A method and system for identifying illegal positions of a vehicle

Abstract

The present invention provides a method and system for identifying illegal driving positions. The method includes: obtaining in real time a plurality of basic coordinate data generated by a target vehicle during driving; screening the basic coordinate data by using a preset processing rule to obtain valid coordinate data; determining a reference coordinate, and using the reference coordinate to perform motion feature recognition on each of the valid coordinate data to identify and / or eliminate illegal coordinate data in the valid coordinate data. Through the present invention, it is realized to dynamically identify whether the driver's position information is normal and legal in the online car-hailing service scenario, and timely perform data feature analysis, identification and correction on the position information uploaded by the online car-hailing driver, so as to avoid user complaints and the intervention of manual customer service, and ensure the best driver-passenger experience.

Description

Technical Field

[0001] The present invention relates to the technical field of online car-hailing services, and particularly to a method and system for identifying illegal driving positions. Background Art

[0002] In the online car-hailing industry, the road environments in which drivers travel vary widely. The GPS signals are weak on viaducts, in tunnels or in remote areas, and the accuracy of the drivers' location information cannot be guaranteed, so there may be some location information that deviates from the driving track. At the same time, in today's technologically advanced era, there are also some grey-market drivers who use software to cheat and deliberately create illegal location information. When abnormal location information is reported to the online car-hailing system, it will affect the calculation of various fees on the online car-hailing platform and even the taxi fares of users, resulting in customer complaints and manual customer service intervention, seriously reducing the driver-passenger experience. Summary of the Invention

[0003] Therefore, the present invention provides a method and system for identifying illegal driving positions, aiming to solve the technical problems of inaccurate taxi fares and low driver-passenger experience caused by the generation of illegal location information during driving in the prior art.

[0004] To achieve the above object, the present invention adopts the following technical solutions:

[0005] According to a first aspect of the present invention, there is provided a method for identifying illegal driving positions, the method comprising:

[0006] Obtaining in real time a plurality of pieces of coordinate basic data generated during the driving of a target vehicle;

[0007] Screening the coordinate basic data by using a preset processing rule to obtain valid coordinate data;

[0008] Determining a reference coordinate, and performing motion feature recognition on each of the valid coordinate data by using the reference coordinate to identify and / or eliminate illegal coordinate data in the valid coordinate data.

[0009] Further, the coordinate basic data includes at least one of longitude and latitude, driving speed, azimuth angle, altitude, coordinate generation time, coordinate upload time, device acquisition time, positioning type, accuracy, and device type.

[0010] Further, the screening the coordinate basic data by using a preset processing rule to obtain valid coordinate data includes:

[0011] Judging whether the positioning type in each piece of the coordinate basic data is a preset positioning type, and eliminating the coordinate basic data whose positioning type is not the preset positioning type; and / or,

[0012] Determine whether the driving speed in each piece of the coordinate basic data is within the preset speed limit range, and eliminate the coordinate basic data whose driving speed is not within the preset speed limit range; and / or,

[0013] Determine whether the device acquisition time in each piece of the coordinate basic data is before the current server time, and eliminate the coordinate basic data whose device acquisition time is not before the current server time; and / or,

[0014] Determine whether the coordinate accuracy in each piece of the coordinate basic data meets the preset accuracy requirement, and eliminate the coordinate basic data whose coordinate accuracy does not meet the preset accuracy requirement.

[0015] Further, before determining the reference coordinate, the method further includes:

[0016] Divide the valid coordinate data into multiple coordinate data packets in chronological order, and each coordinate data packet contains a preset number of valid coordinate data.

[0017] Further, the motion feature recognition includes:

[0018] Determine whether the longitude and latitude of the valid coordinate data to be recognized are the same as those of the reference coordinate, and regard the valid coordinate data with the same longitude and latitude as the reference coordinate as illegal coordinate data and / or eliminate it; and,

[0019] Determine whether the device acquisition time of the valid coordinate data to be recognized is greater than the device acquisition time of the reference coordinate, and regard the valid coordinate data with the device acquisition time less than or equal to the reference coordinate as illegal coordinate data and / or eliminate it; and,

[0020] Calculate the average speed and / or acceleration displacement between the valid coordinate data to be recognized and the reference coordinate, and regard the valid coordinate data with the average speed greater than the average speed threshold and / or the acceleration displacement greater than the acceleration displacement threshold as illegal coordinate data and / or eliminate it; and / or,

[0021] Calculate the azimuth displacement between the valid reference coordinate to be recognized and two reference coordinates, and regard the valid coordinate data with the azimuth displacement greater than the azimuth displacement threshold as illegal coordinate data and / or eliminate it.

[0022] Further, for determining the reference coordinate and performing motion feature recognition on each piece of the valid coordinate data by using the reference coordinate, it includes:

[0023] Take the first valid coordinate data in the first coordinate data packet as the reference coordinate, and sequentially perform motion feature recognition on the other valid coordinate data in the first coordinate data packet to identify the legal coordinate data in the first coordinate data packet;

[0024] For subsequent coordinate data packets, use the last valid coordinate data in the coordinate data packets before the said coordinate data packet as the reference coordinate, and perform motion feature recognition on the valid coordinate data in the said subsequent coordinate data packet;

[0025] If legal coordinate data appears in the valid coordinate data of the said subsequent coordinate data packet, use the said legal coordinate data as the reference coordinate, and perform motion feature recognition on the valid coordinate data after the said legal coordinate data;

[0026] If at least two legal coordinate data accumulate in the valid coordinate data of the said subsequent coordinate data packet, use the said two legal coordinate data as the reference coordinate, and perform feature joint recognition including azimuth displacement recognition on the valid coordinate data after the said two legal coordinate data.

[0027] Further, the performing motion feature recognition on the other valid coordinate data in the first coordinate data packet in sequence includes:

[0028] If there is no legal coordinate data in the other valid coordinate data before performing motion feature recognition on the current valid coordinate data, use the reference coordinate to perform motion feature recognition on the current valid coordinate data;

[0029] If there is legal coordinate data in the other valid coordinate data before performing motion feature recognition on the current valid coordinate data, use the reference coordinate and the last said legal coordinate data to perform feature joint recognition including azimuth displacement recognition on the current valid coordinate data.

[0030] Further, the method further includes:

[0031] After removing all illegal coordinate data during driving, use the remaining valid coordinate data to perform simulation correction on the driving track.

[0032] Further, the using the remaining valid coordinate data to perform simulation correction on the actual driving track includes:

[0033] Sort the remaining valid coordinate data in chronological order to obtain a coordinate point sequence;

[0034] Find at least one pair of adjacent coordinate points in the coordinate point sequence with a device acquisition time interval greater than a preset time threshold, and generate an adjacent coordinate pair set;

[0035] Obtain the navigation planned track of the target vehicle, and use a route cutting algorithm to determine the driving track segments between the adjacent coordinate points in the adjacent coordinate pair set, and generate a driving track segment set;

[0036] Splice the set of driving track segments into the actual driving track of the target vehicle to generate a driving correction track.

[0037] According to a second aspect of the present invention, the present invention provides a driving illegal position recognition system, the system includes:

[0038] A data acquisition module, configured to acquire in real time a plurality of coordinate basic data generated by a target vehicle during driving;

[0039] A data screening module, configured to screen the coordinate basic data by using a preset processing rule to obtain valid coordinate data;

[0040] A data elimination module, configured to determine a reference coordinate, and perform motion feature recognition on each of the valid coordinate data by using the reference coordinate to identify and / or eliminate illegal coordinate data in the valid coordinate data.

[0041] The present invention adopts the above technical solutions and at least has the following beneficial effects:

[0042] Through the solution of the present invention, a plurality of coordinate basic data generated by a target vehicle during driving are acquired in real time; the coordinate basic data are screened by using a preset processing rule to obtain valid coordinate data; a reference coordinate is determined, and motion feature recognition is performed on each of the valid coordinate data by using the reference coordinate to identify and / or eliminate illegal coordinate data in the valid coordinate data. Thus, the present invention realizes that in the online car-hailing service scenario, it can dynamically identify whether the driver's position information is normal and legal, and timely perform data feature analysis on the position information uploaded by the online car-hailing driver, identify and correct the driver's position information, avoid user complaints and manual customer service intervention, and ensure the best driver-passenger experience.

[0043] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained according to these drawings without creative efforts.

[0045] Figure 1 The flowchart of the driving illegal position recognition method provided by an embodiment of the present invention is shown;

[0046] Figure 2Shows a schematic diagram of the illegal driving position recognition system provided by an embodiment of the present invention;

[0047] Figure 3 Shows a structural schematic diagram of the illegal driving position recognition system provided by another embodiment of the present invention;

[0048] Figure 4 Shows a schematic diagram of the physical structure of a computer device provided by an embodiment of the present invention. Detailed implementation manners

[0049] Hereinafter, exemplary embodiments of the present disclosure will be described in more detail with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art.

[0050] It should be noted that, in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device including a series of elements not only includes those elements but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, elements defined by the statement "comprising..." do not exclude the presence of additional identical elements in the process, method, article or device including the said elements.

[0051] The embodiment of the present invention provides an illegal driving position recognition method, as Figure 1 shown, may at least include the following steps S101 to S103:

[0052] Step S101, obtaining in real time a plurality of coordinate basic data generated during the driving of the target vehicle.

[0053] The coordinate driving data in the embodiment of the present invention may include longitude and latitude, driving speed, azimuth angle, altitude, coordinate generation time, coordinate upload time, device acquisition time, positioning type, accuracy, device type, etc.

[0054] Among them, the positioning type refers to the positioning system type of the coordinate generation device installed on the target vehicle, such as the Amap SDK; the coordinate generation time refers to the time when the coordinate generation device generates real-time coordinate data, the coordinate upload time refers to the time when the coordinate generation device uploads the coordinate data to the server, and the device acquisition time refers to the time when the server receives the coordinate data sent from the coordinate generation device.

[0055] Step S102: Use a preset processing rule to screen the coordinate basic data to obtain valid coordinate data.

[0056] Specifically, the preset processing rules in the embodiments of the present invention include one or more of the following:

[0057] a. Determine whether the positioning type in each piece of coordinate basic data is a preset positioning type, and eliminate the coordinate basic data whose positioning type is not the preset positioning type.

[0058] Preferably, the preset positioning type can be Amap. During the navigation of Amap, the actual position information generated by Amap has passed the internal verification of the Amap SDK and is more accurate.

[0059] b. Determine whether the driving speed in each piece of coordinate basic data is within the preset speed limit range, and eliminate the coordinate basic data whose driving speed is not within the preset speed limit range.

[0060] Among them, the preset speed limit range is the speed limit requirement corresponding to each road type. When the driving speed exceeds the preset speed limit range, it is very likely to be an abnormal coordinate position point.

[0061] c. Determine whether the device acquisition time in each piece of coordinate basic data is before the current server time, and eliminate the coordinate basic data whose device acquisition time is not before the current server time.

[0062] It can be understood that for a piece of coordinate basic data, the coordinate generation time should be earlier than the device acquisition time. If the coordinate generation time is equal to or later than the device acquisition time, or the time interval between the coordinate generation time and the device acquisition time is too long, it means that the coordinate basic data is unreliable.

[0063] d. Determine whether the coordinate accuracy in each piece of coordinate basic data meets the preset accuracy requirement, and eliminate the coordinate basic data whose coordinate accuracy does not meet the preset accuracy requirement.

[0064] It should be noted that the preset accuracy requirement can be set according to actual needs, and the present invention does not limit this. Generally speaking, for the coordinate basic data whose coordinate accuracy does not meet the preset accuracy requirement, it may deviate too far from the predetermined driving track and differ too much from the actual navigation plan.

[0065] In the embodiments of the present invention, through the above preset processing rules, unreliable coordinate basic data can be screened and eliminated to obtain valid coordinate data for subsequent processing.

[0066] Step S103: Determine a reference coordinate, and use the reference coordinate to identify the motion characteristics of each valid coordinate data, so as to identify and / or eliminate illegal coordinate data in the valid coordinate data.

[0067] It should be noted that before identifying the illegal coordinate data, the embodiments of the present invention can also divide the valid coordinate data into multiple coordinate data packets in chronological order, and each coordinate data packet contains a preset number of valid coordinate data.

[0068] That is to say, according to the chronological order, every time k valid coordinate data are accumulated, a coordinate data packet is generated, thus obtaining multiple coordinate data packets. It can be understood that for a single valid coordinate data, it is often impossible to identify the tampered location information data of the behavior of using cheating software only from the basic coordinate features. And in special scenario road conditions, the map coordinates may also have correct basic features but the actual coordinates are not on the road. Therefore, it is necessary to combine multiple coordinates to form a context relationship for overall analysis.

[0069] The motion characteristic identification in the embodiments of the present invention can specifically be carried out through the following steps: judging whether the longitude and latitude of the valid coordinate data to be identified are the same as those of the reference coordinate, and taking the valid coordinate data with the same longitude and latitude as the reference coordinate as illegal coordinate data and / or eliminating them; and, judging whether the device acquisition time of the valid coordinate data to be identified is greater than the device acquisition time of the reference coordinate, and taking the valid coordinate data with the device acquisition time less than or equal to the reference coordinate as illegal coordinate data and / or eliminating them; and, calculating the average speed and / or acceleration displacement between the valid coordinate data to be identified and the reference coordinate, and taking the valid coordinate data with the average speed greater than the average speed threshold and / or the acceleration displacement greater than the acceleration displacement threshold as illegal coordinate data and / or eliminating them; and / or, calculating the azimuth displacement between the valid reference coordinate to be identified and two reference coordinates, and taking the valid coordinate data with the azimuth displacement greater than the azimuth displacement threshold as illegal coordinate data and / or eliminating them.

[0070] It can be understood that if the longitude and latitude of the valid coordinate data are the same as those of the reference coordinate, it indicates that the target vehicle is in a stationary state, and there is no need to perform trajectory analysis on this valid coordinate data; generally speaking, the device acquisition time of the reference coordinate should be earlier than that of the valid coordinate data. If the device acquisition time of the valid coordinate data is earlier than that of the reference coordinate, this valid coordinate data will be excluded as illegal coordinate data; due to the speed reachability and displacement reachability of the target vehicle between the valid coordinate data and the reference coordinate, if the average speed or acceleration displacement of the target vehicle between the valid coordinate data and the reference coordinate exceeds the standard, it indicates that this valid coordinate data is abnormal and needs to be excluded as illegal coordinate data.

[0071] Among them, the calculation formula for the average speed between the valid coordinate data and the reference coordinate is as follows:

[0072] v = S / t

[0073] Among them, v is the average speed between the valid coordinate data and the reference coordinate; S is the spherical distance between the valid coordinate data and the reference coordinate; t is the difference in device acquisition time between the valid coordinate data and the reference coordinate.

[0074] The calculation formula for the acceleration displacement between the valid coordinate data and the reference coordinate is as follows:

[0075] x = (L((v1 + v2) / 2 * t) - S) / t

[0076] Among them, x is the acceleration displacement between the valid coordinate data and the reference coordinate; L is the estimated formal distance between the valid coordinate data and the reference coordinate; v1 is the speed of the vehicle corresponding to the valid coordinate data; v2 is the speed of the vehicle corresponding to the reference coordinate; S is the spherical distance between the valid coordinate data and the reference coordinate; t is the difference in device acquisition time between the valid coordinate data and the reference coordinate.

[0077] In the embodiments of the present invention, when there are two reference coordinates, motion feature recognition can also be performed on the azimuth displacement between the valid reference coordinate and the two reference coordinates, that is, if the target vehicle does not meet the azimuth displacement reachability requirement in the valid coordinate data, it indicates that this valid coordinate data is abnormal and needs to be excluded as illegal coordinate data.

[0078] It should be noted that for the motion feature recognition in the embodiments of the present invention, the valid coordinate data needs to meet all the requirements of longitude and latitude recognition, acquisition time recognition, speed recognition, acceleration displacement recognition, and / or azimuth displacement recognition to be determined as legal coordinate data; if any one does not meet the requirements, it will be excluded as illegal coordinate data.

[0079] Further, in the embodiment of the present invention, for the determination of the reference coordinate, the following rules can be followed: Use the first valid coordinate data in the first coordinate data packet as the reference coordinate, and sequentially perform motion feature recognition on other valid coordinate data in the first coordinate data packet to identify the legal coordinate data in the first coordinate data packet; for subsequent coordinate data packets, use the last valid coordinate data in the coordinate data packet before the current coordinate data packet as the reference coordinate, and perform motion feature recognition on the valid coordinate data in the subsequent coordinate data packet; if legal coordinate data appears in the valid coordinate data of the subsequent coordinate data packet, use the legal coordinate data as the reference coordinate and perform motion feature recognition on the valid coordinate data after the legal coordinate data; if at least two legal coordinate data accumulate in the valid coordinate data of the subsequent coordinate data packet, use the two legal coordinate data as the reference coordinate and perform feature joint recognition including azimuth displacement recognition on the valid coordinate data after the two legal coordinate data.

[0080] It is understandable that for the first coordinate data packet, there is no previous valid coordinate data as a reference. Therefore, the first valid coordinate data in it is used as the reference coordinate, and the motion characteristics of the other valid coordinate data in the first coordinate data packet are identified in sequence to determine whether it is legal coordinate data. During the motion characteristics identification process, two situations may occur: The first situation is that before the motion characteristics of the current valid coordinate data are identified, no legal coordinate data has appeared among the other valid coordinate data in the first coordinate data packet. Then, the first valid coordinate data is continuously used as the reference coordinate to identify the motion characteristics of the current valid coordinate data. Another situation is that before the motion characteristics of the current valid coordinate data are identified, legal coordinate data has appeared among the other valid coordinate data in the first coordinate data packet. Then, the last legal coordinate data before the current valid coordinate data and the first valid coordinate data are used as the reference coordinates to identify the motion characteristics of the current valid coordinate data, including azimuth displacement identification. For the determination of the reference coordinate of the second coordinate data packet, there are also two situations: The first situation is that no legal coordinate data exists among the other valid coordinate data in the first coordinate data packet. Then, the first valid coordinate data in the first coordinate data packet is still used as the reference coordinate to identify the motion characteristics of the valid coordinate data in the second coordinate data packet. Another situation is that legal coordinate data exists among the other valid coordinate data in the first coordinate data packet. Then, the last legal coordinate data in the first coordinate data packet is used as the reference coordinate to identify the motion characteristics of the valid coordinate data in the second coordinate data packet. In addition, during the process of identifying the motion characteristics of subsequent coordinate data packets, if new legal coordinate data appears before the current valid coordinate data, then this legal coordinate data is used as the reference coordinate to identify the motion characteristics of the current valid coordinate data. If two legal coordinate data have accumulated before the current valid coordinate data, then these two legal coordinate data are used as two reference coordinates to identify the motion characteristics of the current valid coordinate data, including azimuth displacement identification. Based on the above rules, the motion characteristics identification is repeatedly executed until the motion characteristics identification of all valid coordinate data is completed, and the legal coordinate data and illegal coordinate data are screened out.

[0081] It can be understood that after eliminating the illegal coordinate data, some of the driving trajectories of the target vehicle are cleared due to illegal coordinates, resulting in incomplete driving trajectories and unable to reflect the true driving trajectory of the target vehicle, which has a greater impact on the billing scenario of online car-hailing. Therefore, after eliminating all illegal coordinate data during driving, the embodiments of the present invention can further simulate and correct the driving trajectory using the remaining valid coordinate data. Specifically, the remaining valid coordinate data can be sorted according to the chronological order to obtain a coordinate point sequence; at least a pair of adjacent coordinate points with a device acquisition time interval greater than a preset time threshold in the coordinate point sequence are found to generate an adjacent coordinate pair set; the navigation planned trajectory of the target vehicle is obtained, and the route cutting algorithm is used to determine the driving trajectory segments between the adjacent coordinate points in the adjacent coordinate pair set to generate a driving trajectory segment set; the driving trajectory segment set is spliced into the actual driving trajectory of the target vehicle to generate a driving corrected trajectory.

[0082] It can be understood that the navigation planned trajectory of the target vehicle is pre-stored in the server database of the embodiments of the present invention and can be retrieved when needed. In addition, the server database can also save and update the reference coordinate data in real time to ensure the accurate identification of illegal coordinate data. In practical applications, the preset time threshold in the embodiments of the present invention can be set according to actual needs, and the present invention does not make any limitations in this regard.

[0083] The embodiments of the present invention provide a method for identifying illegal driving positions, which includes: obtaining multiple pieces of coordinate basic data generated by the target vehicle during driving in real time; screening the coordinate basic data using a preset processing rule to obtain valid coordinate data; determining a reference coordinate, and using the reference coordinate to identify the motion characteristics of each valid coordinate data to identify and / or eliminate the illegal coordinate data in the valid coordinate data. Compared with the single coordinate analysis method of the prior art, the present invention adopts comprehensive and multi-dimensional coordinate data analysis, greatly improving the identification accuracy; introducing a dynamic update mechanism for reference coordinates to ensure the real-time and effectiveness of data; through a multi-step filtering and identification mechanism, comprehensively improving the effect of data cleaning, preventing cheating more comprehensively and effectively, and then correcting the illegal position information to ensure the integrity of the position information.

[0084] Further, as Figure 1 a specific implementation, the embodiments of the present invention provide a system for identifying illegal driving positions, as Figure 2 shown, the system may include: a data acquisition module 210, a data screening module 220, and a data elimination module 230.

[0085] The data acquisition module 210 can be used to obtain multiple pieces of coordinate basic data generated by the target vehicle during driving in real time;

[0086] The data screening module 220 can be used to screen the coordinate basic data by using a preset processing rule to obtain valid coordinate data;

[0087] The data elimination module 230 can be used to determine a reference coordinate and identify the motion characteristics of each valid coordinate data by using the reference coordinate to identify and / or eliminate illegal coordinate data in the valid coordinate data.

[0088] In an optional embodiment, as Figure 3 shown, an illegal position recognition system for a vehicle provided by another embodiment of the present invention further includes: a data partitioning module 240 and a simulation correction module 250.

[0089] The data partitioning module 240 can be used to partition the valid coordinate data into multiple coordinate data packets in chronological order, and each coordinate data packet contains a preset number of valid coordinate data.

[0090] The simulation correction module 250 can be used to simulate and correct the driving trajectory by using the remaining valid coordinate data after eliminating all illegal coordinate data during the driving process.

[0091] Optionally, the data screening module 220 can also be used to determine whether the positioning type in each coordinate basic data is a preset positioning type, and eliminate the coordinate basic data whose positioning type is not the preset positioning type; and / or,

[0092] determine whether the driving speed in each coordinate basic data is within a preset speed limit range, and eliminate the coordinate basic data whose driving speed is not within the preset speed limit range; and / or,

[0093] determine whether the device acquisition time in each coordinate basic data is before the current server time, and eliminate the coordinate basic data whose device acquisition time is not before the current server time; and / or,

[0094] determine whether the coordinate accuracy in each coordinate basic data meets the preset accuracy requirement, and eliminate the coordinate basic data whose coordinate accuracy does not meet the preset accuracy requirement.

[0095] Optionally, the data elimination module 230 can also be used to determine whether the longitude and latitude of the valid coordinate data to be recognized are the same as those of the reference coordinate, and use the valid coordinate data with the same longitude and latitude as the reference coordinate as illegal coordinate data and / or eliminate it; and,

[0096] determine whether the device acquisition time of the valid coordinate data to be recognized is greater than the device acquisition time of the reference coordinate, and use the valid coordinate data whose device acquisition time is less than or equal to the reference coordinate as illegal coordinate data and / or eliminate it; and,

[0097] Calculate the average velocity and / or acceleration displacement between the valid coordinate data to be recognized and the reference coordinates, and use the valid coordinate data with an average velocity greater than the average velocity threshold and / or an acceleration displacement greater than the acceleration displacement threshold as illegal coordinate data and / or eliminate them; and / or,

[0098] Calculate the azimuth displacement between the valid reference coordinates to be recognized and two reference coordinates, and use the valid coordinate data with an azimuth displacement greater than the azimuth displacement threshold as illegal coordinate data and / or eliminate them.

[0099] Optionally, the data elimination module 230 can also be used to use the first valid coordinate data in the first coordinate data packet as the reference coordinate, and sequentially perform motion feature recognition on the other valid coordinate data in the first coordinate data packet to identify the legal coordinate data in the first coordinate data packet;

[0100] For subsequent coordinate data packets, use the last valid coordinate data in the coordinate data packet before the current coordinate data packet as the reference coordinate, and perform motion feature recognition on the valid coordinate data in the subsequent coordinate data packets;

[0101] If legal coordinate data appears in the valid coordinate data of the subsequent coordinate data packet, use the legal coordinate data as the reference coordinate, and perform motion feature recognition on the valid coordinate data after the legal coordinate data;

[0102] If at least two legal coordinate data accumulate in the valid coordinate data of the subsequent coordinate data packet, use the two legal coordinate data as the reference coordinates, and perform feature joint recognition including azimuth displacement recognition on the valid coordinate data after the two legal coordinate data.

[0103] Optionally, the data elimination module 230 can also be used to, if before performing motion feature recognition on the current valid coordinate data, the other valid coordinate data does not contain legal coordinate data, use the reference coordinate to perform motion feature recognition on the current valid coordinate data;

[0104] If before performing motion feature recognition on the current valid coordinate data, the other valid coordinate data contains legal coordinate data, use the reference coordinate and the last legal coordinate data to perform feature joint recognition including azimuth displacement recognition on the current valid coordinate data.

[0105] Optionally, the simulation correction module 250 can also be used to sort the remaining valid coordinate data in chronological order to obtain a coordinate point sequence;

[0106] Find at least one pair of adjacent coordinate points in the coordinate point sequence with a device acquisition time interval greater than the preset time threshold, and generate a set of adjacent coordinate pairs;

[0107] Obtain the navigation planning trajectory of the target vehicle, use the route cutting algorithm to determine the driving trajectory segments between adjacent coordinate points in the set of adjacent coordinate pairs, and generate a set of driving trajectory segments;

[0108] Splice the set of driving trajectory segments into the actual driving trajectory of the target vehicle to generate a driving correction trajectory.

[0109] It should be noted that for other corresponding descriptions of each functional module involved in the driving illegal position recognition system provided in the embodiments of the present invention, reference can be made to Figure 1 the corresponding descriptions of the methods shown, which will not be elaborated here.

[0110] Based on the above as Figure 1 shown in the method, correspondingly, the embodiments of the present invention also provide a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the driving illegal position recognition method described in any of the above embodiments are implemented.

[0111] Based on the above as Figure 1 shown in the method and the embodiments of the system as Figure 3 shown, the embodiments of the present invention also provide a physical structure diagram of a computer device, as Figure 4 shown. The computer device may include a communication bus, a processor, a memory, and a communication interface, and may also include an input / output interface and a display device. Among them, each functional unit can complete mutual communication through the bus. The memory stores a computer program, and the processor is used to execute the program stored on the memory and execute the steps of the driving illegal position recognition method described in the above embodiments.

[0112] Those skilled in the art can clearly understand the specific working processes of the above-described system, device, module, and unit, which can refer to the corresponding processes in the foregoing method embodiments. For the sake of brevity, they will not be elaborated here.

[0113] In addition, in each embodiment of the present invention, the functional units may be physically independent of each other, or two or more functional units may be integrated together, or all functional units may be integrated in a processing unit. The above integrated functional units may be implemented in the form of hardware, or in the form of software or firmware.

[0114] Those of ordinary skill in the art can understand that: when the integrated functional units are implemented in software form and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computing device (such as a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present invention when the instructions are run. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs.

[0115] Alternatively, all or part of the steps of implementing the foregoing method embodiments can be completed by hardware related to program instructions (such as a computing device like a personal computer, a server, or a network device, etc.). The program instructions can be stored in a computer-readable storage medium. When the program instructions are executed by a processor of the computing device, the computing device executes all or part of the steps of the methods described in the embodiments of the present invention.

[0116] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that within the spirit and principles of the present invention, they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the corresponding technical solutions to deviate from the protection scope of the present invention.

Claims

1. A method for identifying illegal driving positions, characterized in that: The method comprises: Real-time acquisition of multiple coordinate basic data generated by the target vehicle during driving; Using preset processing rules to filter the coordinate basic data to obtain valid coordinate data; Determine a reference coordinate, and use the reference coordinate to perform motion feature recognition on each of the valid coordinate data to identify and / or remove illegal coordinate data in the valid coordinate data; Before determining the reference coordinates, the method further includes: Dividing the valid coordinate data into a plurality of coordinate data packets in chronological order, each of the coordinate data packets containing a preset number of valid coordinate data; The determining of the reference coordinates and using the reference coordinates to perform motion feature recognition on each of the valid coordinate data includes: Taking the first valid coordinate data in the first coordinate data packet as a reference coordinate, and sequentially performing motion feature recognition on other valid coordinate data in the first coordinate data packet to identify the legal coordinate data in the first coordinate data packet; For a subsequent coordinate data packet, the last valid coordinate data in the coordinate data packet before the coordinate data packet is used as a reference coordinate, and motion feature recognition is performed on the valid coordinate data in the subsequent coordinate data packet; If legal coordinate data appears in the effective coordinate data in the subsequent coordinate data packet, the legal coordinate data is used as a reference coordinate to perform motion feature recognition on the effective coordinate data subsequent to the legal coordinate data; If at least two legal coordinate data are accumulated in the valid coordinate data in the subsequent coordinate data packet, the two legal coordinate data are used as reference coordinates, and feature joint recognition including azimuth displacement recognition is performed on the valid coordinate data subsequent to the two legal coordinate data; The step of sequentially performing motion feature recognition on other valid coordinate data in the first coordinate data packet includes: If, before the motion feature recognition is performed on the current valid coordinate data, the other valid coordinate data does not contain legal coordinate data, the motion feature recognition is performed on the current valid coordinate data using the reference coordinates; If the other valid coordinate data include legal coordinate data before the motion feature recognition is performed on the current valid coordinate data, the reference coordinates and the last legal coordinate data are used to perform feature joint recognition including azimuth displacement recognition on the current valid coordinate data.

2. The method according to claim 1, characterized in that The coordinate basic data includes at least one of longitude and latitude, driving speed, azimuth, altitude, coordinate generation time, coordinate upload time, device acquisition time, positioning type, accuracy and device type.

3. The method according to claim 2, characterized in that The method of screening the coordinate basic data by using a preset processing rule to obtain valid coordinate data includes: Determine whether the positioning type in each piece of the coordinate basic data is a preset positioning type, and eliminate the coordinate basic data whose positioning type is not the preset positioning type; and / or, Determine whether the driving speed in each piece of the coordinate basic data is within a preset speed limit range, and eliminate the coordinate basic data whose driving speed is not within the preset speed limit range; and / or, Determine whether the device acquisition time in each piece of the coordinate basic data is before the current server time, and remove the coordinate basic data whose device acquisition time is not before the current server time; and / or, It is determined whether the coordinate accuracy of each piece of the coordinate basic data meets the preset accuracy requirement, and the coordinate basic data whose coordinate accuracy does not meet the preset accuracy requirement are eliminated.

4. The method according to claim 1, characterized in that: The motion feature recognition includes: Determine whether the valid coordinate data to be identified is the same as the longitude and latitude of the reference coordinates, and treat the valid coordinate data that is the same as the longitude and latitude of the reference coordinates as illegal coordinate data and / or remove it; and, Determine whether the device acquisition time of the valid coordinate data to be identified is greater than the device acquisition time of the reference coordinates, and treat the valid coordinate data whose device acquisition time is less than or equal to the reference coordinates as illegal coordinate data and / or remove them; and Calculate the average speed and / or acceleration displacement between the valid coordinate data to be identified and the reference coordinates, and treat the valid coordinate data with an average speed greater than an average speed threshold and / or an acceleration displacement greater than an acceleration displacement threshold as illegal coordinate data and / or remove them; and / or, The valid reference coordinate to be identified and the azimuth displacement between the two reference coordinates are calculated, and the valid coordinate data with an azimuth displacement greater than an azimuth displacement threshold is regarded as illegal coordinate data and / or is removed.

5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: After eliminating all illegal coordinate data during driving, the remaining valid coordinate data is used to simulate and correct the driving trajectory.

6. The method according to claim 5, characterized in that The method of using the remaining valid coordinate data to simulate and correct the actual driving trajectory includes: Sorting the remaining valid coordinate data in chronological order to obtain a coordinate point sequence; Searching for at least one pair of adjacent coordinate points in the coordinate point sequence whose time interval of acquisition by the device is greater than a preset time threshold, and generating a set of adjacent coordinate pairs; Acquire the navigation planning trajectory of the target vehicle, determine the driving trajectory segments between each of the adjacent coordinate points in the adjacent coordinate pair set by using a route cutting algorithm, and generate a driving trajectory segment set; The driving trajectory segment set is spliced ​​into the actual driving trajectory of the target vehicle to generate a driving correction trajectory.

7. A system for identifying illegal vehicle positions, characterized in that: The system comprises: The data acquisition module is used to acquire multiple coordinate basic data generated by the target vehicle during driving in real time; A data screening module, used to screen the coordinate basic data using preset processing rules to obtain valid coordinate data; A data elimination module, used to determine a reference coordinate, and use the reference coordinate to perform motion feature recognition on each of the valid coordinate data, so as to identify and / or eliminate illegal coordinate data in the valid coordinate data; A data division module is used to divide the valid coordinate data into a plurality of coordinate data packets in chronological order, each coordinate data packet containing a preset number of valid coordinate data; The data rejection module is further used to use the first valid coordinate data in the first coordinate data packet as a reference coordinate, and sequentially perform motion feature recognition on other valid coordinate data in the first coordinate data packet to identify the legal coordinate data in the first coordinate data packet; For the subsequent coordinate data packets, the last valid coordinate data in the coordinate data packet before the coordinate data packet is used as the reference coordinate, and the motion feature recognition is performed on the valid coordinate data in the subsequent coordinate data packets; If legal coordinate data appears in the valid coordinate data in the subsequent coordinate data packet, the legal coordinate data is used as a reference coordinate to perform motion feature recognition on the valid coordinate data subsequent to the legal coordinate data; If at least two legal coordinate data are accumulated in the valid coordinate data in the subsequent coordinate data packet, the two legal coordinate data are used as reference coordinates, and feature joint recognition including azimuth displacement recognition is performed on the valid coordinate data subsequent to the two legal coordinate data; If, before the motion feature recognition is performed on the current valid coordinate data, the other valid coordinate data do not contain legal coordinate data, the motion feature recognition is performed on the current valid coordinate data using the reference coordinates; If other valid coordinate data include legal coordinate data before motion feature recognition is performed on the current valid coordinate data, then the reference coordinates and the last legal coordinate data are used to perform feature joint recognition including azimuth displacement recognition on the current valid coordinate data.

Images