An abnormal trajectory identification method and device, electronic equipment and storage medium

Abstract

The application provides an abnormal trajectory identification method and device, electronic equipment and a storage medium, relates to the technical field of information processing, and can effectively identify abnormal driving mileage. The specific scheme comprises the following steps: obtaining travel data of a vehicle; the travel data comprises a boarding position, an alighting position and a driving mileage; determining a first area to which the boarding position belongs and a second area to which the alighting position belongs; obtaining an upper mileage limit value corresponding to the travel data with the first area and the second area as start and end points; and if the driving mileage is greater than or equal to the upper mileage limit value corresponding to the travel data, it is determined that the travel data is abnormal travel data.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of information processing, and in particular to an abnormal trajectory identification method and device, an electronic device and a storage medium. BACKGROUND

[0002] Currently, after completing an order, a network car can report the driving mileage and the pickup and drop-off positions of passengers and other travel data to a network car platform. Then, the network car platform can calculate the driving cost of the order according to the driving mileage. In order to increase the driving cost, some network cars will generate and report a high driving mileage. The driving cost calculated by the network car platform according to the high driving mileage is higher than the real driving cost.

[0003] Due to some characteristics of network cars, such as flexible and variable pickup and drop-off positions of passengers, and the change of driving paths of network cars due to road conditions and passenger specified routes, the driving mileage in different travel data varies greatly. Therefore, there is no standard driving mileage to refer to for each travel data. That is, the problem of network cars reporting false driving mileage cannot be identified at present. SUMMARY

[0004] The present application provides an abnormal trajectory identification method, device, electronic device and storage medium, which can effectively identify abnormal driving mileage.

[0005] To achieve the above technical purposes, the present application adopts the following technical solutions:

[0006] In a first aspect, the present application provides an abnormal trajectory identification method, which comprises: obtaining travel data of a vehicle; the travel data comprising pickup and drop-off positions and driving mileage; determining a first area to which the pickup position belongs and a second area to which the drop-off position belongs; obtaining an upper mileage limit corresponding to the travel data with the first area and the second area as start and end points; and determining that the travel data is abnormal travel data if the driving mileage is greater than or equal to the upper mileage limit corresponding to the travel data.

[0007] It can be understood that the electronic device can determine at least one upper mileage limit according to a plurality of historical travel data within a target time period and save it. Then, the electronic device can use the saved upper mileage limit to determine whether the driving mileage in the travel data of a vehicle is abnormal.

[0008] The electronic device can first determine a first region to which the pickup location in the trip data belongs and a second region to which the drop-off location belongs. In this way, the pickup and drop-off locations that change frequently are classified. Then, the electronic device can obtain an upper mileage value of a mileage corresponding to the trip data with the first region and the second region as start and end points. Since the pickup location in the trip data is in the first region and the drop-off location in the trip data is in the second region, it can be known that the driving mileage from the pickup location to the drop-off location is almost the same as the upper mileage value with the first region and the second region as start and end points. Therefore, by using the upper mileage value with the first region and the second region as start and end points, it can be determined whether the driving mileage from the pickup location to the drop-off location is too high. If the driving mileage is greater than or equal to the upper mileage value, it indicates that the driving mileage is too high, and it can be determined that the driving mileage in the trip data is abnormal, that is, the trip data is abnormal trip data. That is, the method provided in the embodiment of the present application realizes the identification of the trip data with abnormal driving mileage.

[0009] In a possible implementation, the trip data further includes driver information. The method further includes: according to the driver information, counting the number of abnormal trip data of the driver indicated by the driver information within a preset time length; and if the number of abnormal trip data is greater than or equal to a preset number of times, issuing a prompt information.

[0010] It can be understood that, in order to exclude the possibility that the abnormal trip data of the driver occurs once or several times accidentally, a preset number of times of abnormal trip data occurring within a preset time length can be set. Further, the electronic device can count the number of abnormal trip data of the driver in the abnormal trip data. If the total number of abnormal trip data of the driver is greater than or equal to the preset number of times, it indicates that the driver has a high probability of intentionally tampering with the driving mileage and needs to be focused on. Therefore, the electronic device can issue a prompt information for prompting to focus on the driver.

[0011] In another possible implementation, the method further includes: obtaining a plurality of historical trip data of vehicles in the target region; further determining position information of each of the at least one region in the target region; then, according to the pickup location and the drop-off location in the plurality of historical trip data and the position information of each of the at least one region, determining at least one group of regions and target historical trip data corresponding to each group of regions in the at least one group of regions; and finally, for each group of regions, determining an upper mileage value corresponding to each group of regions according to the driving mileage in the target historical trip data corresponding to each group of regions.

[0012] The historical travel data includes a pickup location, a drop-off location and a travel mileage. One region and another region in each group of regions include the pickup location and the drop-off location in the target historical travel data respectively. The mileage upper bound corresponding to each group of regions is a mileage upper bound with two regions in each group of regions as start and end points.

[0013] It can be understood that in the embodiments of the present application, the target region is first divided into at least one region, and the historical travel data of the vehicle traveling between any two regions is obtained. By dividing the target region into at least one region, the historical travel data with different pickup and drop-off locations is classified. For example, the historical travel data with the pickup and drop-off locations in the two regions included in any group of regions can be considered as the historical travel data of the vehicle traveling between the group of regions, i.e., all are the target historical travel data corresponding to the group of regions. In this way, multiple target historical travel data with the pickup and drop-off locations belonging to the group of regions can be obtained. Then, according to the multiple target historical travel data with the pickup and drop-off locations belonging to the group of regions, the upper bound of the travel mileage with the two regions in the group of regions as start and end points (i.e., the mileage upper bound corresponding to the group of regions) can be determined. By using the mileage upper bound corresponding to the group of regions, it can be determined whether the travel mileage of the vehicle with the pickup and drop-off locations belonging to the group of regions is too high, i.e., the abnormal travel mileage is identified.

[0014] In another possible implementation, the determining of the position information of each of the at least one region in the target region includes: dividing the target region into at least one region with the same size by using a preset encoding algorithm, and determining first encoding data of each region in the at least one region. The first encoding data of each region is the position information of each region. The preset encoding algorithm can include a GeoHash algorithm.

[0015] The determining of the at least one group of regions and the target historical travel data corresponding to each group of regions in the at least one group of regions according to the pickup and drop-off locations in the multiple historical travel data and the position information of each of the at least one region includes: for each historical travel data in the multiple historical travel data, converting the pickup and drop-off locations in the historical travel data by using a preset encoding algorithm respectively to obtain a pair of second encoding data; determining a group of regions from the at least one region and determining that the historical travel data belongs to the target historical travel data corresponding to the group of regions according to the pair of second encoding data; and the first encoding data of the group of regions includes the pair of second encoding data.

[0016] In this design, an implementation of dividing the target region into at least one region is described.

[0017] In another possible implementation, the above-mentioned preset encoding algorithm is used to divide the target area into at least one area of ​​the same size, and to determine the first encoded data of each area in the at least one area, including: using the preset encoding algorithm to convert the latitude and longitude of the target area, and extracting the first preset number of GeoHash characters from the converted encoded data to obtain at least one area and the first encoded data of each area; the first encoded data of each area is the first preset number of GeoHash characters in the converted encoded data of each area.

[0018] The above-mentioned determination of a group of regions from at least one region based on a pair of second encoded data includes: determining from at least one region that a region in which the first encoded data is equal to the first preset number of characters of any one of the second encoded data in the pair of second encoded data belongs to the group of regions.

[0019] This design approach describes the specific implementation process of dividing the target area into at least one region.

[0020] In another possible implementation, the above-mentioned method for determining the upper bound of mileage for each group of regions based on the mileage in the target historical travel data corresponding to each group of regions includes: sorting the mileage in the target historical travel data corresponding to each group of regions when the total number of target historical travel data for each group of regions is greater than or equal to a preset confidence threshold, to obtain sorted mileage; determining a first value and a second value from the sorted mileage; wherein the first value is less than the median of the sorted mileage; the second value is greater than the median of the sorted mileage; multiplying the difference between the second value and the first value by a preset multiple, and then summing it with the second value, to obtain the upper bound of mileage for each group of regions.

[0021] It can be understood that although the driving mileage in the plurality of target historical travel data corresponding to any one group of regions is the driving mileage between two regions in the group of regions. However, the drop-off and pick-up locations in different target historical travel data can be different; the driving path in the target historical travel data with similar drop-off and pick-up locations can also be different due to the influence of the route specified by the passenger and the road condition and other factors. These can cause some differences in the driving mileage in different travel data between two regions in the group of regions. Then, if the target historical travel data is more, the distribution of the driving mileage between two regions in the group of regions can be more accurately reflected. If the target historical travel data is less, it indicates that the route between two regions in the group of regions is a cold route, and the distribution of the driving mileage between two regions in the group of regions reflected by the less target historical travel data is also inaccurate. Therefore, it can be known that the accuracy of the upper limit value of the driving mileage between two regions in the group of regions (i.e., the mileage upper limit value corresponding to the group of regions) determined by the electronic device according to more target historical travel data is higher.

[0022] Further, the electronic device can determine the mileage upper limit value corresponding to the group of regions according to the driving mileage in all target historical travel data in a case where the total number of target historical travel data corresponding to the group of regions is greater than or equal to a preset confidence threshold. If the total number is less than the preset confidence threshold, the electronic device can not determine the mileage upper limit value corresponding to the group of regions.

[0023] In a second aspect, the present application provides an abnormal trajectory identification device. The abnormal trajectory identification device comprises various modules for executing the method of the first aspect or any possible design of the first aspect.

[0024] In a third aspect, the present application provides an electronic device, which comprises a memory and a processor. The memory and the processor are coupled. The memory is used to store computer program code, which comprises computer instructions. When the processor executes the computer instructions, the electronic device executes the abnormal trajectory identification method as described in the first aspect and any possible design of the first aspect.

[0025] In a fourth aspect, the present application provides a chip system applied to an abnormal trajectory identification device; the chip system comprises one or more interface circuits and one or more processors. The interface circuit and the processor are interconnected through a circuit; the interface circuit is used to receive signals from the memory of the abnormal trajectory identification device and send signals to the processor, and the signals comprise computer instructions stored in the memory. When the processor executes the computer instructions, the electronic device executes the abnormal trajectory identification method as described in the first aspect and any possible design of the first aspect.

[0026] In a fifth aspect, the present application provides a computer readable storage medium, which stores computer instructions, when the computer instructions are executed on an electronic device, the electronic device is caused to perform the abnormal trajectory identification method according to the first aspect and any possible implementation manner thereof.

[0027] In a sixth aspect, the present application provides a computer program product, which comprises computer instructions, when the computer instructions are executed on an electronic device, the electronic device is caused to perform the abnormal trajectory identification method according to the first aspect and any possible implementation manner thereof.

[0028] The detailed description of the second aspect to the sixth aspect and various implementation manners thereof in the present application can refer to the detailed description in the first aspect and various implementation manners thereof; and the beneficial effects of the second aspect to the sixth aspect and various implementation manners thereof can refer to the beneficial effect analysis in the first aspect and various implementation manners thereof, which will not be repeated here.

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

[0030] Figure 1 An implementation environment involved in an abnormal trajectory identification method provided by an embodiment of the present application Figure 1 ;

[0031] Figure 2 An implementation environment involved in an abnormal trajectory identification method provided by an embodiment of the present application Figure 2 ;

[0032] Figure 3 An implementation environment involved in an abnormal trajectory identification method provided by an embodiment of the present application Figure 3 ;

[0033] Figure 4 A flow of an abnormal trajectory identification method provided by an embodiment of the present application Figure 1 ;

[0034] Figure 5 A schematic diagram of dividing a target region into multiple regions with the same size provided by an embodiment of the present application

[0035] Figure 6 A box type of quartile provided by an embodiment of the present application Figure 1 ;

[0036] Figure 7 A data ladder diagram based on three-sigma criterion provided by an embodiment of the present application

[0037] Figure 8A box type of quartile provided for an embodiment of the present application Figure 2 ;

[0038] Figure 9 A flow of an abnormal trajectory identification method provided for an embodiment of the present application Figure 2 ;

[0039] Figure 10 A flow of an abnormal trajectory identification method provided for an embodiment of the present application Figure 3 ;

[0040] Figure 11 A flow of an abnormal trajectory identification method provided for an embodiment of the present application Figure 4 ;

[0041] Figure 12 A structural schematic diagram of an abnormal trajectory identification device provided for an embodiment of the present application

[0042] Figure 13 A structural schematic diagram of an electronic device provided for an embodiment of the present application DETAILED DESCRIPTION

[0043] Hereinafter, the terms "first", "second", and "third" and the like are used only for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" or "third" and the like can explicitly or implicitly include one or more of the features.

[0044] At present, the rise and promotion of online car-hailing bring great convenience to the travel of users. Among them, there are some online car-hailing tampering with the driving mileage in the travel data to improve the driving fee calculated according to the tampered driving mileage. Since the driving mileage in different travel data is different, there is no standard driving mileage to refer to for each driving mileage. That is to say, the problem of online car-hailing falsely reporting driving mileage cannot be identified at present.

[0045] To solve the problem, the embodiment of the present application provides an abnormal trajectory identification method, which divides a target area into at least one area, and then acquires historical travel data of a vehicle traveling between any two areas. By dividing the target area into at least one area, the historical travel data of different drop-off and pick-up locations can be classified. For example, the historical travel data of the drop-off and pick-up locations in any two areas can be considered as the historical travel data of the vehicle traveling between the two areas, i.e., the target historical travel data corresponding to the two areas. In this way, multiple target historical travel data of the drop-off and pick-up locations belonging to the two areas can be obtained. Then, according to the multiple target historical travel data of the drop-off and pick-up locations belonging to the two areas, the upper bound of the mileage between the two areas can be determined. By using the upper bound of the mileage between the two areas, whether the travel mileage of the vehicle with the drop-off and pick-up locations belonging to the two areas is too high can be determined, i.e., the abnormal travel mileage is identified.

[0046] The implementation of the embodiment of the present application will be described in detail below with reference to the accompanying drawings.

[0047] Please refer to Figure 1 which shows an implementation environment schematic diagram related to an abnormal trajectory identification method provided by the embodiment of the present application. As Figure 1 shown, the implementation environment can include a server 100, a terminal 110, and a plurality of collection modules 120 for collecting travel data of a vehicle. Among them, the plurality of collection modules 120 are respectively installed in a plurality of vehicles.

[0048] Exemplarily, each collection module 120 can include a GPS module, a timing module, and an input module (such as a touch screen). Figure 1 The GPS module, the timing module, and the input module in the collection module 120 are not shown in the figure. The GPS module is used to collect the drop-off and pick-up latitude and longitude of the passengers and the travel path, and is also used to determine the travel mileage. The timing module is used to collect the drop-off and pick-up time of the passengers. The input module is used to collect the driver information, vehicle information, etc. input by the driver.

[0049] The server 100 can receive the travel data of the vehicle from the plurality of collection modules 120. The travel data can include the drop-off and pick-up latitude and longitude of the passengers, the drop-off and pick-up time, the travel path, the travel mileage, the driver information, and the vehicle information, etc.

[0050] As Figure 2As shown, terminal 110 can receive a first operation input by the user, which indicates the target area, target vehicle type (e.g., ride-hailing, taxi), target duration, and area division parameters. Then, in response to the first operation, terminal 110 can obtain historical travel data from server 100 for vehicles belonging to the target vehicle type that are traveling within the target area and within the target duration. Terminal 110 can also divide the target area into at least one area based on the area division parameters. Terminal 110 then determines the mileage upper limit between two areas within the at least one area based on the obtained historical travel data. After obtaining the mileage upper limit, terminal 110 can obtain travel data for a vehicle from server 100 and determine whether the mileage in the travel data is abnormal based on the mileage upper limit. If the mileage in the travel data is abnormal, a prompt message can be issued to indicate that the vehicle's mileage is abnormal. For example, terminal 110 can display this prompt message on a screen.

[0051] Or, such as Figure 3 As shown, in response to the first operation, terminal 110 can send target information to server 100. This target information includes the target area, target vehicle type, target duration, and area division parameters. Then, terminal 110 can divide the target area into at least one area based on the area division parameters. Server 100 also acquires historical travel data of vehicles belonging to the target vehicle type that are traveling within the target area during the target duration. Server 100 then determines the mileage upper limit between two areas within the at least one area based on the acquired historical travel data. After obtaining the mileage upper limit, server 100 can receive travel data for a vehicle sent by a collection module 120 and determine whether the mileage in the travel data is abnormal based on the mileage upper limit. If the mileage in the travel data is abnormal, the aforementioned prompt information can be sent to terminal 110. Terminal 110 can issue this prompt information.

[0052] The target duration can be one month, one quarter, etc. The regional division parameters can characterize the size of at least one region, for example, 1.2 kilometers (km) * 0.6 km.

[0053] For example, the terminal 110 in this application embodiment may be a mobile phone, tablet computer, desktop computer, laptop computer, netbook, etc., and this application embodiment does not impose any special restrictions on the specific form of the terminal 110.

[0054] It should be noted that the abnormal trajectory identification method provided in the embodiments of the present application can be applied to the server 100 described above, can be applied to the terminal 110 described above, and can also be applied to the server 100 and the terminal 110. The server 100 and the terminal 110 can be collectively referred to as an electronic device. The execution subject of the abnormal trajectory identification method provided in the embodiments of the present application can also be an abnormal trajectory identification device. The device can be an electronic device; or the device can be an application (APP) installed in the electronic device and providing an abnormal trajectory identification function; or the device can be a 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. The abnormal trajectory identification provided in the embodiments of the present application will be described in detail below taking the electronic device as an example.

[0055] It should be noted that the abnormal trajectory identification method provided in the embodiments of the present application can be applied to the server 100 described above, can be applied to the terminal 110 described above, and can also be applied to the server 100 and the terminal 110. The server 100 and the terminal 110 can be collectively referred to as an electronic device. The execution subject of the abnormal trajectory identification method provided in the embodiments of the present application can also be an abnormal trajectory identification device. The device can be an electronic device; or the device can be an application (APP) installed in the electronic device and providing an abnormal trajectory identification function; or the device can be a 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. The abnormal trajectory identification provided in the embodiments of the present application will be described in detail below taking the electronic device as an example. Figure 4 A flowchart of an abnormal trajectory identification method provided in the embodiments of the present application is shown in FIG. 4. As shown in FIG. 4, the method can include S401-S404. Figure 4

[0056] S401, the electronic device acquires a plurality of historical travel data of a vehicle in a target region; the historical travel data includes a pickup location, a drop-off location and a driving distance.

[0057] The electronic device can acquire all historical travel data within a target time length. Each historical travel data can include, in addition to the pickup location (such as pickup latitude and longitude), the drop-off location (such as drop-off latitude and longitude) and the driving distance, the pickup time, the drop-off time, the driver information and the vehicle information, etc.

[0058] The target region can be any region, for example, Shaanxi Province, Beijing, etc.

[0059] S402, the electronic device determines the position information of each of at least one region in the target region.

[0060] The electronic device can divide the target region into at least one region, and acquire the position information of each region in the at least one region.

[0061] In some embodiments, the electronic device can use a preset encoding algorithm to divide the target region into at least one region of the same size, and determine the first encoding data of each region in the at least one region.

[0062] The first encoding data of each region is the position information of each region. The first encoding data of each region can represent the position of any point in the region.

[0063] ​The preset encoding algorithm can include a GeoHash algorithm. The GeoHash algorithm is an address encoding method that can encode a longitude and latitude in a two-dimensional space into a string. The longer the string, the smaller the range it represents and the more accurate the location. That is, the first few characters in a string can represent all locations including the first few characters. For example, a point with longitude and latitude is converted to wx4g0ec1, and the prefix wx4g0e of wx4g0ec1 can represent a larger range including wx4g0ec1.

[0064] In some embodiments, the electronic device can employ a preset encoding algorithm (e.g., a GeoHash algorithm) to convert the longitude and latitude in the target area, and extract the first preset number m of GeoHash characters from the converted encoding data to obtain at least one region and the first encoding data of each region. The first encoding data of each region is the first preset number m of GeoHash characters in the converted encoding data in each region.

[0065] The electronic device divides the target area into grids of the same size by extracting the first m bits of GeoHash characters from the converted encoding data. A grid is a region. The smaller m is, the smaller the size of the region. For example, when n is 6, the size of each region is 1.2 km*0.6 km, and the first encoding data of each region is a 6-bit GeoHash character.

[0066] For example, as shown in FIG. 1, the target area is the Xuzhou District of Shanghai, and m is equal to 6. The electronic device can employ a GeoHash algorithm to convert the longitude and latitude of the target area, and extract the first 6 bits of GeoHash characters from the converted encoding data to obtain 9 regions in the target area and the first encoding data of the 9 regions. When n is 6, the size of each region is 1.2 km*0.6 km, and the first encoding data of each region is a 6-bit GeoHash character. The first encoding data of the 9 regions is wtw37p, wtw37r, wtw37x, wtw37n, wtw37q, wtw37w, wtw37j, wtw37m, and wtw37t, respectively. Figure 5

[0067] For example, taking a point in region 55 with longitude and latitude coordinates of (39.923201, 116.390705) as an example, the process of converting the longitude and latitude of the point using the GeoHash algorithm is described.

[0068] ​(1) The electronic device can first convert the latitude and longitude of the point into binary. Specifically, the range of latitude is (-90, 90), and the middle value of (-90, 90) is 0. Since the latitude of the point is 39.923201, which is greater than 0, a 1 is first obtained; the middle value of (0, 90) is 45, and the latitude 39.923201 is less than 45; therefore, a 0 is obtained; and the binary representation corresponding to the latitude 39.923201 can be obtained by sequentially calculating down. Similarly, the binary representation of the longitude 116.390705 can be obtained.

[0069] (2) The electronic device can further combine the binary representations of the latitude and longitude. Specifically, the longitude is in the even bits, and the latitude is in the odd bits. The electronic device can obtain the combined binary number of the point as 11100 11001 11100 000110011110110.

[0070] (3) The electronic device can encode the combined binary number by using Base32 encoding. Base32 encoding refers to encoding by using 0-9 and b-z (excluding a, i, and l). Specifically, the electronic device can first convert the combined binary number into a decimal number; and then generate a string corresponding to the decimal number according to the characters corresponding to the 32 characters. For example, the electronic device converts the combined binary number into a decimal number, and the decimal number is 28 25 28 37 22; then, the string corresponding to the decimal number can be obtained by searching for the characters corresponding to the 32 characters, and the string is wtw37q.

[0071] As can be seen, the first encoding data of the region 55 is wtw37q, and the first 6 characters of a point in the region 55 are also wtw37q. The first 6 characters of the converted encoding data of all points in each region are the same as the first encoding data of the region.

[0072] S403, The electronic device determines at least one group of regions and target historical travel data corresponding to each group of regions in the at least one group of regions according to the boarding positions and alighting positions in the plurality of historical travel data and the position information of the at least one region; wherein one region and another region in each group of regions include the boarding position and the alighting position in the target historical travel data corresponding to each group of regions, respectively.

[0073] The electronic device can determine one region including the boarding position and another region including the alighting position from the at least one region according to the boarding position and the alighting position in each historical travel data. The one region including the boarding position and the other region including the alighting position form a group of regions. Further, the electronic device can obtain a plurality of groups of regions, and each group of regions includes two regions.

[0074] In the embodiments of the present application, after the electronic device obtains the first encoding data of each region by using the preset encoding algorithm, the electronic device can also convert the pickup location and the drop-off location in each historical travel data by using the preset encoding algorithm, to obtain a pair of second encoding data. Then, the electronic device determines a group of regions from the at least one region according to the pair of second encoding data, and determines that the historical travel data belongs to the target historical travel data corresponding to the group of regions.

[0075] The pickup location can be pickup longitude and latitude, and the drop-off location can be drop-off longitude and latitude. The pair of second encoding data includes the second encoding data corresponding to the pickup location and the second encoding data corresponding to the drop-off location.

[0076] The first encoding data of the group of regions includes the pair of second encoding data can mean that the first encoding data of one region in the group of regions includes the second encoding data corresponding to the pickup location, and the first encoding data of another region in the group of regions includes the second encoding data corresponding to the drop-off location.

[0077] In some embodiments, the electronic device can determine that the region whose first encoding data is equal to the characters of the first preset number of bits of any one of the pair of second encoding data in the group of regions belongs to the group of regions.

[0078] Exemplarily, Figure 5 The first encoding data of the region 52 is wtw37r, and the first encoding data of the region 55 is wtw37q. The second encoding data corresponding to the pickup location in a historical travel data is wtw37qd2, and the second encoding data corresponding to the drop-off location is wtw37re1. At this time, the electronic device can determine that the first encoding data of the region 52 includes the second encoding data corresponding to the drop-off location in the historical travel data, and the first encoding data of the region 55 includes the second encoding data corresponding to the pickup location in the historical travel data. Further, the electronic device can determine that the region 52 and the region 55 form a group of regions, and that the historical travel data belongs to the target historical travel data corresponding to the region 52 and the region 55.

[0079] S404, the electronic device determines, for each group of regions, a mileage upper limit value corresponding to each group of regions according to the driving mileage in the target historical travel data corresponding to each group of regions. The mileage upper limit value corresponding to each group of regions is a mileage upper limit value with two regions in each group of regions as start and end points.

[0080] The electronic device can determine, for each of the at least one group of regions, a mileage upper bound value corresponding to each group of regions according to the travel mileage in the corresponding target historical travel data. Further, the electronic device can determine at least one mileage upper bound value, and the regions corresponding to different mileage upper bound values are not completely the same. Then, the electronic device can determine whether the travel mileage in the travel data of a vehicle is abnormal by using the determined mileage upper bound value.

[0081] In the embodiments of the present application, the travel mileage in the plurality of target historical travel data corresponding to any group of regions is the travel mileage between two regions in the group of regions. However, the drop-off and pick-up locations in different target historical travel data can be different. The travel path in the target historical travel data with similar drop-off and pick-up locations can also be different due to the influence of the route specified by the passenger and the road conditions. These can cause some differences in the travel mileage between the two regions in the group of regions in different travel data. Therefore, if there are more target historical travel data, the distribution of the travel mileage between the two regions in the group of regions can be more accurately reflected. If there are less target historical travel data, it indicates that the route between the two regions in the group of regions is a cold route, and the distribution of the travel mileage between the two regions in the group of regions reflected by the less target historical travel data is also not accurate. Therefore, it can be known that the accuracy of the upper bound value of the travel mileage between the two regions in the group of regions (i.e., the mileage upper bound value corresponding to the group of regions) determined by the electronic device according to more target historical travel data is higher.

[0082] Further, the electronic device can determine the mileage upper bound value corresponding to the group of regions according to the travel mileage in all target historical travel data when the total number of target historical travel data corresponding to any group of regions is greater than or equal to a preset confidence threshold. If the total number is less than the preset confidence threshold, the electronic device can not determine the mileage upper bound value corresponding to the group of regions; or the electronic device determines the mileage upper bound value corresponding to the group of regions according to the travel mileage in all target historical travel data, and takes the total number as the confidence of the mileage upper bound value corresponding to the group of regions.

[0083] The preset confidence threshold can be indicated by the first operation input by the user. The confidence of the mileage upper bound value can represent the number of travel mileages used to determine the mileage upper bound value.

[0084] In some embodiments, the electronic device can use quartile method or three-sigma method to determine the mileage upper bound value corresponding to each group of regions according to the travel mileage in all target historical travel data corresponding to each group of regions.

[0085] The quartile method is to divide a set of data into four equal parts, and obtain the values at the quartile points (i.e., quartiles). The upper limit value of the set of data is determined by using the quartiles.

[0086] As shown in the box plot of the quartiles, Figure 6 As shown in the box plot of the quartiles,

[0087] The electronic device can substitute the first quartile Q1 and the third quartile Q3 into the following formula (1) to calculate the upper limit value Z:

[0088] Z = Q3 + k * (Q3 - Q1) = Q3 + k * IQR (1)

[0089] The difference between the third quartile Q3 and the first quartile Q1 can be referred to as the interquartile range (IQR). The preset multiple k takes a value within a certain range, for example, k can take a value of 1.5 or 3.

[0090] It can be understood that if a value exceeds the upper limit value Z, or is less than Q1 - k * IQR, the value can be confirmed as an outlier. The box plot used to represent the quartiles is obtained according to the real data, and has no requirement on the data, so the box plot can truly and intuitively represent all real data.

[0091] Secondly, some outliers are usually too large or too small. If too small, the distance from the first quartile Q1 is far, and if too large, the distance from the third quartile Q1 is far. That is, the outliers are usually far from the quartiles and have less interference with the quartiles. Or, the quartiles have strong anti-interference ability. Then, the upper limit value is calculated according to the quartiles and the interquartile range, and the interquartile range is also calculated according to the quartiles, so the upper limit value is calculated according to the quartiles. Therefore, the outliers have less interference with the quartiles, and also have less interference with the upper limit value calculated according to the quartiles. The upper limit value obtained by the quartile method can more accurately detect larger outliers.

[0092] The three-sigma method is to determine the upper limit value of a set of data according to the three-sigma criterion. As shown in Figure 7As shown, the three-sigma rule indicates that, in statistics, if a set of data is approximately normally distributed, then about 68% of the data in the set will be within one standard deviation of the mean, about 95% of the data will be within two standard deviations of the mean, and about 99.7% of the data will be within three standard deviations of the mean. Therefore, if any data is more than 3 times the standard deviation from the mean, it is likely to be an outlier.

[0093] For example, the electronic device can substitute the mean and the standard deviation of a set of data into the following formula (2) to calculate the upper bound Z:

[0094] Z = mean + 3 * Std (2)

[0095] It can be known that the accuracy of the upper bound calculated by the electronic device using the formula (2) for judging outliers is high.

[0096] In some embodiments, the electronic device can first sort the driving mileage in the target historical travel data corresponding to each group of regions to obtain sorted driving mileage. Then, the electronic device can determine a first value and a second value from the sorted driving mileage. Finally, the electronic device can multiply the difference between the second value and the first value by a preset multiple k, and then sum the second value to obtain the mileage upper bound corresponding to each group of regions.

[0097] The first value is less than the median of the sorted driving mileage. The second value is greater than the median of the sorted driving mileage. For example, the first value is the first quartile Q1, the second value is the third quartile Q3, and the preset multiple can be 1.5 or 3.

[0098] For example, the electronic device can first sort the driving mileage in all target historical travel data corresponding to each group of regions in ascending order to obtain ascending driving mileage. Assuming that the total number of driving mileage in all target historical travel data corresponding to each group of regions is n. The position of the first quartile Q1 in the ascending driving mileage can be equal to (n+1) * 0.25, and the position of the third quartile Q3 in the ascending driving mileage can be equal to (n+1) * 0.75.

[0099] If (n+1)*0.25 is an integer, the first quartile Q1 is equal to the (n+1)*0.25 th data in the ascending order of the driving distances. If (n+1)*0.25 is a decimal number, (n+1)*0.25 can be rounded (e.g., rounded to the nearest integer, rounded by removing the digits after the decimal point), and the result is h. The first quartile Q1 is equal to the h th data in the ascending order of the driving distances. Similarly, the electronic device can determine the third quartile Q3.

[0100] For example, n=11, and the 11 driving distances include: 6, 47, 49, 15, 42, 41, 7, 39, 43, 40, 36. The electronic device sorts the 11 driving distances in ascending order, and the ascending order of the driving distances is: 6, 7, 15, 36, 39, 40, 41, 42, 43, 47, 49. (11+1)*0.25=3, and the first quartile Q1=15. (11+1)*0.75=6, and the third quartile Q3=43.

[0101] For another example, n=9, and the ascending order of the driving distances is: 6, 7, 15, 36, 39, 40, 41, 42, 43. (9+1)*0.25=2.5, and the electronic device can round 2.5 to obtain 2 or 3, and the first quartile Q1 is 7 or 15. (9+1)*0.75=7.5, and the electronic device can round 7.5 to obtain 7 or 8, and the third quartile Q3 is 41 or 42.

[0102] In some embodiments, the electronic device can first calculate the mean and the standard deviation Std of the driving distances in the target historical travel data corresponding to each group of regions. Then, the electronic device can take the sum of 3 times of the standard deviation Std and the mean mean as the mileage upper limit value corresponding to each group of regions.

[0103] For example, a group of regions in Hangzhou is taken as an example, the first encoding data of a region in the group of regions is wtmsh8, and the first encoding data of another region in the group of regions is wtmk72. The electronic device can obtain all the target historical travel data corresponding to the group of regions. Then, the electronic device can calculate the mean mean equal to 58.542279 and the standard deviation Std equal to 9.675643 of the driving distances in all the target historical travel data. The electronic device can further obtain the mileage upper limit value equal to 87.5692 corresponding to the group of regions by substituting the mean mean and the standard deviation Std into the above formula (2).

[0104] Alternatively, the electronic device can determine the first quartile Q1 equal to 52 km, the second quartile Q2 equal to 53.1 km, and the third quartile Q3 equal to 65.6 km according to the driving distances in all the target historical travel data, as shown in the following table:Figure 8 Assuming that the preset multiple k takes the value of 1.5, the electronic device can substitute 52km, 65.6km and 1.5 into the above formula (1) to obtain the upper mileage limit corresponding to the group of regions equal to 86.

[0105] In the embodiments of the present application, the electronic device can update the upper mileage limit corresponding to each group of regions according to a preset update period, or receive and respond to a request operation for triggering an update to update the upper mileage limit corresponding to each group of regions. The preset update period can be indicated by the first operation.

[0106] For example, the preset update period can be a quarter, and the electronic device can determine the upper mileage limit corresponding to each group of regions according to the historical travel data from January 2021 to March 2021. Then, the electronic device can determine new upper mileage limits according to the historical travel data from April 2021 to June 2021.

[0107] In the embodiments of the present application, the electronic device can determine the upper mileage limit corresponding to each group of regions in at least one group of regions according to a plurality of historical travel data within a target time period, and save it. Then, the electronic device can use the saved upper mileage limit to determine whether the driving mileage in the travel data of a vehicle is abnormal.

[0108] Specifically, as shown in Figure 9 The abnormal trajectory recognition method provided by the embodiments of the present application can further include S601-S604.

[0109] S601, the electronic device obtains the travel data of a vehicle in a target region; the travel data includes the boarding position, the alighting position and the driving mileage.

[0110] The electronic device can obtain the travel data of the vehicle after the target time period. For example, the electronic device can obtain the travel data of the vehicle in the target region.

[0111] S602, the electronic device determines a first region to which the boarding position belongs and a second region to which the alighting position belongs.

[0112] The electronic device can determine the first region and the second region according to the boarding position (such as the boarding latitude and longitude) and the alighting position (such as the alighting latitude and longitude) in the travel data. The first region includes the boarding position, and the second region includes the alighting position.

[0113] It should be noted that the specific process of determining the first region and the second region according to the boarding position and the alighting position can be referred to the detailed introduction of the electronic device determining a group of regions including the boarding position and the alighting position, which will not be described here.

[0114] S603, the electronic device acquires an upper bound of mileage corresponding to the travel data with the first region and the second region as start and end points.

[0115] The electronic device can determine, from the saved at least one upper bound of mileage corresponding to at least one region, the upper bound of mileage with the first region and the second region as start and end points as the upper bound of mileage corresponding to the travel data.

[0116] In some embodiments, the confidence of the upper bound of mileage corresponding to the travel data is greater than or equal to a preset confidence threshold. If the confidence of the upper bound of mileage with the first region and the second region as start and end points determined by the electronic device from the at least one upper bound of mileage is less than the preset confidence threshold, the electronic device can determine that there is no upper bound of mileage corresponding to the travel data.

[0117] S604, if the driving mileage is greater than or equal to the upper bound of mileage corresponding to the travel data, the electronic device determines that the travel data is abnormal travel data.

[0118] The electronic device determines that the travel data is abnormal travel data with abnormal driving mileage when the driving mileage in the travel data is greater than or equal to the upper bound of mileage corresponding to the travel data, and marks and saves the travel data as abnormal. The electronic device determines that the travel data is not abnormal travel data when the driving mileage in the travel data is less than the upper bound of mileage corresponding to the travel data, and can also save the travel data, i.e. the travel data is new historical travel data.

[0119] In the embodiments of the present application, after determining that the travel data is abnormal travel data, the electronic device can also count the number of abnormal travel data of the driver in the travel data. If the total number of abnormal travel data is greater than or equal to a preset number, it means that the driver has a large number of abnormal driving mileage, and needs to be paid attention to. Further, the electronic device can send a prompt information for prompting to pay attention to the driver.

[0120] Specifically, as shown in FIG. 6, after S604, the method can further include S605-S606. Figure 10

[0121] S605, the electronic device counts the number of abnormal travel data of the driver indicated by the driver information in the travel data within a preset time length according to the driver information in the travel data.

[0122] The electronic device can save the determined abnormal travel data. Then, the electronic device can determine all abnormal travel data of the driver indicated by the driver information from the saved abnormal travel data, and count the number of abnormal travel data.

[0123] ​The preset time length can refer to a period of time before the travel data is obtained. For example, one month, one quarter, or the like before the travel data is obtained.

[0124] In S606, the electronic device sends a prompt information if the number of abnormal travel data is greater than or equal to a preset number. The prompt information indicates that the driving mileage of the driver indicated by the driver information is abnormal.

[0125] The electronic device can display the prompt information through a display screen, or play the prompt information through a voice, and the like.

[0126] The preset number and the preset time length are related. The longer the preset time length is, the greater the preset number is. The preset time length and the preset number can be indicated by the first operation.

[0127] The prompt information can include specific content of the abnormal travel data of the driver within the preset time length, the number of abnormal travel data, and the like.

[0128] It can be understood that, in order to exclude the possibility that the abnormal travel data of the driver occurs once or several times is accidental, a preset number of abnormal travel data within a preset time length can be set. If the number of abnormal travel data of a driver within a preset time length exceeds the preset number, it can be confirmed that the driver intentionally tampers with the driving mileage, and the electronic device can send a prompt information.

[0129] It should be noted that in S605-S606, the electronic device counts the number of abnormal travel data in the dimension of the driver. In addition, the electronic device can also count the number of abnormal travel data in the dimension of the vehicle. The process of counting the number of abnormal travel data in the dimension of the vehicle by the electronic device can be referred to the specific introduction of S605-S606, which will not be described here.

[0130] In an embodiment of the present application, a group of regions can include region A and region B, and the target historical travel data corresponding to the group of regions can include a first target historical travel data of the vehicle from region A to region B, and can also include a second target historical travel data of the vehicle from region B to region A. The first target historical travel data and the second target historical travel data correspond to the same group of regions (i.e., region A and region B). Then, the electronic device can use a key (which can be referred to as a first key) to represent the group of regions, and whether the first target historical travel data or the second target historical travel data, the corresponding group of regions can be represented by the first key.

[0131] The electronic device can use the first encoded data from two regions within this set of regions, according to a preset character order, to form a unique first key representing this set of regions. Specifically, the characters in the first encoded data all belong to the 32 characters 0-9 and bz (excluding a, i, l, o). The order of these characters can include: the order from 0 to 9, and the order from b to z (excluding a, i, l, o). The order of these characters can also include: 0-9 preceding bz (excluding a, i, l, o). Then, based on this character order, the electronic device can start from the first character of the first encoded data in region A and the first character of the first encoded data in region B, compare the order of every two characters, and concatenate the first encoded data with the character that comes first before the first encoded data with the character that comes later to obtain the first key.

[0132] For example, the first encoded data for region A is wtmsh8, and the first encoded data for region B is wtmk72. The first three characters of wtmsh8 are the same as the first three characters of wtmk72, and the fourth character 's' in wtmsh8 follows the fourth character 'k' in wtmk72. Therefore, the electronic device can obtain the first key representing region A and region B as wtmk72+wtmsh8. Furthermore, the regions corresponding to the first and second target historical travel data can both be represented using wtmk72+wtmsh8.

[0133] In some embodiments, the electronic device can determine a first key composed of first coded data from two regions in each group of regions. Furthermore, the electronic device can obtain multiple first keys. Then, the electronic device stores the multiple first keys and the corresponding mileage upper bound value in a database. Furthermore, after acquiring travel data for a vehicle, the electronic device can determine a key (which may be called a second key) corresponding to the travel data. This second key represents the first region and the second region to which the alighting and pick-up locations in the travel data belong, respectively. The electronic device then uses this second key to search the database for the mileage upper bound value corresponding to the second key.

[0134] Specifically, such as Figure 11 As shown, in this method, S402 may include S701, S403 may include S702, and S404 may include S703-S704. The method may also include S601-S606. Specifically, S602 may include S705, S603 may include S706, S604 may include S709, and S606 may include S711.

[0135] S701, the electronic device determines first encoding data of each of at least one region in the target region; the first encoding data is used to represent a position of the region.

[0136] It should be noted that the specific process of S701 can be referred to the detailed description of the first encoding data in S402 described above, and details are not repeated here.

[0137] S702, the electronic device determines a plurality of first keywords and target historical travel data corresponding to each of the plurality of first keywords according to the boarding position and the alighting position in the plurality of historical travel data and the position information of each of the at least one region; each of the first keywords is used to represent a group of regions.

[0138] The first keyword corresponding to each group of regions can be composed by splicing the first encoding data of two regions in each group of regions according to the preset order of characters.

[0139] It should be noted that the specific process of S702 can be referred to the detailed description of determining each group of regions and the target historical travel data corresponding thereto in S403 described above, and the detailed description of the electronic device generating the first keyword, and details are not repeated here.

[0140] S703, the electronic device determines a mileage upper limit value corresponding to each keyword and a confidence of the mileage upper limit value according to a travel mileage in the target historical travel data corresponding to each keyword.

[0141] The confidence of the mileage upper limit value corresponding to each keyword can be a number of the target historical travel data corresponding to each keyword.

[0142] S704, the electronic device saves the mileage upper limit value corresponding to each keyword.

[0143] It should be noted that the specific process of S703-S704 can be referred to the detailed description of determining the mileage upper limit value corresponding to each group of regions and the confidence of the mileage upper limit value in S404 described above, and details are not repeated here.

[0144] S705, the electronic device determines a first region to which the boarding position belongs and a second region to which the alighting position belongs from the at least one region, and determines a second keyword corresponding to the first region and the second region.

[0145] The electronic device can first determine the second encoding data of the first region to which the boarding position belongs and the second encoding data of the two second regions to which the alighting position belongs. The electronic device then obtains the second keyword according to the second encoding data of the first region and the second encoding data of the second region.

[0146] The second keyword corresponding to the first region and the second region can be formed by splicing the first preset number of characters in the second encoded data of the first region and the first preset number of characters in the second encoded data of the second region in the preset order of the characters.

[0147] For example, the preset number of bits m=6, and the second encoded data of the two second regions includes: wtw37qd2 and wtw37re1. The electronic device splices wtw37q in wtw37qd2 and wtw37r in wtw37re1 in the preset order of the characters. The first five characters in wtw37q are the same as the first five characters in wtw37q. The order of the sixth character q in wtw37q is after the sixth character r in wtw37r, and the electronic device can splice wtw37q and wtw37r, and can obtain the second keyword as wtw37r+wtw37q.

[0148] S706, the electronic device obtains the mileage upper limit value corresponding to the second keyword and the confidence of the mileage upper limit value from the mileage upper limit values corresponding to the plurality of first keywords.

[0149] The mileage upper limit value corresponding to the second keyword is the mileage upper limit value with the first region and the second region as the start and end points among the mileage upper limit values corresponding to the plurality of first keywords.

[0150] It should be noted that the specific process of S706 can refer to the detailed introduction of determining the mileage upper limit value corresponding to each group of regions and the confidence of the mileage upper limit value in S603 described above, which will not be described here.

[0151] S707, the electronic device determines whether the confidence of the mileage upper limit value corresponding to the second keyword is not less than a preset confidence threshold.

[0152] If the confidence of the mileage upper limit value corresponding to the second keyword is not less than (i.e., greater than or equal to) the preset confidence threshold, the electronic device performs S708. If the confidence of the mileage upper limit value corresponding to the second keyword is less than the preset confidence threshold, the electronic device can end the identification process.

[0153] S708, the electronic device determines whether the driving mileage in the travel data is not less than the mileage upper limit value corresponding to the second keyword.

[0154] If the driving mileage in the travel data is not less than (i.e., greater than or equal to) the mileage upper limit value corresponding to the second keyword, the electronic device performs S709. If the driving mileage in the travel data is less than the mileage upper limit value corresponding to the second keyword, the electronic device can end the identification process.

[0155] S709, the electronic device determines that the travel data is abnormal travel data, and saves the travel data as abnormal travel data.

[0156] It should be noted that the specific process of S709 can refer to the detailed description of determining that the travel data is abnormal travel data in S604 described above, and will not be described here.

[0157] S710, the electronic device determines whether the number of abnormal travel data is not less than a preset number.

[0158] If the number of abnormal travel data is not less than (i.e., greater than or equal to) the preset number, the electronic device performs S711. If the number of abnormal travel data is less than the preset number, the electronic device can end the identification process.

[0159] S711, the electronic device sends a prompt information.

[0160] It should be noted that the specific process of S711 can refer to the detailed description of sending a prompt information in S606 described above, and will not be described here.

[0161] The above mainly introduces the scheme provided by the embodiments of the present application from the perspective of method. In order to realize the above functions, it contains the hardware structure and / or software module corresponding to the execution of each function. The technical person skilled in the art should easily realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in the present application can be realized in the form of hardware or combination of hardware and computer software. Whether a certain function is executed in hardware or computer software driven hardware depends on the specific application and design constraints of the technical scheme. The professional technical person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0162] The embodiments of the present application also provide an abnormal trajectory identification device. As shown in Figure 12 Fig. 8 is a structural schematic diagram of an abnormal trajectory identification device 800 provided by the embodiments of the present application. The device 800 can include a data acquisition module 801, a position analysis module 802 and an abnormal identification module 803.

[0163] The data acquisition module 801 is configured to acquire travel data of a vehicle, and the travel data includes a boarding position, an alighting position and a driving mileage. The position analysis module 802 is further configured to determine a first area to which the boarding position belongs and a second area to which the alighting position belongs. The abnormal identification module 803 is configured to acquire an upper mileage limit value corresponding to the travel data with the first area and the second area as start and end points, and determine that the travel data is abnormal travel data if the driving mileage is greater than or equal to the upper mileage limit value corresponding to the travel data.

[0164] In another possible implementation manner, the travel data further includes driver information.

[0165] The abnormality identification module 803 is further configured to: according to the driver information, count a number of abnormal travel data of the driver indicated by the driver information within a preset time length; and if the number of abnormal travel data is greater than or equal to a preset number of times, send a prompt information.

[0166] In a possible implementation manner, the apparatus 800 further includes an upper limit value determination module 804.

[0167] The data acquisition module 801 is further configured to acquire a plurality of historical travel data of vehicles in the target region, and the historical travel data includes a pickup location, a drop-off location and a travel mileage. The position analysis module 802 is further configured to: determine respective position information of at least one region in the target region; according to the pickup location and the drop-off location in the plurality of historical travel data and the respective position information of the at least one region, determine at least one group of regions and target historical travel data corresponding to each group of regions in the at least one group of regions. The upper limit value determination module 804 is configured to, for each group of regions, determine a mileage upper limit value corresponding to each group of regions according to the travel mileage in the target historical travel data corresponding to each group of regions.

[0168] The one region and the other region in each group of regions respectively include the pickup location and the drop-off location in the target historical travel data. The mileage upper limit value corresponding to each group of regions is a mileage upper limit value with the two regions in each group of regions as start and end points.

[0169] In another possible implementation manner, the position analysis module 802 is specifically configured to: divide the target region into at least one region with the same size by using a preset encoding algorithm, and determine first encoding data of each region in the at least one region; the first encoding data of each region is the position information of each region; the preset encoding algorithm includes a GeoHash algorithm; for each historical travel data in the plurality of historical travel data, respectively convert the pickup location and the drop-off location in the historical travel data by using the preset encoding algorithm to obtain a pair of second encoding data; according to the pair of second encoding data, determine a group of regions from the at least one region, and determine that the historical travel data belongs to target historical travel data corresponding to the group of regions; the first encoding data of the group of regions includes the pair of second encoding data.

[0170] In another possible implementation, the location analysis module 802 is specifically used to: use a preset encoding algorithm to convert the latitude and longitude of the target area, and extract the first preset number of GeoHash characters from the converted encoded data to obtain at least one area and first encoded data for each area; the first encoded data for each area is the first preset number of GeoHash characters in the converted encoded data within each area; from at least one area, determine that the area whose first encoded data is equal to the first preset number of characters of any one of the second encoded data in a pair belongs to a group of areas.

[0171] In another possible implementation, the upper bound determination module 804 is specifically used to: sort the driving mileage in the target historical travel data corresponding to each group of regions when the total number of target historical travel data corresponding to each group of regions is greater than or equal to a preset confidence threshold, and obtain the sorted driving mileage; determine a first value and a second value from the sorted driving mileage; wherein the first value is less than the median of the sorted driving mileage; the second value is greater than the median of the sorted driving mileage; multiply the difference between the second value and the first value by a preset multiple, and then sum the difference with the second value to obtain the upper bound value of the mileage corresponding to each group of regions.

[0172] Of course, the abnormal trajectory recognition device 800 provided in this application embodiment includes, but is not limited to, the above-mentioned modules.

[0173] Another embodiment of this application also provides an electronic device. For example... Figure 13 As 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, which includes computer instructions. When the processor 902 executes the computer instructions, the electronic device 900 performs each step of the method flow shown in the above method embodiment.

[0174] In actual implementation, the data acquisition module 801, the location analysis module 802, the anomaly detection module 803, and the upper bound determination module 804 can be composed of... Figure 9 The processor 902 shown calls the computer program code in memory 901 to implement this. The specific execution process can be found in the description of the abnormal trajectory recognition method section above, and will not be repeated here.

[0175] Another embodiment of this application provides a computer-readable storage medium storing computer instructions that, when executed on an electronic device, cause the electronic device to perform each step of the method flow shown in the above method embodiment.

[0176] Another embodiment of the present application further provides a chip system applied to an electronic device. The chip system comprises one or more interface circuits and one or more processors. The interface circuits and the processors are interconnected through lines. The interface circuits are configured to receive signals from a memory of the electronic device and send the signals to the processors, the signals comprising computer instructions stored in the memory. When the processors of the electronic device execute the computer instructions, the electronic device performs each step performed by the electronic device in the method flow illustrated in the method embodiments.

[0177] Another embodiment of the present application further provides a computer program product comprising computer instructions, which, when executed on an electronic device, cause the electronic device to perform each step performed by the electronic device in the method flow illustrated in the method embodiments.

[0178] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product comprises one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions according to the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transferred from one website, computer, server or data center to another website, computer, server or data center through wired (for example, coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (for example, infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium accessible by a computer or a data storage device comprising one or more servers, data centers, etc. integrated with the medium. The available medium can be a magnetic medium (for example, floppy disk, hard disk, magnetic tape), an optical medium (for example, DVD) or a semiconductor medium (for example, solid state disk (SSD)) and the like.

[0179] The above is only a specific embodiment of the present application. Those skilled in the art can think of changes or replacements based on the specific embodiments provided by the present application, which should be covered within the protection scope of the present application.

Claims

1. An abnormal trajectory recognition method, characterized in that, The method includes: Acquire travel data of vehicles within the target area; the travel data includes boarding location, alighting location, and mileage. From at least one region of the target region, determine the first region to which the boarding location belongs and the second region to which the alighting location belongs, and determine the second keyword corresponding to the first region and the second region; the second keyword corresponding to the first region and the second region is formed by concatenating the characters of the first preset number of characters in the second encoded data of the first region and the characters of the second encoded data of the second region. Obtain the mileage upper bound value corresponding to the second keyword from the mileage upper bound values ​​corresponding to each of the multiple first keywords; If the mileage of the travel data is greater than or equal to the upper limit of the mileage corresponding to the second keyword, then the travel data is determined to be abnormal travel data. The method further includes: A preset encoding algorithm is used to determine the first encoded data of each region in at least one region of the target region; the first encoded data is the first preset number of characters in the encoded data after latitude and longitude conversion of each region, which is used to characterize the location of the region; For each of the historical travel data in the multiple historical travel data, the preset encoding algorithm is used to convert the boarding location and alighting location in the historical travel data respectively to obtain a pair of second encoded data; From the at least one region, determine that the region whose first encoded data is equal to the first preset number of characters of any one of the pair of second encoded data belongs to a group of regions, and determine that the historical travel data belongs to the target historical travel data corresponding to the group of regions; Multiple first keywords are determined; each first keyword is used to characterize the group of regions; the first keyword corresponding to each group of regions is formed by concatenating the first encoded data of two regions in each group of regions; Based on the mileage in the target historical travel data corresponding to each first keyword, determine the upper limit value of the mileage corresponding to each first keyword.

2. The method according to claim 1, characterized in that, The travel data also includes driver information; The method further includes: Based on the driver information, count the number of abnormal travel data points of the driver indicated by the driver information within a preset time period; If the number of abnormal travel data is greater than or equal to a preset number, a prompt message will be issued.

3. The method according to claim 1, characterized in that, The step of using a preset encoding algorithm to determine the first encoded data of each region in at least one region of the target region includes: Using the preset encoding algorithm, the target region is divided into at least one region of the same size, and the first encoded data of each region in the at least one region is determined.

4. The method according to claim 3, characterized in that, The step of using the preset encoding algorithm to divide the target region into at least one region of the same size, and determining the first encoded data of each of the at least one region, includes: The latitude and longitude of the target area are converted using the preset encoding algorithm, and the GeoHash characters of the first preset number of digits are extracted from the converted encoded data to obtain the at least one area and the first encoded data of each area; the first encoded data of each area is the GeoHash characters of the first preset number of digits in the converted encoded data of each area.

5. The method according to claim 1, characterized in that, The step of determining the upper bound of the mileage corresponding to each first keyword based on the mileage in the target historical travel data corresponding to each first keyword includes: If the total number of target historical travel data corresponding to the first keyword is greater than or equal to the preset confidence threshold, the driving mileage in the target historical travel data corresponding to the first keyword is sorted to obtain the sorted driving mileage. A first value and a second value are determined from the sorted mileage; wherein the first value is less than the median of the sorted mileage; and the second value is greater than the median of the sorted mileage. The difference between the second value and the first value is multiplied by a preset multiple, and then summed with the second value to obtain the upper limit value of the mileage corresponding to the first keyword.

6. An abnormal trajectory recognition device, characterized in that, The device includes: The data acquisition module is used to acquire travel data of vehicles within the target area; the travel data includes boarding location, alighting location, and mileage. The location analysis module is used to determine, from at least one region of the target area, the first region to which the boarding location belongs and the second region to which the alighting location belongs, and to determine a second keyword corresponding to the first region and the second region; the second keyword corresponding to the first region and the second region is formed by concatenating the first preset number of characters in the second encoded data of the first region and the first preset number of characters in the second encoded data of the second region; The anomaly detection module is used to: obtain the mileage upper limit value corresponding to the second keyword from the mileage upper limit values ​​corresponding to each of the multiple first keywords; if the mileage of the travel data is greater than or equal to the mileage upper limit value corresponding to the second keyword, then determine that the travel data is abnormal travel data; The location analysis module is also used for: A preset encoding algorithm is used to determine the first encoded data of each region in at least one region of the target region; the first encoded data is the first preset number of characters in the encoded data after latitude and longitude conversion of each region, which is used to characterize the location of the region; For each of the historical travel data in the multiple historical travel data, the preset encoding algorithm is used to convert the boarding location and alighting location in the historical travel data respectively to obtain a pair of second encoded data; From the at least one region, determine that the region whose first encoded data is equal to the first preset number of characters of any one of the pair of second encoded data belongs to a group of regions, and determine that the historical travel data belongs to the target historical travel data corresponding to the group of regions; Multiple first keywords are determined; each first keyword is used to characterize the group of regions; the first keyword corresponding to each group of regions is formed by concatenating the first encoded data of two regions in each group of regions; The upper bound value determination module is used to determine the mileage upper bound value corresponding to each first keyword based on the driving mileage in the target historical travel data corresponding to each first keyword.

7. The apparatus according to claim 6, characterized in that, The travel data also includes driver information; the anomaly identification module is further configured to: count the number of abnormal travel data points of the driver indicated by the driver information within a preset time period based on the driver information; and issue a prompt message if the number of abnormal travel data points is greater than or equal to a preset number of times. The location analysis module is specifically used for: Using a preset encoding algorithm, the target region is divided into at least one region of the same size, and the first encoded data of each region in the at least one region is determined; The location analysis module is specifically used for: The latitude and longitude of the target area are converted using the preset encoding algorithm, and the GeoHash characters of the first preset number of digits are extracted from the converted encoded data to obtain the at least one area and the first encoded data of each area; the first encoded data of each area is the GeoHash characters of the first preset number of digits in the converted encoded data of each area. The upper bound value determination module is specifically used for: If the total number of target historical travel data corresponding to each group of regions is greater than or equal to a preset confidence threshold, the driving mileage in the target historical travel data corresponding to each group of regions is sorted to obtain the sorted driving mileage. A first value and a second value are determined from the sorted mileage; wherein the first value is less than the median of the sorted mileage; and the second value is greater than the median of the sorted mileage. The difference between the second value and the first value is multiplied by a preset multiple, and then summed with the second value to obtain the upper limit value of the mileage corresponding to each group of regions.

8. An electronic device, characterized in that, The electronic device includes a memory and a processor; the memory and the processor are coupled; the memory is used to store computer program code, the computer program code including computer instructions; When the processor executes the computer instructions, the electronic device performs the abnormal trajectory recognition method as 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 that, when executed on an electronic device, cause the electronic device to perform the abnormal trajectory recognition method as described in any one of claims 1-5.

Images