory compared to the length of the planned path corresponding to the normal historical driving trajectory; the second excess rate refers to the excess rate of the length of the abnormal historical driving trajectory compared to the length of the planned path corresponding to the abnormal historical driving trajectory.

[0075] After obtaining the excess rate, the electronic device determines whether the excess rate is greater than a preset excess rate threshold. If the excess rate is greater than the preset excess rate threshold, the electronic device can determine that the driving trajectory is abnormal. If the excess rate is less than or equal to the preset excess rate threshold, the electronic device can determine that the driving trajectory is normal.

[0076] In some embodiments, the electronic device can obtain multiple normal historical travel data. A normal historical travel data includes: a first starting point position and a first end point position, and the length of a normal historical driving trajectory. The electronic device then determines the length of the first planned path based on the first starting point position and the first end point position. The electronic device can also determine a first excess rate, which is the excess rate of the length of the normal historical driving trajectory compared to the length of the first planned path. Then, the electronic device can determine a preset excess rate threshold based on multiple first excess rates corresponding to multiple normal historical travel data.

[0077] The electronic device can determine the length of the first planned path for each normal historical travel data; then subtract the length of the first planned path from the length of the normal historical travel track in the normal historical travel data, and divide the difference by the length of the first planned path to obtain the first excess rate. Furthermore, the electronic device can obtain multiple first excess rates corresponding to multiple normal historical travel data. Among them, the first planned path is the path from the first starting position to the first end position. The first planned path is the actual path from the first starting position to the first end position, such as the first planned path is the actual path from the first starting position to the first end position on the map.

[0078] Furthermore, after obtaining multiple first excess rates, the electronic device can count at least one first proportion corresponding to each reference excess rate threshold in the multiple reference excess rate thresholds. The electronic device then determines a preset excess rate threshold from the multiple reference excess rate thresholds based on at least the multiple first proportions corresponding to the multiple reference excess rate thresholds.

[0079] Among them, each first proportion in at least one first proportion is the proportion of the number of second historical travel data with a first excess rate greater than a reference excess rate threshold in the number of multiple first historical travel data within the same mileage range. At least one first proportion corresponds to a different mileage range; the number of at least one proportion corresponding to each reference excess rate threshold is equal to the number of at least one mileage range. Multiple first historical travel data belong to multiple normal historical travel data; second historical travel data belong to multiple first historical travel data.

[0080] The multiple first historical travel data within the same mileage range may refer to multiple historical travel data whose driving track lengths are within the same mileage range, for example, multiple first historical travel data within 3km to 10km, or multiple first historical travel data within 10km to 30km.

[0081] It can be understood that the first proportion corresponding to a reference excess rate threshold represents the proportion of the second historical travel data whose first excess rate is greater than the reference excess rate threshold among multiple first historical travel data within the same mileage range, and multiple first historical travel data and second historical travel data are all normal historical travel data. The smaller the first proportion is, the fewer normal historical travel data whose first excess rate is greater than the reference excess rate threshold is, that is, the first excess rate corresponding to more normal historical travel data is less than the reference excess rate threshold. Then, if the reference excess rate threshold corresponding to a smaller first proportion is determined as the preset excess rate threshold, it can be determined that the first excess rate corresponding to many normal historical travel data is less than the preset excess rate threshold. Furthermore, if the excess rate corresponding to a travel data is greater than the preset excess rate threshold, it can be determined that the driving trajectory in the travel data is likely to be abnormal. Therefore, the smaller the first proportion is, the higher the accuracy of the abnormal driving trajectory determined by the reference excess rate threshold corresponding to the first proportion is.

[0082] Secondly, the smaller the first proportion is, the larger the reference excess rate threshold corresponding to the first proportion is, and the larger the preset excess rate threshold whose value is equal to the reference excess rate threshold is. The larger the preset excess rate threshold is, the smaller the excess rate corresponding to the travel data with abnormal driving trajectory is, and it cannot be identified. Therefore, the preset excess rate threshold cannot be too large, that is, the first proportion cannot be too small. The electronic device can determine a reference excess rate threshold from multiple reference excess rate thresholds as the preset excess rate threshold, and at least one proportion corresponding to this reference excess rate threshold is relatively small (that is, for multiple first historical travel data within different mileage ranges, the second historical travel data with a first excess rate greater than this reference excess rate threshold accounts for a relatively small proportion in the multiple first historical travel data).

[0083] Specifically, after the electronic device obtains multiple first proportions corresponding to multiple reference excess rate thresholds, it can determine a first proportion (called a third proportion) corresponding to the mileage range from at least one first proportion corresponding to each reference excess rate threshold for each mileage range in at least one mileage range, and then obtain multiple third proportions corresponding to the mileage range and corresponding to the multiple reference excess rate thresholds one by one. The electronic device then determines a preset excess rate threshold from multiple reference excess rate thresholds based on the multiple third proportions corresponding to each mileage range in at least one mileage range. Among them, the third proportions corresponding to the preset excess rate threshold in the multiple third proportions corresponding to different mileage ranges are all smaller than the first preset ratio.

[0084] The value of the first preset ratio can ensure that the first excess rate corresponding to most normal historical travel data within different mileage ranges is less than the preset excess rate threshold. For example, the first preset ratio is 2%, 3%, 4% or 5%, etc.

[0085] Exemplarily, the electronic device may sort the multiple third proportions corresponding to each mileage range in at least one mileage range in descending order to obtain multiple third proportions in descending order. Then, the electronic device may determine a preset excess rate threshold starting from the starting position of all the multiple third proportions in descending order corresponding to the at least one mileage range. The preset excess rate threshold corresponds to a third proportion in all the multiple third proportions in descending order that is less than the first preset ratio.

[0086] In some embodiments, in addition to determining the preset excess rate threshold based on multiple first proportions corresponding to multiple normal historical travel data, the electronic device may also determine the preset excess rate threshold in combination with multiple abnormal historical travel data.

[0087] Specifically, the electronic device can obtain multiple abnormal historical travel data. An abnormal historical travel data may include: a second starting point position and a second end point position, and the length of the abnormal historical travel track. The electronic device then determines the length of the second planned path according to the second starting point position and the second end point position for each abnormal historical travel data in the multiple abnormal historical travel data. The electronic device can also determine the second excess rate for each abnormal historical travel data in the multiple abnormal historical travel data; the second excess rate is the excess rate of the length of the abnormal historical travel track compared to the length of the second planned path. Then, the electronic device can count at least one second proportion corresponding to the reference excess rate threshold for each reference excess rate threshold. Finally, the electronic device can determine a preset excess rate threshold from multiple reference excess rate thresholds according to multiple first proportions corresponding to multiple reference excess rate thresholds and multiple second proportions corresponding to multiple reference excess rate thresholds; the first proportion corresponding to the preset excess rate threshold is less than the second proportion corresponding to the preset excess rate threshold.

[0088] The second planned path is the path from the second starting position to the second end position on the map. The second planned path is the actual path from the second starting position to the second end position, such as the second planned path is the actual path from the second starting position to the second end position on the map.

[0089] Among them, each second proportion in at least one second proportion is the proportion of the number of fourth historical travel data with a second excess rate greater than a reference excess rate threshold in the number of multiple third historical travel data in the same mileage range. At least one second proportion corresponds to a different mileage range. Multiple third historical travel data belong to multiple abnormal historical travel data; and the fourth historical travel data belongs to multiple third historical travel data.

[0090] The electronic device can determine the length of the second planned path for each abnormal historical travel data; then subtract the length of the second planned path from the length of the abnormal historical travel track in the normal historical travel data, and divide the difference by the length of the second planned path to obtain a second excess rate. Furthermore, the electronic device can obtain multiple second excess rates corresponding to multiple abnormal historical travel data.

[0091] It can be understood that, since the second proportion corresponding to a reference excess rate threshold represents the proportion of the fourth historical travel data with a second excess rate greater than the reference excess rate threshold in the multiple third historical travel data within the same mileage range, and the multiple third historical travel data and the fourth historical travel data are all abnormal historical travel data, then the larger the second proportion, the more abnormal historical travel data with a second excess rate greater than the reference excess rate threshold, that is, the second excess rate corresponding to more abnormal historical travel data is greater than the reference excess rate threshold. Then, if the reference excess rate threshold corresponding to a larger second proportion is determined as the preset excess rate threshold, the preset excess rate threshold can be used to identify more travel data with abnormal driving trajectories. Therefore, the electronic device can determine the reference excess rate threshold corresponding to the larger second proportion as the preset excess rate threshold. Then, according to the higher accuracy of the abnormal driving trajectory determined by the reference excess rate threshold corresponding to the smaller first proportion, the electronic device can determine the reference excess rate threshold corresponding to the smaller first proportion and the larger second proportion as the preset excess rate threshold.

[0092] Specifically, after the electronic device obtains multiple first proportions corresponding to multiple reference excess rate thresholds and multiple second proportions corresponding to multiple reference excess rate thresholds, for each mileage range in at least one mileage range, a first proportion (called a third proportion) corresponding to the mileage range is determined from at least one first proportion corresponding to each reference excess rate threshold, and a second proportion (called a fourth proportion) corresponding to the mileage range is determined from at least one second proportion corresponding to each reference excess rate threshold. Then, multiple third proportions corresponding to the mileage range and corresponding to multiple reference excess rate thresholds one by one, and multiple fourth proportions corresponding to the mileage range and corresponding to multiple reference excess rate thresholds one by one are obtained. The electronic device then determines a preset excess rate threshold from multiple reference excess rate thresholds based on the multiple third proportions corresponding to each mileage range in at least one mileage range and the multiple fourth proportions corresponding to each mileage range. Among them, the third proportions corresponding to the preset excess rate threshold in the multiple third proportions corresponding to different mileage ranges are all less than the first preset ratio, and the fourth proportions corresponding to the preset excess rate threshold in the multiple fourth proportions corresponding to different mileage ranges are all greater than the first preset ratio.

[0093] The first preset ratio is smaller than the second preset ratio.

[0094] The larger the second proportion is, the better, and the larger the second preset ratio is, the better. For example, the second preset ratio is 30%, 40% or 50%, etc.

[0095] Exemplarily, the electronic device may sort the multiple third proportions corresponding to each mileage range in at least one mileage range in descending order to obtain multiple third proportions in descending order. The electronic device also sorts the multiple fourth proportions corresponding to each mileage range in at least one mileage range in descending order to obtain multiple fourth proportions in descending order. Then, the electronic device may determine the preset excess rate threshold starting from the starting position of all the multiple third proportions in descending order corresponding to at least one mileage range and all the multiple fourth proportions in descending order corresponding to at least one mileage range. The third proportion corresponding to the preset excess rate threshold in all the multiple third proportions in descending order is less than the first preset ratio, and the fourth proportion corresponding to the preset excess rate threshold in all the multiple fourth proportions in descending order is greater than the second preset ratio.

[0096] In some embodiments, after obtaining multiple first excess rates, the electronic device may preprocess the multiple first excess rates to obtain the preprocessed first excess rates. Then, the electronic device counts at least one first proportion corresponding to each reference excess rate threshold in the multiple reference excess rate thresholds. At this time, each first proportion in the at least one first proportion is the proportion of the number of second historical travel data whose preprocessed first excess rate is greater than the reference excess rate threshold in the number of multiple first historical travel data within the same mileage range.

[0097] Similarly, the electronic device may also pre-process multiple second excess rates to obtain pre-processed second excess rates; and then calculate the second proportion for each reference excess rate threshold in multiple reference excess rate thresholds. At this time, each second proportion in at least one second proportion is the proportion of the number of fourth historical travel data whose pre-processed second excess rate is greater than the reference excess rate threshold in the number of multiple third historical travel data within the same mileage range.

[0098] The preprocessing may include: deleting the first excess rate and the second excess rate that are negative numbers, deleting the first excess rate and the second excess rate that are null values, and deleting the first excess rate and the second excess rate that are greater than an abnormal excess rate. The abnormal excess rate may be greater than 200%, for example, 400%.

[0099] It is understandable that, since the mileage in the normal historical travel data is less than the corresponding first planned path, the first excess rate is negative. Similarly, the second excess rate may also be negative. The electronic device can filter out the negative first excess rate and the second excess rate.

[0100] Secondly, the first excess rate corresponding to normal historical travel data is generally relatively small, such as the first excess rate is less than 100%. Unless the first starting point position collection in the normal historical travel data is abnormal and / or the first terminal position collection is abnormal, resulting in a large corresponding first excess rate. The large first excess rate caused by the abnormal first starting point position collection and the abnormal first terminal position collection cannot be used to determine the preset excess rate threshold, so the electronic device can delete these large first excess rates. By analyzing the abnormal historical travel data, it can be seen that the second excess rate corresponding to the abnormal historical travel data is usually greater than 200%. Therefore, the abnormal excess rate can be set to be greater than 200%. If the first excess rate and the second excess rate are greater than the abnormal excess rate, the electronic device can delete the first excess rate and the second excess rate that are greater than the abnormal excess rate.

[0101] In some embodiments, the plurality of normal historical travel data acquired by the electronic device may include: normal historical travel data with a driving track length (i.e., driving mileage) within a plurality of mileage ranges. The number of normal historical travel data with a driving mileage within each mileage range may be greater than the first number.

[0102] For example, the plurality of mileage ranges may include 3km-10km, 10km-20km, 20km-30km, 30km-40km, 40km-50km, 50km-60km, 60km-70km, 70km-80km, and greater than 80km. The first number may be equal to 1000.

[0103] It is understandable that the electronic device determines the first excess rate for normal historical travel data within multiple mileage ranges. Then the electronic device can obtain the first excess rate of the driving trajectory within different mileage ranges. If most of the first excess rates obtained by the electronic device are less than a reference excess rate threshold, it means that the first excess rates corresponding to most of the driving trajectories within multiple mileage ranges are less than the reference excess rate threshold. If the reference excess rate threshold is determined as a preset excess rate threshold, the preset excess rate threshold can be applicable to judging the driving trajectories within different mileage ranges.

[0104] Exemplarily, taking 10 reference exceedance rate thresholds including 10%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, 90% and 100%, and 9 mileage ranges including 3km~10km, 10km~20km, 20km~30km, 30km~40km, 40km~50km, 50km~60km, 60km~70km, 70km~80km and greater than 80km as an example, the electronic device can first obtain 1268 abnormal historical travel data. The electronic device also obtains 1563 normal historical travel data with a mileage of 3km to 10km, 1818 normal historical travel data with a mileage of 10km to 20km, 1933 normal historical travel data with a mileage of 20km to 30km, 1960 normal historical travel data with a mileage of 30km to 40km, 1951 normal historical travel data with a mileage of 40km to 50km, 1956 normal historical travel data with a mileage of 50km to 60km, 1942 normal historical travel data with a mileage of 60km to 70km, 1936 normal historical travel data with a mileage of 70km to 80km, and 1882 normal historical travel data with a mileage greater than 80km.

[0105] Then, the electronic device can determine the second excess rate for the 1268 abnormal historical travel data, and then count 10 second proportions corresponding to 10 reference excess rate thresholds based on the second excess rates corresponding to the 1268 abnormal historical travel data.

[0106] The electronic device can also determine the first excess rate for normal historical travel data with mileages of 3km to 10km, 10km to 20km, 20km to 30km, 30km to 40km, 40km to 50km, 50km to 60km, 60km to 70km, 70km to 80km, and greater than 80km. The electronic device then counts 10 first proportions corresponding to each mileage range and corresponding to 10 reference excess rate thresholds (which can be referred to as 10 first proportions corresponding to each mileage range) based on the first excess rate corresponding to the normal historical travel data within each mileage range.

[0107] The 10 first proportions corresponding to the normal historical travel data within each mileage range and the 10 second proportions corresponding to the abnormal historical travel data of the mileage obtained by the electronic device are shown in Table 1 below.

[0108] Table 1

[0109]

[0110] It can be seen that the larger the reference excess rate threshold is, the smaller the 10 first proportions corresponding to different mileage ranges are. Therefore, the electronic device can determine a larger reference excess rate threshold as the preset excess rate threshold, and the first proportion corresponding to the preset excess rate threshold in the 10 first proportions corresponding to different mileage ranges is relatively small. The first proportion represents the proportion of normal historical travel data with a first excess rate greater than the reference excess rate threshold in multiple normal historical travel data. It can be seen that the smaller first proportion corresponding to different mileage ranges means that the first excess rate corresponding to most of the driving trajectories within different mileage ranges is less than the preset excess rate threshold. In other words, the preset excess rate threshold is suitable for judging driving trajectories within multiple mileage ranges.

[0111] Secondly, when a larger reference excess rate threshold is equal to 80%, 90% or 100%, the first proportion corresponding to normal historical travel data is relatively small, indicating that there are few normal historical travel data with a first excess rate greater than the larger reference excess rate threshold. However, the second proportion corresponding to abnormal historical travel data is still relatively large, that is, there are still many abnormal historical travel data with a second excess rate greater than the reference excess rate threshold. Then, if the larger reference excess rate threshold is set as the preset excess rate threshold, more abnormal driving trajectories can be identified through the preset excess rate threshold.

[0112] In addition, since the first excess rate of the mileage in normal historical travel data is smaller than the length of the corresponding first planned path, the first planned path (such as the planned path from the starting point to the end point on the map) can be used as a reference value to compare the mileage in the travel data.

[0113] In some embodiments, since the length of abnormal driving trajectories is relatively long, the electronic device may first determine whether the length of a driving trajectory in a travel data is relatively long. If the length of the driving trajectory is relatively long, it indicates that the driving trajectory is likely to be abnormal, and then the above S202-S204 is continued to be executed to further determine whether the driving trajectory is abnormal.

[0114] Specifically, Figure 5 As shown, the method provided in the embodiment of the present application may further include S301 before S202.

[0115] S301. The electronic device determines whether the length of the driving track is greater than a preset mileage threshold.

[0116] The preset mileage threshold is determined based on a plurality of abnormal historical driving trajectories. If the length of the driving trajectory is greater than the preset mileage threshold, the electronic device may execute S202. If the length of the driving trajectory is less than or equal to the preset mileage threshold, the electronic device may not execute S202.

[0117] In some embodiments, after the electronic device obtains the lengths of multiple second planned paths corresponding to multiple abnormal historical driving trajectories, it can average or take the minimum value of the lengths of the multiple second planned paths to obtain a preset mileage threshold.

[0118] In some embodiments, since the initiator of calling a vehicle in the travel data with abnormal driving trajectory is most likely to be an enterprise, the electronic device can first determine whether the initiator of calling a vehicle in a travel data is an enterprise. If the initiator of calling a vehicle in the travel data is an enterprise, it means that the driving trajectory of the travel data is likely to be abnormal, and then continue to execute the above S202-S204 to further determine whether the driving trajectory is abnormal.

[0119] Specifically, the travel data may also include: information about the initiator of calling the vehicle. Figure 5 As shown, the method provided in the embodiment of the present application may further include S302 before S202.

[0120] S302: The electronic device determines whether the initiating object represented by the initiating object information is a preset object.

[0121] The preset object may include: an enterprise. If the initiating object belongs to the preset object, the electronic device may execute S202. If the initiating object does not belong to the preset object, the electronic device may not execute S202.

[0122] It should be noted that the electronic device may execute S301 first and then S302, or execute S302 first and then S301. The embodiment of the present application does not limit the order of executing S301 and S302.

[0123] In some embodiments, after determining that the driving trajectory in the travel data is abnormal, the electronic device can also count the number of abnormal driving trajectories of the driver in the travel data. If the total number of abnormal driving trajectories is greater than or equal to the preset number, it means that the driver has a large number of abnormal driving trajectories and needs to be paid special attention to. Furthermore, the electronic device can issue a prompt message to prompt the driver to pay special attention to the driver.

[0124] Specifically, the travel data also includes driver information. Figure 5 As shown, the method provided in the embodiment of the present application may further include S303-S304 after S204.

[0125] S303: The electronic device counts the number of abnormal driving trajectories of the driver indicated by the driver information within a preset time period based on the driver information.

[0126] The electronic device counts the number of abnormal driving trajectories of the driver within a preset time period, and determines whether the number of abnormal driving trajectories is greater than a preset number of times. If the number of abnormal driving trajectories is greater than the preset number of times, the electronic device executes S304 and issues a prompt message. If the number of abnormal driving trajectories is less than or equal to the preset number of times, the electronic device may not issue a prompt message. In addition, the electronic device may also save the travel data of the abnormal driving trajectory.

[0127] S304: If the number of abnormal driving trajectories is greater than a preset number, the electronic device sends a prompt message.

[0128] The prompt information indicates that the driving track of the driver indicated by the driver information is abnormal. The electronic device can display the prompt information through a display screen, or play the prompt information through voice, etc.

[0129] The preset number of times and the preset duration are related. The longer the preset duration, the greater the preset number of times. Both the preset duration and the preset number of times can be indicated by the above-mentioned first operation.

[0130] The prompt information may include the specific content of the driver's travel data with abnormal driving trajectory within a preset time period, the number of travel data with abnormal driving trajectory, etc.

[0131] It is understandable that in order to exclude that a driver's abnormal driving trajectory occurs once or several times by chance, a preset number of abnormal driving trajectories within a preset time period can be set. If a driver's abnormal driving trajectory occurs more than the preset number of times within a preset time period, it can be confirmed that the driver intentionally tampered with the driving trajectory, and the electronic device can issue a prompt message.

[0132] It should be noted that, in addition to counting the number of abnormal driving trajectories based on the driver as the dimension, the electronic device can also count the number of abnormal driving trajectories based on the vehicle as the dimension. The process of the electronic device counting the number of abnormal driving trajectories based on the vehicle as the dimension can refer to the specific introduction of counting the number of abnormal driving trajectories based on the driver as the dimension, which will not be repeated in the embodiments of this application.

[0133] It should be noted that in the embodiment of the present application, the situation of "greater than a certain threshold value" is classified into one branch, and the situation of "less than or equal to" is classified into another branch. In actual implementation, the situation of "greater than or equal to a certain threshold value" can also be classified into one branch, and the situation of "less than" can be classified into another branch.

[0134] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. In order to achieve the above functions, it includes hardware structures and / or software modules corresponding to the execution of each function. It should be easy to realize that the technical goals in this field are combined with the units and algorithm steps of each example described in the embodiments disclosed in this article, and the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical goals can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0135] The present application also provides a device for identifying abnormal trajectories. Figure 6 , which is a schematic diagram of the structure of an abnormal trajectory recognition device 400 provided in an embodiment of the present application. The recognition device 400 may include: a data acquisition module 401, a planned path acquisition module 402 and an abnormality judgment module 403.

[0136] The data acquisition module 401 is used to acquire the travel data of the vehicle; the travel data includes: the starting position and the end position of the driving trajectory, and the length of the driving trajectory. The planned path acquisition module 402 is used to determine the length of the target planned path according to the starting position and the end position; the target planned path is the path from the starting position to the end position. The abnormality judgment module 403 is used to determine the excess rate of the length of the driving trajectory compared to the length of the target planned path; if the excess rate is greater than the preset excess rate threshold, the driving trajectory is determined to be abnormal.

[0137] In a possible implementation, the abnormality judgment module 403 is further used to: before determining the length of the target planned path according to the starting position and the end position, determine whether the length of the driving track is greater than a preset mileage threshold. The preset mileage threshold is determined based on multiple abnormal historical driving tracks. The planned path acquisition module 402 is specifically used to: if the length of the driving track is greater than the preset mileage threshold, determine the length of the target planned path according to the starting position and the end position.

[0138] In another possible implementation, the travel data also includes: information of the initiating object of calling the vehicle. The abnormality judgment module 403 is further used to: before determining the length of the target planned path according to the starting position and the end position, determine whether the initiating object represented by the initiating object information belongs to the preset object. The planned path acquisition module 402 is specifically used to: if the initiating object belongs to the preset object, determine the length of the target planned path according to the starting position and the end position.

[0139] In another possible implementation, the identification device 400 further includes: a threshold determination module 404 .

[0140] The data acquisition module 401 is also used to acquire multiple normal historical travel data. A normal historical travel data includes: a first starting point position and a first end point position, and the length of a normal historical driving trajectory. The planned path acquisition module 402 is also used to determine the length of the first planned path according to the first starting point position and the first end point position for each normal historical travel data in the multiple normal historical travel data. The threshold determination module 404 is used to: determine the first excess rate for each normal historical travel data in the multiple normal historical travel data; determine the preset excess rate threshold according to the multiple first excess rates corresponding to the multiple normal historical travel data.

[0141] The first planned path is a path from the first starting point to the first end point. The first excess rate is an excess rate of the length of the normal historical driving trajectory compared to the length of the first planned path.

[0142] In another possible implementation, the threshold determination module 404 is specifically used to: for each reference excess rate threshold among multiple reference excess rate thresholds, count at least one first proportion corresponding to the reference excess rate threshold; and determine a preset excess rate threshold from the multiple reference excess rate thresholds based on at least multiple first proportions corresponding to the multiple reference excess rate thresholds.

[0143] Among them, each first proportion in at least one first proportion is the proportion of the number of second historical travel data with a first excess rate greater than a reference excess rate threshold in the number of multiple first historical travel data within the same mileage range. At least one first proportion corresponds to a different mileage range; the multiple first historical travel data belong to multiple normal historical travel data.

[0144] In another possible implementation, the data acquisition module 401 is also used to acquire multiple abnormal historical travel data; one abnormal historical travel data includes: a second starting position and a second end position, and the length of the abnormal historical travel trajectory. The planned path acquisition module 402 is also used to determine the length of the second planned path according to the second starting position and the second end position for each abnormal historical travel data in the multiple abnormal historical travel data; the second planned path is the path from the second starting position to the second end position. The threshold determination module 404 is also used to: determine the second excess rate for each abnormal historical travel data in the multiple abnormal historical travel data; for each of the above-mentioned reference excess rate thresholds, count at least one second proportion corresponding to the reference excess rate threshold; determine a preset excess rate threshold from the multiple reference excess rate thresholds according to the multiple first proportions corresponding to the multiple reference excess rate thresholds and the multiple second proportions corresponding to the multiple reference excess rate thresholds;

[0145] Among them, the second planned path is the path from the second starting point position to the second end point position. The second excess rate is the excess rate of the length of the abnormal historical driving trajectory compared to the length of the second planned path. Each second proportion in at least one second proportion is the proportion of the number of fourth historical travel data with a second excess rate greater than the reference excess rate threshold in the number of multiple third historical travel data within the same mileage range. At least one second proportion corresponds to a different mileage range. Multiple third historical travel data belong to multiple abnormal historical travel data; the first proportion corresponding to the preset excess rate threshold is less than the second proportion corresponding to the preset excess rate threshold.

[0146] Of course, the abnormal trajectory identification device 400 provided in the embodiment of the present application includes but is not limited to the above modules.

[0147] Another embodiment of the present application also provides an electronic device. Figure 7As shown, the electronic device 500 includes a memory 501 and a processor 502; the memory 501 and the processor 502 are coupled; the memory 501 is used to store computer program codes, and the computer program codes include computer instructions. When the processor 502 executes the computer instructions, the electronic device 500 executes each step executed by the electronic device in the method flow shown in the above method embodiment.

[0148] In actual implementation, the data acquisition module 401, the planning path acquisition module 402, the abnormality judgment module 403 and the threshold determination module 404 can be composed of Figure 7 The processor 502 shown is implemented by calling the computer program code in the memory 501. The specific execution process can refer to the description of the above-mentioned abnormal trajectory identification method part, which will not be repeated here.

[0149] Another embodiment of the present application further provides a computer-readable storage medium, which stores computer instructions. When the computer instructions are executed on an electronic device, the electronic device executes each step executed by the electronic device in the method flow shown in the above method embodiment.

[0150] Another embodiment of the present application also provides a chip system, which is applied to an electronic device. The chip system includes one or more interface circuits and one or more processors. The interface circuit and the processor are interconnected by a line. The interface circuit is used to receive a signal from a memory of the electronic device and send the signal to the processor, wherein the signal includes a computer instruction stored in the memory. When the processor of the electronic device executes the computer instruction, the electronic device executes each step performed by the electronic device in the method flow shown in the above method embodiment.

[0151] In another embodiment of the present application, a computer program product is provided. The computer program product includes computer instructions. When the computer instructions are executed on an electronic device, the electronic device executes each step executed by the electronic device in the method flow shown in the above method embodiment.

[0152] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using a software program, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loading and executing computer execution instructions on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server, data center, etc. that contains one or more servers that can be integrated with a medium. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium (eg, a solid state disk (SSD)).

[0153] The above is only a specific implementation of the present application. Those skilled in the art may conceive of changes or substitutions based on the specific implementation provided by the present application, which should all be included in the protection scope of the present application.

Claims

1. A method for identifying abnormal trajectories, characterized in that: The method comprises: Acquire travel data of the vehicle; the travel data includes: the starting position and the end position of the driving track, and the length of the driving track; Determine the length of the target planning path according to the starting position and the end position; the target planning path is the path from the starting position to the end position; Determining the excess rate of the length of the driving trajectory compared to the length of the target planned path; If the excess rate is greater than a preset excess rate threshold, the driving trajectory is determined to be abnormal, wherein the preset excess rate threshold is determined from multiple reference excess rate thresholds based on at least one first proportion corresponding to each reference excess rate threshold; each first proportion in the at least one first proportion corresponds to a mileage range, and the first proportion is the proportion of historical travel data in the first historical travel data whose excess rate is greater than the reference excess rate threshold corresponding to the first proportion; the first historical travel data is historical travel data within the mileage range corresponding to the first proportion among multiple normal historical travel data.

2. The method according to claim 1, characterized in that Before determining the length of the target planning path according to the starting position and the end position, the method further includes: Determining whether the length of the driving track is greater than a preset mileage threshold; the preset mileage threshold is determined based on a plurality of abnormal historical driving tracks; Wherein, determining the length of the target planning path according to the starting point position and the end point position includes: If the length of the driving trajectory is greater than the preset mileage threshold, the length of the target planned path is determined according to the starting position and the end position.

3. The method according to claim 1, characterized in that The travel data also includes: information about the initiator of calling the vehicle; Before determining the length of the target planning path according to the starting position and the end position, the method further includes: Determining whether the initiating object represented by the initiating object information belongs to a preset object; Wherein, determining the length of the target planning path according to the starting point position and the end point position includes: If the initiating object belongs to the preset object, the length of the target planned path is determined according to the starting point position and the end point position.

4. The method according to any one of claims 1 to 3, characterized in that The method further comprises: Acquire a plurality of normal historical travel data; one of the normal historical travel data includes: a first starting point position and a first end point position, and a length of a normal historical driving track; For each normal historical travel data among the plurality of normal historical travel data, determining the length of a first planned path according to the first starting point position and the first end point position; the first planned path is a path from the first starting point position to the first end point position; For each normal historical travel data among the plurality of normal historical travel data, an excess rate of the length of the normal historical driving trajectory compared with the length of the first planned path is determined.

5. The method according to claim 4, characterized in that The method further comprises: For each reference excess rate threshold among the multiple reference excess rate thresholds, at least one first proportion corresponding to the reference excess rate threshold is counted.

6. The method according to claim 1, characterized in that The method further comprises: Acquire a plurality of abnormal historical travel data; one of the abnormal historical travel data includes: a second starting point position and a second end point position, and a length of the abnormal historical travel track; For each abnormal historical travel data among the plurality of abnormal historical travel data, determining the length of a second planned path according to the second starting position and the second end position; the second planned path is a path from the second starting position to the second end position; For each abnormal historical travel data among the plurality of abnormal historical travel data, a second excess rate is determined; the second excess rate is an excess rate of the length of the abnormal historical travel trajectory compared to the length of the second planned path; For each reference excess rate threshold, at least one second proportion corresponding to the reference excess rate threshold is counted; wherein each second proportion in the at least one second proportion is the proportion of the number of fourth historical travel data having a second excess rate greater than the reference excess rate threshold in the number of the plurality of third historical travel data within the same mileage range; the at least one second proportion corresponds to different mileage ranges; the plurality of third historical travel data belong to the plurality of abnormal historical travel data; The preset excess rate threshold is determined from the multiple reference excess rate thresholds based on at least one first proportion corresponding to each reference excess rate threshold and at least one second proportion corresponding to each reference excess rate threshold; the first proportion corresponding to the preset excess rate threshold is smaller than the second proportion corresponding to the preset excess rate threshold.

7. An abnormal trajectory recognition device, characterized in that: The identification device comprises: A data acquisition module, used to acquire the travel data of the vehicle; the travel data includes: the starting position and the end position of the driving track, and the length of the driving track; A planned path acquisition module, used to determine the length of a target planned path according to the starting position and the end position; the target planned path is a path from the starting position to the end position; An abnormality judgment module is used to determine the excess rate of the length of the driving trajectory compared to the length of the target planned path; if the excess rate is greater than a preset excess rate threshold, the driving trajectory is determined to be abnormal, wherein the preset excess rate threshold is determined from multiple reference excess rate thresholds based on at least one first proportion corresponding to each reference excess rate threshold; each first proportion of the at least one first proportion corresponds to a mileage range, and the first proportion is the proportion of historical travel data in the first historical travel data whose excess rate is greater than the reference excess rate threshold corresponding to the first proportion; the first historical travel data is historical travel data within the mileage range corresponding to the first proportion among multiple normal historical travel data.

8. The device according to claim 7, characterized in that The abnormality judgment module is further used to: before determining the length of the target planned path according to the starting position and the end position, judge whether the length of the driving track is greater than a preset mileage threshold; the preset mileage threshold is determined according to a plurality of abnormal historical driving tracks; The planned path acquisition module is specifically used to: if the length of the driving trajectory is greater than the preset mileage threshold, determine the length of the target planned path according to the starting position and the end position; The travel data also includes: information of the initiating object of calling the vehicle; the abnormality judgment module is further used to: before determining the length of the target planned path according to the starting position and the end position, determine whether the initiating object represented by the initiating object information belongs to the preset object; the planned path acquisition module is specifically used to: if the initiating object belongs to the preset object, determine the length of the target planned path according to the starting position and the end position; The identification device also includes a threshold determination module; The data acquisition module is further used to acquire a plurality of normal historical travel data; one of the normal historical travel data includes: a first starting point position and a first end point position, and the length of a normal historical travel track; the planned path acquisition module is further used to determine the length of a first planned path according to the first starting point position and the first end point position for each normal historical travel data in the plurality of normal historical travel data; the first planned path is a path from the first starting point position to the first end point position; The threshold determination module is used to: determine, for each normal historical travel data among the plurality of normal historical travel data, an excess rate of the length of the normal historical travel trajectory compared to the length of the first planned path; The threshold determination module is specifically used to: for each reference excess rate threshold among the multiple reference excess rate thresholds, count at least one first proportion corresponding to the reference excess rate threshold; The data acquisition module is further used to acquire a plurality of abnormal historical travel data; one of the abnormal historical travel data includes: a second starting position and a second end position, and the length of an abnormal historical travel trajectory; the planned path acquisition module is further used to determine the length of a second planned path according to the second starting position and the second end position for each abnormal historical travel data in the plurality of abnormal historical travel data; the threshold determination module is further used to: determine a second excess rate for each abnormal historical travel data in the plurality of abnormal historical travel data; for each of the above-mentioned reference excess rate thresholds, count at least one second proportion corresponding to the reference excess rate threshold; determine the preset excess rate threshold from the plurality of reference excess rate thresholds according to at least one first proportion corresponding to each reference excess rate threshold and at least one second proportion corresponding to each reference excess rate threshold; Among them, the second planned path is the path from the second starting point position to the second end point position; the second excess rate is the excess rate of the length of the abnormal historical driving trajectory compared to the length of the second planned path; each of the at least one second proportions is the proportion of the number of fourth historical travel data with a second excess rate greater than the reference excess rate threshold in the number of the multiple third historical travel data within the same mileage range; the at least one second proportion corresponds to different mileage ranges; the multiple third historical travel data belong to the multiple abnormal historical travel data; the first proportion corresponding to the preset excess rate threshold is smaller than the second proportion corresponding to the preset excess rate threshold.

9. An electronic device, characterized in that: The electronic device comprises a memory and a processor; the memory and the processor are coupled; the memory is used to store computer program code, and the computer program code comprises computer instructions; When the processor executes the computer instructions, the electronic device executes the abnormal trajectory identification method as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed on an electronic device, the electronic device executes the abnormal trajectory recognition method according to any one of claims 1 to 6.

Images