Method, apparatus, electronic device, and storage medium for identifying abnormal trajectories

Abstract

The present application provides a method, apparatus, electronic device and storage medium for identifying abnormal trajectories, relating to the technical field of information processing, which can accurately identify abnormal driving trajectories. The specific solution includes: obtaining travel data of a vehicle; the travel data includes: the collection locations and collection times of multiple trajectory points in the driving trajectory; the multiple trajectory points include the end point of the driving trajectory; respectively determining the distances between each of the multiple trajectory points and the end point according to the collection locations of the multiple trajectory points; judging whether the driving trajectory meets the trajectory abnormal condition according to the multiple distances and the collection times of the multiple trajectory points; the trajectory abnormal condition is used to characterize that the driving trajectory includes an abnormal fluctuation indicating that the vehicle is moving away from the end point; if the driving trajectory meets the abnormal fluctuation condition, that is, the trajectory abnormal condition, it is determined 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 service platform. Then, the online ride-hailing service 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 of travel data in order to increase the driving fee. The online ride-hailing service then reports the tampered driving trajectory. The mileage determined by the online ride-hailing service platform based on the tampered mileage is also inconsistent with the actual mileage, so the driving fee calculated based on the mileage exceeds the actual driving fee.

[0003] The relevant scheme obtains the recommended driving path corresponding to each travel data for each trip data; then compares the driving trajectory reported by the online car-hailing vehicle with the recommended driving path to determine whether the driving trajectory is abnormal. However, in some cases, such as poor road conditions and passenger-specified routes, there is a deviation between the actual driving trajectory of the online car-hailing vehicle and the recommended driving path. Therefore, it is impossible to accurately determine whether the driving trajectory of the online car-hailing vehicle is abnormal using the recommended driving path. 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 acquiring travel data of a vehicle; then determining the distance between each of the multiple trajectory points and the end point based on the collection positions of the multiple trajectory points; then, judging whether the driving trajectory meets the trajectory abnormality condition based on the multiple distances and the collection time of the multiple trajectory points; the trajectory abnormality condition is used to characterize the driving trajectory, including characterizing abnormal fluctuations of the vehicle away from the end point; if the driving trajectory meets the trajectory abnormality condition, the driving trajectory is determined to be abnormal.

[0007] The travel data includes: the collection positions and collection times of multiple track points in the driving track. The multiple track points include the end point of the driving track.

[0008] It can be understood that when a network car-hailing service tampers with the driving trajectory, it usually adds a section of trajectory that the vehicle has not traveled in the real driving trajectory, or replays a certain section of the real driving trajectory. Whether adding a section of trajectory that the vehicle has not traveled or replaying a certain section of the real trajectory will result in abnormal fluctuations in the tampered driving trajectory (i.e., the abnormal driving trajectory) where the vehicle moves away from the end point after approaching it. Therefore, in the embodiments of the present application, for each trajectory point in the driving trajectory of the vehicle, the distance between the trajectory point and the end point of the driving trajectory can be determined; then, based on the multiple distances corresponding to the multiple trajectory points, it can be determined whether there are abnormal fluctuations in the driving trajectory where the vehicle moves away from the end point. Finally, based on the abnormal fluctuations in the driving trajectory where the vehicle moves away from the end point, it can be accurately determined whether the driving trajectory is abnormal.

[0009] Secondly, by using the method provided in the embodiments of the present application, it is not necessary to use the recommended driving route, and it is possible to determine whether the driving trajectory in the travel data is abnormal only based on the travel data. The implementation requirements of this method are simpler.

[0010] In a possible implementation manner, the above determination of whether the driving trajectory meets the trajectory abnormality condition based on the multiple distances and the collection times of the multiple trajectory points includes: arranging the multiple distances in the order of the collection times of the multiple trajectory points to obtain the arranged multiple distances; determining the peaks and valleys in the arranged multiple distances; determining, based on the peaks, valleys, and the collection times of the multiple trajectory points, the reference value corresponding to each peak in the peaks; the reference value is used to characterize whether each peak belongs to an abnormal peak; and determining whether the driving trajectory meets the trajectory abnormality condition based on the determined reference value.

[0011] In this design manner, a specific implementation manner of an electronic device for determining whether a driving trajectory meets the trajectory abnormality condition based on multiple distances and the collection times of multiple trajectory points is described.

[0012] In another possible implementation manner, the above determination of the reference value corresponding to each peak in the peaks based on the peaks, valleys, and the collection times of the multiple trajectory points includes: for the first peak, determining the difference between the first peak and the previous valley as the reference value corresponding to the first peak.

[0013] Wherein, the first peak is any one of the peaks. The previous valley is the valley among at least one valley that is before the first peak and adjacent to the first peak.

[0014] It can be understood that during the normal driving process of the vehicle, due to the winding of the road, some fluctuations from approaching the end point to moving away from the end point will occur. Moreover, this fluctuation (i.e., the fluctuation between the previous trough corresponding to a wave peak and this wave peak) is very small. In addition, the vehicle turning around may also cause fluctuations from approaching the end point to moving away from the end point, and this fluctuation is also relatively small. That is to say, during the normal driving process of the vehicle, there will also be some fluctuations from approaching the end point to moving away from the end point, and this fluctuation is small. Therefore, the electronic device can first determine the difference between the first wave peak and the previous trough corresponding to it as the reference value corresponding to this first wave peak. Then, for the reference value corresponding to the first wave peak, a preset distance threshold is set to determine whether the reference value corresponding to the first wave peak is generated by some fluctuations from approaching the end point to moving away from the end point caused by normal situations (including winding roads and vehicle turning around). If the reference value corresponding to the first wave peak is caused by the above normal situations, it cannot be used to judge the abnormality of the driving trajectory. If the reference value corresponding to the first wave peak is not caused by the above normal situations, it can be used to determine that the driving trajectory is abnormal.

[0015] In another possible implementation manner, the above-mentioned judging whether the driving trajectory meets the trajectory abnormality condition according to the determined reference value includes: counting the number of reference values greater than or equal to the preset distance threshold among the determined reference values; and judging whether the driving trajectory meets the trajectory abnormality condition according to this number.

[0016] It can be understood that if the preset distance threshold is set to be small, the reference values generated by the fluctuations caused by normal situations (including winding roads and vehicle turning around) may also be counted. Therefore, the electronic device also needs to consider the number of reference values greater than or equal to this preset distance threshold in order to more accurately judge whether the driving trajectory meets the trajectory abnormality condition.

[0017] Secondly, if the preset distance threshold is set to be large, and the reference values generated by the fluctuations caused by this normal situation are all small. Then, if there is a reference value greater than this preset distance threshold, it can be determined that this reference value is caused by adding a section of trajectory that the vehicle has not driven through or replaying a section of trajectory. That is to say, at least one reference value greater than this preset distance threshold can determine that the driving trajectory meets the trajectory abnormality condition.

[0018] In another possible implementation, determining whether the driving trajectory meets the trajectory anomaly condition based on at least one difference value includes: counting the number of first reference values greater than or equal to the first distance threshold among the determined reference values; if the number of first reference values is greater than or equal to the first number, determining that the driving trajectory meets the trajectory anomaly condition; and / or counting the number of second reference values greater than or equal to the second distance threshold among the determined reference values; if the number of second reference values is greater than or equal to the second number, determining that the driving trajectory meets the trajectory anomaly condition. Wherein, the second distance threshold is greater than the first distance threshold, and the second number is less than the first number.

[0019] It can be understood that if the preset distance threshold is set to be small (e.g., the first distance threshold), the reference values of the first peak generated by fluctuations caused by one or several normal situations may also be counted. Therefore, the electronic device can set a preset number threshold greater than 1 (e.g., the first number), and only when the counted number is greater than or equal to the first number, determine that the driving trajectory meets the trajectory anomaly condition.

[0020] Secondly, if the preset distance threshold is set to be large (e.g., the second distance threshold), and the reference values of the first peak generated by the fluctuations caused by the above normal situations are all small, then if a reference value is greater than the second distance threshold, it can be determined that this reference value is caused by adding a section of the trajectory that the vehicle has not traveled or replaying a section of the trajectory. Furthermore, the electronic device can set the preset number threshold to be equal to 1 or close to 1 (e.g., the second number), that is, if at least one reference value with one first peak is greater than the second distance threshold, it is determined that the driving trajectory is abnormal.

[0021] In another possible implementation, the travel data further includes driver information. The method further includes: in the case of determining that the driving trajectory is abnormal, according to the driver information, counting the number of abnormal driving trajectories of the driver indicated by the driver information within a preset duration; then, if the number of abnormal driving trajectories is greater than or equal to a preset number of times, sending a prompt message. The prompt message indicates that the driving trajectory of the driver indicated by the driver information is abnormal.

[0022] It can be understood that in order to rule out the possibility that one or several abnormal driving trajectories of a driver occur accidentally, a preset number of times of abnormal driving trajectories within a preset duration can be set. If the number of times of abnormal driving trajectories of a driver within a preset duration exceeds the preset number of times, it can be confirmed that the driver intentionally tampers with the driving trajectory, and then the electronic device can send a prompt message. The prompt message is used to prompt to pay close attention to this driver.

[0023] In a second aspect, the present application provides an abnormal trajectory recognition device. The abnormal trajectory recognition device includes various modules for executing the method described in the first aspect or any one of the possible design manners in the first aspect.

[0024] In a third aspect, the present application provides an electronic device, which includes a memory and a processor. The above-mentioned memory and processor are coupled. The memory is used to store computer program code, and the computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device is caused to execute the abnormal trajectory recognition method as described in the first aspect and any one of its possible design manners.

[0025] In a fourth aspect, the present application provides a chip system, which is applied to the abnormal trajectory recognition device; the chip system includes one or more interface circuits and one or more processors. The interface circuits and the processors are interconnected by lines; the interface circuits are used to receive signals from the memory of the abnormal trajectory recognition device and send signals to the processors, and the signals include the computer instructions stored in the memory. When the processors execute the computer instructions, the electronic device is caused to execute the abnormal trajectory recognition method as described in the first aspect and any one of its possible design manners.

[0026] In a fifth aspect, the present application provides a computer-readable storage medium, which stores computer instructions. When the computer instructions run on an electronic device, the electronic device is caused to execute the abnormal trajectory recognition method as described in the first aspect and any one of its possible design manners.

[0027] In a sixth aspect, the present application provides a computer program product, which includes computer instructions. When the computer instructions run on an electronic device, the electronic device is caused to execute the abnormal trajectory recognition method as described in the first aspect and any one of its possible design manners.

[0028] For the specific descriptions of the second to sixth aspects and their various implementation manners in the present application, reference may be made to the detailed descriptions in the first aspect and its various implementation manners; and, for the beneficial effects of the second to sixth aspects and their various implementation manners, reference may be made to the analysis of the beneficial effects in the first aspect and its various implementation manners, which will not be elaborated here.

[0029] These aspects or other aspects of the present application will be more clearly understood in the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1A It is a schematic diagram of the first abnormal driving trajectory provided by an embodiment of the present application;

[0031] Figure 1B It is a schematic diagram of the second abnormal driving trajectory provided by an embodiment of the present application;

[0032] Figure 1C It is a schematic diagram of the third abnormal driving trajectory provided by the embodiment of the present application;

[0033] Figure 1D It is a schematic diagram of the fourth abnormal driving trajectory provided by the embodiment of the present application;

[0034] Figure 2 It is the first schematic diagram of the implementation environment involved in the abnormal trajectory recognition method provided by the embodiment of the present application;

[0035] Figure 3 It is the schematic diagram of the implementation environment involved in the abnormal trajectory recognition method provided by the embodiment of the present application Figure 2 ;

[0036] Figure 4 It is the schematic diagram of the implementation environment involved in the abnormal trajectory recognition method provided by the embodiment of the present application Figure 3 ;

[0037] Figure 5 It is the flowchart of the abnormal trajectory recognition method provided by the embodiment of the present application;

[0038] Figure 6 It is the distance change diagram of a normal driving trajectory and an abnormal driving trajectory provided by the embodiment of the present application;

[0039] Figure 7A It is the distance change diagram corresponding to the first abnormal driving trajectory provided by the embodiment of the present application;

[0040] Figure 7B It is the distance change diagram corresponding to the second abnormal driving trajectory provided by the embodiment of the present application;

[0041] Figure 7C It is the distance change diagram corresponding to the third abnormal driving trajectory provided by the embodiment of the present application;

[0042] Figure 7D It is the distance change diagram corresponding to the fourth abnormal driving trajectory provided by the embodiment of the present application;

[0043] Figure 8 It is the structural schematic diagram of an abnormal trajectory recognition device provided by the embodiment of the present application;

[0044] Figure 9 It is the structural schematic diagram of an electronic device provided by the embodiment of the present application. Detailed implementation manners

[0045] Hereinafter, terms such as "first" and "second" are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first", "second", etc. may explicitly or implicitly include one or more such features.

[0046] Currently, the rise and popularization of online car-hailing have brought great convenience to users' travel. However, there are some online car-hailing services that tamper with the driving track in the travel data to increase the driving mileage determined based on the tampered driving track. Thereby, the driving fee calculated based on this driving mileage can be increased. In order to identify the tampered driving track (which can be called an abnormal driving track), relevant solutions rely on the recommended driving track corresponding to the travel data to determine whether the reported driving track is abnormal. However, in some cases, for example, poor road conditions, passengers specifying routes, etc., there are deviations between the actual driving track of the online car-hailing and the recommended driving route itself. In view of these situations, it is impossible to accurately determine whether the driving track of the online car-hailing is abnormal using the recommended driving route.

[0047] In the embodiments of the present application, by analyzing some abnormal driving tracks, it can be found that when an online car-hailing tampers with the driving track, it usually adds a section of track that the vehicle has not traveled on the actual driving track or replays a section of the actual driving track. Among them, on the actual driving track of the vehicle, it is generally gradually approaching the end point from the starting point. If a section of track that the vehicle has not traveled is added outside the actual driving track close to the end point, this newly added track will include a track where the vehicle is moving away from the end point. Secondly, replaying a section of the traveled track is manifested as the vehicle traveling on this section of the track multiple times. When the vehicle actually travels on this section of the track for the first time, it is close to the end point, and when it travels on this section of the track for the second time, it is moving away from the end point.

[0048] In summary, whether adding a section of track that the vehicle has not traveled or replaying a section of the actual track will result in abnormal fluctuations in the tampered driving track (i.e., the abnormal driving track) where it moves away from the end point after approaching it.

[0049] Exemplarily, such as Figure 1AThe first abnormal driving trajectory shown. In the first abnormal driving trajectory, the vehicle starts from the starting point 101 and travels in the direction towards the end point 105 for a certain distance and reaches a trajectory point 102. Then, the vehicle changes its driving direction at the trajectory point 102 and travels in the direction away from the end point 105 until it reaches the trajectory point 103. The vehicle then changes its driving direction at the trajectory point 103 and travels again in the direction towards the end point 105 until it reaches the trajectory point 104. The vehicle then travels back from the trajectory point 104 to the trajectory point 103. Then, the vehicle makes a U-turn at the trajectory point 103, passes through the trajectory point 104, and reaches the end point 105.

[0050] It can be seen that when the vehicle travels from the starting point 101 to the trajectory point 102 in the direction towards the end point 105, it changes its driving direction at the trajectory point 102 and travels in the direction away from the end point 105. The trajectory from the trajectory point 102 to the trajectory point 103 is getting farther and farther away from the end point 105. The trajectory from the trajectory point 102 to the trajectory point 103 may be a trajectory that the vehicle has tampered with and has not actually traveled. Secondly, the vehicle travels from the trajectory point 103 to the trajectory point 104, then returns from the trajectory point 104 to the trajectory point 103, and then travels from the trajectory point 103 to the trajectory point 104 again. It can be determined that the vehicle replays the trajectory from the trajectory point 103 to the trajectory point 104 multiple times, and when the vehicle travels from the trajectory point 104 to the trajectory point 103, it is moving away from the end point 105.

[0051] Exemplarily, as Figure 1B The second abnormal driving trajectory shown. In the second abnormal driving trajectory, the vehicle starts from the starting point 111, passes through the trajectory points 112, 113, 114, and reaches the trajectory point 115. Then, the vehicle returns from the trajectory point 115 to the previously passed trajectory point 112, and then retraces the previously traveled path from this trajectory point 112, passes through the trajectory points 112, 113, 114, and reaches the trajectory point 115. Finally, the vehicle travels from the trajectory point 115 to the end point 116.

[0052] It can be seen that the vehicle returns from the trajectory point 115 to the previously passed trajectory point 112. When the vehicle travels from the trajectory point 115 to the trajectory point 112, it is getting farther and farther away from the end point 105. Then, the trajectory from the trajectory point 115 to the trajectory point 112 may be a trajectory that the vehicle has tampered with and has not actually traveled. Secondly, the vehicle repeatedly travels from the trajectory point 112, passes through the trajectory points 113 and 114, and reaches the trajectory point 115. That is to say, the trajectory from the trajectory point 112, passing through the trajectory points 113 and 114, and reaching the trajectory point 115 is replayed.

[0053] Exemplarily, as Figure 1CThe third abnormal driving trajectory shown. In the third abnormal driving trajectory, the vehicle starts from the starting point 121, passes through the trajectory points 122 and 123, and reaches the end point 124. The vehicle then turns around from the end point 124 and drives to the trajectory point 123, and from the trajectory point 123 to the trajectory point 122. The vehicle then drives from the trajectory point 122 to the trajectory point 123, and again from the trajectory point 123 to the trajectory point 122. Finally, the vehicle drives from the trajectory point 122, passes through the trajectory point 123, and reaches the end point 124.

[0054] It can be seen that after the vehicle reaches the end point 124, it drives back to the trajectory point 123 and then repeatedly drives on the trajectory section from the trajectory point 123 to the trajectory point 122. Among them, the trajectory that the vehicle drives after reaching the end point 124 may be all trajectories that the vehicle fabricates and has not driven. When the vehicle drives from the end point 124 to the trajectory point 123, it shows that the vehicle is moving away from the end point 124. When the vehicle repeatedly drives on the trajectory section from the trajectory point 123 to the trajectory point 122, it shows that the vehicle repeatedly moves away from and approaches the end point 124.

[0055] As Figure 1D shown in the fourth abnormal driving trajectory. In the fourth abnormal driving trajectory, the vehicle starts from the starting point 131, passes through the trajectory points 132 and 133, and reaches the end point 134. Then, the vehicle drives back from the end point 134 along the same trajectory to the starting point 131.

[0056] It can be seen that after the vehicle reaches the end point 134, it drives back to the starting point 131. The trajectory section from the end point 134 to the starting point 131 may be a trajectory fabricated by the vehicle and not driven. Moreover, when the vehicle drives back from the end point 134 to the starting point 131, it shows that the vehicle is always moving away from the end point 134.

[0057] Based on the above Figure 1A 、 Figure 1B 、 Figure 1C and Figure 1D shown several abnormal driving trajectories, it can be known that some trajectories fabricated by the vehicle and not driven cause at least one abnormal fluctuation of the vehicle moving away from the end point during the process of approaching the end point. Therefore, the embodiment of the present application provides a driving method for abnormal trajectories, which can determine the distance between each trajectory point in the driving trajectory of the vehicle and the end point of the driving trajectory; then, according to the multiple distances corresponding to the multiple trajectory points, determine whether there is an abnormal fluctuation of the vehicle moving away from the end point in the driving trajectory. Finally, according to the abnormal fluctuation of the vehicle moving away from the end point in the driving trajectory, it can be determined whether the driving trajectory is abnormal.

[0058] The following will describe in detail the implementation manners of the embodiments of the present application with reference to the accompanying drawings.

[0059] Please refer to Figure 2, which shows a schematic diagram of the implementation environment involved in a method for identifying abnormal trajectories provided by an embodiment of the present application. As Figure 2 shown, the implementation environment may include: a server 200, a terminal 210, and multiple collection devices 220 for collecting travel data of vehicles. Among them, the multiple collection devices 220 are respectively installed in different vehicles.

[0060] Exemplarily, each collection device 220 may include a GPS module, a timing module, and an input module (such as a touch screen). Figure 2 The GPS module, the timing module, and the input module in the collection module 220 are not shown in the figure. The GPS module is used to collect the longitude and latitude of multiple trajectory points in the driving trajectory. The timing module is used to record the collection time of multiple trajectory points. The input module is used to collect driver information, vehicle information, etc. input by the driver. Among them, the driving trajectory is composed of multiple trajectory points, and the collection positions of the multiple trajectory points in the driving trajectory can represent the complete driving trajectory. The multiple trajectory points include a starting point and an ending point.

[0061] The server 200 can receive the travel data of the vehicle from the collection device 220 in each vehicle. The travel data may include: the longitude and latitude and collection time of multiple trajectory points in the driving trajectory, driver information, and vehicle information, etc. The server 200 can also determine the driving mileage according to the longitude and latitude of the multiple trajectory points.

[0062] Specifically, as Figure 3 shown, the terminal 210 can receive a first operation input by the user, and the first operation is used to indicate a target area and a target vehicle type (such as a network car, a taxi), etc. Then, in response to the first operation, the terminal 210 can obtain the travel data of the vehicles driving in the target area and belonging to the target vehicle type from the server 200. The terminal 210 then determines the distance between each of the multiple trajectory points in the travel data and the ending point. Then, the terminal 210 determines whether the driving trajectory in the travel data is abnormal according to the multiple distances. If the driving trajectory is abnormal, a prompt message can be sent, and the prompt message is used to indicate that the driving trajectory of the vehicle is abnormal. For example, the terminal 210 can display the prompt message through a display screen.

[0063] Or, as Figure 4As shown, in response to the first operation, the terminal 210 may send target information including the target area and the target vehicle type, etc. to the server 200. The server 200 may obtain the travel data of vehicles traveling within the target area and belonging to the target vehicle type. The server 200 then determines the distance between each of the multiple trajectory points in the travel data and the end point. Then, the server 200 determines whether the travel trajectory in the travel data is abnormal based on the multiple distances. If the travel trajectory is abnormal, the server 200 may send the above prompt information to the terminal 210. The terminal 210 may issue the prompt information.

[0064] Exemplarily, the terminal 210 in the embodiments of the present application may be a mobile phone, a tablet computer, a desktop type, a laptop, a notebook computer, a netbook, etc. The embodiments of the present application do not impose special restrictions on the specific form of the terminal 210.

[0065] It should be noted that the method for identifying abnormal trajectories provided in the embodiments of the present application may be applied to the above-mentioned server 200, or may be applied to the above-mentioned terminal 210, or may be applied to both the above-mentioned server 200 and the terminal 210. The server 200 and the terminal 210 may be collectively referred to as electronic devices. The execution subject of the method for identifying abnormal trajectories provided in the embodiments of the present application may also be an abnormal trajectory identification device. The identification device may be an electronic device; or, the device may be an application program (APP) installed on the electronic device that provides the function of identifying abnormal trajectories; or, the device may be a Central Processing Unit (CPU) in the electronic device; or, the device may be a control module in the electronic device for executing the method for identifying abnormal trajectories.

[0066] Next, taking the electronic device as an example, the method for identifying abnormal trajectories provided in the embodiments of the present application will be described in detail.

[0067] Please refer to Figure 5 , which is a flowchart of a method for identifying abnormal trajectories provided in the embodiments of the present application. As Figure 5 shown, the method may include S501 - S504.

[0068] S501. The electronic device obtains the travel data of the vehicle; the travel data includes: the collection locations and collection times of multiple trajectory points in the travel trajectory; the multiple trajectory points include the end point of the travel trajectory.

[0069] The electronic device may 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 taxis.

[0070] Among them, the multiple trajectory points further include the starting point of the driving trajectory. The trajectory point with the earliest acquisition time among the multiple trajectory points is the starting point, and the trajectory point with the latest acquisition time is the ending point. The acquisition location of each trajectory point can be the longitude and latitude of the trajectory point.

[0071] Among them, the travel data may further include: the order identifier corresponding to the travel data, driver information, vehicle information, and so on. The vehicle information can be a vehicle identifier, such as a vehicle number, license plate number, etc.

[0072] S502. The electronic device determines the distances between each of the multiple trajectory points and the ending point respectively according to the acquisition locations of the multiple trajectory points.

[0073] The electronic device can calculate the distance between each trajectory point among the multiple trajectory points and the ending point, and thus obtain multiple distances. The multiple distances and the multiple trajectory points are in one-to-one correspondence.

[0074] In some embodiments, the acquisition locations of the multiple trajectory points can be longitude and latitude, then the electronic device can use a distance calculation formula to calculate the distance between each trajectory point and each other corresponding trajectory point. The distance calculation formula can include the haversine equation, Vincenty formula.

[0075] For example, the acquisition location of a trajectory point can include the longitude lon 1 and latitude lat 1 . The acquisition location of another trajectory point corresponding to this trajectory point can include the longitude lon 2 and latitude lat 2 . The electronic device can use the haversine equation to calculate the distance d haversine between this trajectory point and this other trajectory point. Among them, the haversine equation is shown as the following formula (1):

[0076]

[0077] Among them, r is the radius of the earth, with the unit of meter. Arcsin is the Arcsin function.

[0078] S503. The electronic device determines whether the driving trajectory meets the trajectory anomaly condition according to the multiple distances and the acquisition times of the multiple trajectory points; the trajectory anomaly condition is used to characterize that the driving trajectory includes an abnormal fluctuation indicating that the vehicle is moving away from the ending point.

[0079] The electronic device can arrange the multiple distances in the order of the acquisition times of the multiple trajectory points. The electronic device then determines whether the driving trajectory meets the trajectory anomaly condition according to the change situation of the arranged multiple distances.

[0080] In some embodiments, the electronic device may arrange multiple distances in the order of the acquisition times of multiple trajectory points to obtain the arranged multiple distances. The electronic device then determines the peaks and valleys among the arranged multiple distances. Then, the electronic device determines, according to the peaks, valleys, and the acquisition times of the multiple trajectory points, a reference value corresponding to each peak among the peaks. The reference value is used to characterize whether each peak belongs to an abnormal peak. Finally, the electronic device may determine whether the driving trajectory meets the trajectory abnormality condition according to the determined reference values.

[0081] The electronic device may determine that each inflection point where the order changes from ascending to descending among the arranged multiple distances is a peak, and each inflection point where the order changes from descending to ascending is a valley. Further, the electronic device may obtain at least one peak and at least one valley.

[0082] Among them, for the first peak, the electronic device may determine the difference between the first peak and the previous valley corresponding to the first peak as the reference value corresponding to the first peak. Among them, the first peak is any one of the determined peaks. The previous valley corresponding to the first peak is the valley among the at least one valley that is before the first peak and adjacent to the first peak.

[0083] Exemplarily, as Figure 6 shown in the distance change diagram of the normal driving trajectory in (a) of. The abscissa in the distance change diagram is the acquisition time of the trajectory point corresponding to each distance. It can be seen that among the arranged multiple distances obtained by the electronic device according to the normal driving trajectory, there are a first valley 611, a first peak 621, a second valley 612, and a second peak 622. The previous valley corresponding to the first peak 621 is the first valley 611. The previous valley corresponding to the second peak 622 is the second valley 612. Among them, the difference between the first peak 621 and the first valley 611 (i.e., the reference value corresponding to the first peak 621), and the difference between the second peak 622 and the second valley 612 (i.e., the reference value corresponding to the second peak 622) are both relatively small, both less than 1000 m. That is to say, the normal driving trajectory may also include some fluctuations from approaching the end point to moving away from the end point, and these fluctuations are all relatively small.

[0084] Secondly, referring again to Figure 6 the distance change diagram of the abnormal driving trajectory shown in (b) of. Figure 6 The normal driving trajectory shown in (a) of and Figure 6 the normal driving trajectory shown in (b) of are trajectories from the same starting point to the same end point. From Figure 6As can be seen from (b) in [description], among the multiple arranged distances obtained by the electronic device according to the normal driving trajectory, there are the first trough 631, the first peak 641, the second trough 632, the second peak 642, the third trough 633, the third peak 643, the fourth trough 634, the fourth peak 644, the fifth trough 635, the fifth peak 645, the sixth trough 636, and the sixth peak 646. The previous trough corresponding to the first peak 641 is the first trough 631. The previous trough corresponding to the second peak 642 is the second trough 632. The previous trough corresponding to the third peak 643 is the third trough 633. The previous trough corresponding to the fourth peak 644 is the fourth trough 634. The previous trough corresponding to the fifth peak 645 is the fifth trough 635. The previous trough corresponding to the sixth peak 646 is the sixth trough 636.

[0085] Among them, the differences between the first peak 641 and the first trough 631 (i.e., the reference value corresponding to the first peak 641), between the fourth peak 644 and the fourth trough 634 (i.e., the reference value corresponding to the fourth peak 644), between the fifth peak 645 and the fifth trough 635 (i.e., the reference value corresponding to the fifth peak 645), and between the sixth peak 646 and the sixth trough 646 (i.e., the reference value corresponding to the sixth peak 646) are all relatively large, all greater than 1000m. The differences between the second peak 642 and the second trough 632 (i.e., the reference value corresponding to the second peak 642), and between the third peak 643 and the third trough 643 (i.e., the reference value corresponding to the third peak 643) are all relatively small, all less than 1000m.

[0086] It can be understood that during the normal driving of the vehicle, due to the winding of the road, some fluctuations from approaching the end point to moving away from the end point will be caused. And this kind of fluctuation (such as the fluctuation between the above-mentioned first trough 611 and the first peak 621, and the fluctuation between the above-mentioned second trough 612 and the second peak 622) is very small. In addition, the vehicle turning around may also cause fluctuations from approaching the end point to moving away from the end point, and this kind of fluctuation is also small. That is to say, during the normal driving of the vehicle, there will also be some fluctuations from approaching the end point to moving away from the end point, and this kind of fluctuation is small. Therefore, the electronic device can set a preset distance threshold for the difference between the first peak and the previous trough corresponding to it (i.e., the reference value corresponding to the first peak) to judge whether the reference value corresponding to the first peak is caused by some fluctuations from approaching the end point to moving away from the end point under the above normal conditions (including road winding and vehicle turning around). If the reference value corresponding to the first peak belongs to the above normal situation, it cannot be used to judge the abnormality of the driving trajectory.

[0087] Specifically, in one embodiment, the electronic device may average the determined reference values to obtain an average value. Then, if the average value is greater than or equal to a preset value, the electronic device may determine that the driving trajectory meets the trajectory anomaly condition. If the average value is less than the preset value, the electronic device may determine that the driving trajectory does not meet the trajectory anomaly condition.

[0088] Among them, the preset value may be obtained by analyzing some abnormal driving trajectories. For example, the first preset value may be 1000m or 2000m, etc. The preset value may be indicated by the above first operation.

[0089] In another embodiment, the electronic device may count the number of reference values greater than or equal to a preset distance threshold among the determined reference values. Then, the electronic device may determine whether the driving trajectory meets the trajectory anomaly condition based on this number.

[0090] Among them, the electronic device may determine whether this number is not less than (i.e., greater than or equal to) a preset number threshold. If this number is not less than the preset number threshold, the electronic device may determine that the driving trajectory meets the trajectory anomaly condition. If this number is less than the preset number threshold, the electronic device may determine that the driving trajectory does not meet the trajectory anomaly condition. The preset distance threshold and the preset number threshold may be obtained by analyzing some abnormal driving trajectories. Both the preset distance threshold and the preset number threshold may be indicated by the above first operation.

[0091] Alternatively, the electronic device may determine the proportion of this number in the total number of determined reference values. If the proportion is greater than or equal to a preset ratio, the electronic device may determine that the driving trajectory meets the trajectory anomaly condition. If the proportion is less than the preset ratio, the electronic device may determine that the driving trajectory does not meet the trajectory anomaly condition. The preset ratio may be obtained by analyzing some abnormal driving trajectories. The preset ratio may be indicated by the above first operation.

[0092] In some embodiments, if the preset distance threshold is set to be small, the reference values of the first wave peaks generated by fluctuations caused by one or several normal situations may also be counted. Therefore, the electronic device may set a preset number threshold greater than 1, and only when the counted number is greater than or equal to the preset number threshold, determine that the driving trajectory meets the trajectory anomaly condition.

[0093] If the preset distance threshold is set to be relatively large, and the reference values of the first peaks generated by the fluctuations caused by the above normal conditions are all relatively small, and the reference value of the first peak is greater than the preset distance threshold, it can be determined that the reference value of the first peak is caused by adding a section of the trajectory that the vehicle has not traveled or replaying a section of the trajectory. Furthermore, the electronic device can set the preset number threshold to be equal to 1 (or close to 1), that is, if there is 1 reference value of the first peak greater than the preset distance threshold, it is determined that the driving trajectory is abnormal.

[0094] Specifically, the trajectory anomaly conditions may include a first anomaly condition and / or a second anomaly condition. The first anomaly condition may include a first distance threshold and a first number. The second anomaly condition includes a second distance threshold and a second number. Among them, the second distance threshold is greater than the first distance threshold, and the second number is less than the first number.

[0095] Furthermore, when the trajectory anomaly condition includes the first anomaly condition, the electronic device can count the number of first reference values that are greater than or equal to the first distance threshold among the determined reference values; if the number of first reference values is greater than or equal to the first number, it is determined that the driving trajectory meets the trajectory anomaly condition.

[0096] When the trajectory anomaly condition includes the second anomaly condition, the electronic device can count the number of second reference values that are greater than or equal to the second distance threshold among the determined reference values. If the number of second reference values is greater than or equal to the second number, it is determined that the driving trajectory meets the trajectory anomaly condition.

[0097] Among them, the first distance threshold is greater than 0, and the first number is greater than 1. The second distance threshold is greater than or equal to 1 / n of the total length, and the second number is greater than 0. The total length can be the driving mileage determined by the electronic device or the server (such as the above server 200) according to the driving trajectory, or the total length is the distance between the starting point and the ending point among multiple trajectory points. n is a number greater than 1.

[0098] For example, the first distance threshold is equal to 1000 meters (m), and the first number is equal to 3.

[0099] For example, the second distance threshold is equal to 1 / 2, 1 / 3, or 1 / 4 of the total length, and the second number is equal to 1.

[0100] S504. If the driving trajectory meets the trajectory anomaly condition, the electronic device determines that the driving trajectory is abnormal.

[0101] If the driving trajectory meets the trajectory anomaly condition, the electronic device determines that the driving trajectory is abnormal. If the driving trajectory meets the trajectory anomaly condition, the electronic device determines that the driving trajectory is normal.

[0102] Exemplarily, taking the total length as the distance between the starting point and the ending point among multiple trajectory points, the first distance threshold being equal to 1000 m, the first number being equal to 2, the second distance threshold being equal to 1 / 3 of the total length, and the second number being equal to 1 as examples, the electronic device respectively performs the above-mentioned abnormal trajectory recognition method on the several abnormal driving trajectories shown in the following Figure 1A , Figure 1B , Figure 1C and Figure 1D , and can obtain the distance change diagrams shown in Figure 7A , the distance change diagrams shown in Figure 7B , the distance change diagrams shown in Figure 7C , and the distance change diagrams shown in Figure 7D .

[0103] Specifically, referring to Figure 7A , Figure 1A , the abnormal driving trajectory therein generates the first trough where the trajectory point 102 is located, the first peak where the trajectory point 103 is located, the second trough where the trajectory point 104 is located, and the second peak where the trajectory point 103 is located. The distance between the first peak where the trajectory point 103 is located and the first trough where the trajectory point 102 is located is greater than 1000 m, and the distance between the second peak where the trajectory point 103 is located and the second trough where the trajectory point 104 is located is greater than 1000 m. The electronic device can determine that the number of first reference values greater than the first distance threshold is equal to 2, and further determine that the driving trajectory in Figure 1A is abnormal.

[0104] Please refer to Figure 7B , Figure 1B , the abnormal driving trajectory therein generates the first trough where the trajectory point 115 is located and the first peak where the trajectory point 112 is located. The distance between the first peak where the trajectory point 112 is located and the first trough where the trajectory point 115 is located is greater than 1 / 3 of the total length (i.e., the distance between the starting point 111 and the ending point 116). The electronic device can determine that the number of second reference values greater than 1 / 3 of the total length is equal to 1, and further determine that the driving trajectory in Figure 1B is abnormal.

[0105] Please refer to Figure 7C , Figure 1C , the abnormal driving trajectory therein generates the first trough where the trajectory point 124 is located, the first peak where the trajectory point 122 is located, the second trough where the trajectory point 123 is located, and the second peak where the trajectory point 122 is located. The distance between the first peak where the trajectory point 122 is located and the first trough where the trajectory point 124 is located is greater than 1000 m, and the distance between the second peak where the trajectory point 122 is located and the second trough where the trajectory point 123 is located is greater than 1000 m. The electronic device can determine that the number of first reference values greater than 1000 m is equal to 2, and further determineFigure 1C The driving trajectory therein is abnormal.

[0106] Please refer to Figure 7D , Figure 1D The abnormal driving trajectory therein generates the first trough where the trajectory point 134 is located and the first peak where the trajectory point 131 is located. The distance between the first peak where the trajectory point 131 is located and the first trough where the trajectory point 134 is located is greater than 1 / 3 of the total length (i.e., the distance between the starting point 131 and the ending point 134). The electronic device can determine that the number of second reference values greater than 1 / 3 of the total length is equal to 1, and further determine Figure 1D The driving trajectory therein is abnormal.

[0107] It should be noted that Figure 7A , Figure 7B , Figure 7C and Figure 7D The distance change diagrams shown in

[0108] are only used to roughly characterize the change of the sorted multiple distances corresponding to each of them, and cannot represent the accurate numerical values of the multiple distances.

[0109] In the embodiments of the present application, after the electronic device determines that the driving trajectory in the travel data is abnormal, it can also count the number of abnormal driving trajectories of the driver in the travel data. If the total number of its abnormal driving trajectories is greater than or equal to a preset number of times, it means that the driver has a relatively large number of abnormal driving trajectories and needs to be focused on. Furthermore, the electronic device can send a prompt message to prompt to focus on this driver.

[0110] Specifically, the travel data further includes driver information. When the electronic device determines that the driving trajectory is abnormal, it can count the number of abnormal driving trajectories of the driver indicated by the driver information within a preset time period according to the driver information. Then, if the number of abnormal driving trajectories is greater than or equal to the preset number of times, the electronic device can send a prompt message. The prompt message characterizes that the driving trajectory of the driver indicated by the driver information is abnormal.

[0111] Among them, the electronic device can display the prompt message through a display screen, or play the prompt message through voice, etc.

[0112] Among them, the preset number of times and the preset time period are related. The longer the preset time period, the larger the preset number of times. Both the preset time period and the preset number of times can be indicated by the above first operation.

[0113] It can be understood that, in order to rule out the possibility that one or several abnormal driving trajectories of a driver occur accidentally, a preset number of abnormal driving trajectories occurring within a preset time period can be set. If the number of abnormal driving trajectories of a driver within a preset time period exceeds the preset number, it can be confirmed that the driver deliberately tampers with the driving trajectory, and then the electronic device can send out a prompt message.

[0114] It should be noted that, in addition to counting the number of abnormal driving trajectories in terms of the driver, the electronic device can also count the number of abnormal driving trajectories in terms of the vehicle. The process of the electronic device counting the number of abnormal driving trajectories in terms of the vehicle can refer to the specific introduction of counting the number of abnormal driving trajectories in terms of the driver, which will not be elaborated in this embodiment of the present application.

[0115] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. To implement the above functions, it includes the corresponding hardware structure and / or software module for executing each function. Those skilled in the art should easily realize that, combining the units and algorithm steps of each example described in the embodiments disclosed in this article, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the way of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Skilled professionals can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0116] The embodiment of the present application also provides an abnormal trajectory recognition device. As Figure 8 shown, it is a schematic structural diagram of an abnormal trajectory recognition device 800 provided by the embodiment of the present application. The recognition device 800 may include: a data acquisition module 801, a distance determination module 802, and an abnormality determination module 803.

[0117] Among them, the data acquisition module 801 is used to acquire the travel data of the vehicle. The travel data includes: the acquisition location and acquisition time of multiple trajectory points in the driving trajectory; the multiple trajectory points include the end point of the driving trajectory. The distance determination module 802 is used to respectively determine the distance between each of the multiple trajectory points and the end point according to the acquisition locations of the multiple trajectory points. The abnormality determination module 803 is used to determine whether the driving trajectory meets the trajectory abnormality condition according to the multiple distances and the acquisition times of the multiple trajectory points; if the driving trajectory meets the trajectory abnormality condition, it is determined that the driving trajectory is abnormal. The trajectory abnormality condition is used to characterize that the driving trajectory includes an abnormal fluctuation indicating that the vehicle is far from the end point.

[0118] In a possible implementation, the anomaly determination module 803 is specifically configured to: arrange multiple distances in the order of the acquisition times of multiple trajectory points to obtain the arranged multiple distances; determine the peaks and valleys in the arranged multiple distances; determine a reference value corresponding to each peak in the peaks according to the peaks, valleys, and the acquisition times of the multiple trajectory points; and determine whether the driving trajectory meets the trajectory anomaly condition according to the determined reference values. The reference value is used to represent whether each peak belongs to an abnormal peak.

[0119] In another possible implementation, the anomaly determination module 803 is specifically configured to: for a first peak, determine the difference between the first peak and the previous valley as the reference value corresponding to the first peak. Wherein, the first peak is any one of the peaks. The previous valley is the valley that is before the first peak and adjacent to the first peak among at least one valley.

[0120] In another possible implementation, the anomaly determination module 803 is specifically configured to: count the number of reference values greater than or equal to a preset distance threshold among the determined reference values; and determine whether the driving trajectory meets the trajectory anomaly condition according to the number.

[0121] In another possible implementation, the anomaly determination module 803 is specifically configured to: count the number of first reference values greater than or equal to a first distance threshold among the determined reference values; if the number of first reference values is greater than or equal to a first number, determine that the driving trajectory meets the trajectory anomaly condition; and / or count the number of second reference values greater than or equal to a second distance threshold among the determined reference values; if the number of second reference values is greater than or equal to a second number, determine that the driving trajectory meets the trajectory anomaly condition. Wherein, the second distance threshold is greater than the first distance threshold, and the second number is less than the first number.

[0122] In another possible implementation, the travel data further includes driver information. The recognition device 800 further includes: an anomaly statistics module 804 and a prompt module 805.

[0123] Among them, the anomaly statistics module 804 is configured to, when it is determined that the driving trajectory is abnormal, count the number of abnormal driving trajectories of the driver indicated by the driver information within a preset duration according to the driver information. The prompt module 805 is configured to issue a prompt message if the number of abnormal driving trajectories is greater than or equal to a preset number; the prompt message indicates that the driving trajectory of the driver indicated by the driver information is abnormal.

[0124] Of course, the anomaly trajectory recognition device 800 provided in the embodiments of the present application includes but is not limited to the above modules.

[0125] Another embodiment of the present application further provides an electronic device. Such as Figure 9As shown, the electronic device 900 includes a memory 901 and a processor 902; the memory 901 and the processor 902 are coupled; the memory 901 is used to store computer program code, and the computer program code includes computer instructions. Among them, when the processor 902 executes the computer instructions, the electronic device 900 is caused to execute each step performed by the electronic device in the method flow shown in the above method embodiment.

[0126] In actual implementation, the data acquisition module 801, the distance determination module 802, the anomaly judgment module 803, the anomaly statistics module 804, and the prompt module 805 can be Figure 9 implemented by the processor 902 shown in calling the computer program code in the memory 901. The specific execution process can refer to the description in the above part of the method for identifying abnormal trajectories and will not be elaborated here.

[0127] Another embodiment of the present application further provides a computer-readable storage medium in which computer instructions are stored. When the computer instructions run on an electronic device, the electronic device is caused to execute each step performed by the electronic device in the method flow shown in the above method embodiment.

[0128] Another embodiment of the present application further 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 circuits and the processors are interconnected by lines. The interface circuits are used to receive signals from the memory of the electronic device and send the signals to the processors, and the signals include the computer instructions stored in the memory. When the processor of the electronic device executes the computer instructions, the electronic device executes each step performed by the electronic device in the method flow shown in the above method embodiment.

[0129] In another embodiment of the present application, a computer program product is further provided, and the computer program product includes computer instructions. When the computer instructions run on an electronic device, the electronic device is caused to execute each step performed by the electronic device in the method flow shown in the above method embodiment.

[0130] 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 the computer execution instructions are loaded and executed on a computer, the processes or functions according to the embodiments of the present application are 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. The 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, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server, data center, etc. that contains one or more media integrated therein. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0131] As described above, the above is only the specific implementation manner of the present application. Those skilled in the art of this technology can think of changes or substitutions according to the specific implementation manner provided by the present application, and all should be covered within the protection scope of the present application.

Claims

1. A method for identifying abnormal trajectories, characterized in that, the method includes: Obtaining travel data of a vehicle; the travel data includes: the collection locations and collection times of multiple trajectory points in the driving trajectory; the multiple trajectory points include the end point of the driving trajectory; According to the collection locations of the multiple trajectory points, respectively determine the distances between each of the multiple trajectory points and the end point; Arrange the multiple distances in the order of the collection times of the multiple trajectory points to obtain the arranged multiple distances; Determine the peaks and valleys in the arranged multiple distances; According to the peaks and valleys, determine whether the driving trajectory meets the trajectory abnormal condition; the trajectory abnormal condition is used to characterize the abnormal fluctuations in the driving trajectory where the vehicle is far from the end point; If the driving trajectory meets the trajectory abnormal condition, determine that the driving trajectory is abnormal.

2. The method according to claim 1, characterized in that, The determining whether the driving trajectory meets the trajectory abnormal condition according to the peaks and valleys includes: According to the peaks, valleys and the collection times of the multiple trajectory points, determine the reference value corresponding to each peak in the peaks; the reference value is the difference between the peak and at least one valley that is before the peak and adjacent to the peak; According to the determined reference value, determine whether the driving trajectory meets the trajectory abnormal condition.

3. The method according to claim 2, characterized in that, The determining whether the driving trajectory meets the trajectory abnormal condition according to the determined reference value includes: Count the number of reference values among the determined reference values that are greater than or equal to a preset distance threshold; According to the number, determine whether the driving trajectory meets the trajectory abnormal condition.

4. The method according to claim 2, characterized in that, The determining whether the driving trajectory meets the trajectory abnormal condition according to the determined reference value includes: Count the number of first reference values among the determined reference values that are greater than or equal to a first distance threshold; if the number of the first reference values is greater than or equal to a first preset number, determine that the driving trajectory meets the trajectory abnormal condition; and / or Count the number of second reference values among the determined reference values that are greater than or equal to a second distance threshold; if the number of the second reference values is greater than or equal to a second preset number, determine that the driving trajectory meets the trajectory abnormal condition; wherein, the second distance threshold is greater than the first distance threshold, and the second preset number is less than the first preset number.

5. The method according to any one of claims 1-4, characterized in that, The travel data further includes driver information; the method further includes: When it is determined that the driving trajectory is abnormal, according to the driver information, count the number of abnormal driving trajectories of the driver indicated by the driver information within a preset time period; If the number of abnormal driving trajectories is greater than or equal to a preset number of times, send a prompt message.

6. An apparatus for identifying abnormal trajectories, characterized in that, The recognition device includes: a data acquisition module configured to acquire travel data of a vehicle; the travel data includes: collection positions and collection times of a plurality of trajectory points in a travel trajectory; the plurality of trajectory points includes an end point of the travel trajectory; a distance determination module configured to respectively determine distances between each of the plurality of trajectory points and the end point according to the collection positions of the plurality of trajectory points; an anomaly judgment module configured to: arrange the plurality of distances in the order of the collection times of the plurality of trajectory points to obtain the arranged plurality of distances; determine peaks and valleys in the arranged plurality of distances; judge whether the travel trajectory meets a trajectory anomaly condition according to the peaks and the valleys; the trajectory anomaly condition is used to characterize an abnormal fluctuation in which the vehicle moves away from the end point in the travel trajectory; if the travel trajectory meets the trajectory anomaly condition, determine that the travel trajectory is abnormal.

7. The device according to claim 6, wherein, the anomaly judgment module is specifically configured to: determine a reference value corresponding to each peak in the peaks according to the peaks, the valleys, and the collection times of the plurality of trajectory points; judge whether the travel trajectory meets the trajectory anomaly condition according to the determined reference value; wherein the reference value is used to characterize whether each peak belongs to an abnormal peak; the anomaly judgment module is specifically configured to: for a first peak, determine a difference between the first peak and the previous valley as the reference value corresponding to the first peak; wherein, the previous valley is the valley that is before the first peak and adjacent to the first peak among the valleys; the first peak is any one of the peaks; the anomaly judgment module is specifically configured to: count the number of the reference values that are greater than or equal to a preset distance threshold among the determined reference values; judge whether the travel trajectory meets the trajectory anomaly condition according to the number; the anomaly judgment module is specifically configured to: count the number of first reference values that are greater than or equal to a first distance threshold among the determined reference values; if the number of the first reference values is greater than or equal to a first preset number, determine that the travel trajectory meets the trajectory anomaly condition; and / or count the number of second reference values that are greater than or equal to a second distance threshold among the determined reference values; if the number of the second reference values is greater than or equal to a second preset number, determine that the travel trajectory meets the trajectory anomaly condition; wherein, the second distance threshold is greater than the first distance threshold, and the second preset number is less than the first preset number; the travel data further includes driver information; the recognition device further includes: an anomaly statistics module and a prompt module; the anomaly statistics module is configured to, when determining that the travel trajectory is abnormal, count the number of abnormal travel trajectories of the driver indicated by the driver information within a preset time period according to the driver information; the prompt module is configured to send a prompt message if the number of the abnormal travel trajectories is greater than or equal to a preset number of times.

8. An electronic device, wherein, The electronic device includes a memory and a processor; the memory is coupled to the processor; the memory is used to store computer program code, and the computer program code includes computer instructions; Wherein, when the processor executes the computer instructions, the electronic device is caused to execute the abnormal trajectory recognition method described in any one of claims 1-5.

9. A computer-readable storage medium, characterized in that, the computer-readable storage medium stores computer instructions, and when the computer instructions run on an electronic device, the electronic device is caused to execute the abnormal trajectory recognition method described in any one of claims 1-5.

Images