Vehicle use analysis method, apparatus, device and medium based on vehicle trajectory

Abstract

Embodiments of the present application disclose a vehicle use analysis method and device based on vehicle trajectory, equipment and medium. The vehicle running trajectory of a single vehicle is obtained through the vehicle running trajectory data of the vehicle within a preset time, and the candidate trajectory points of the vehicle running trajectory are determined based on the Douglas-Pok road thinning algorithm to remove non-candidate trajectory points and reduce the calculation complexity. Meanwhile, the target running trajectory is determined based on the road data and POI information, so that the target running trajectory of a single vehicle is more in line with the actual vehicle use, the calculation accuracy is improved, and then the target running trajectory of each vehicle is analyzed according to the vehicle use determination rule, so as to obtain the real vehicle use, improve the efficiency of identifying different vehicle uses, improve the travel safety of passengers riding in private cars, greatly reduce the safety hidden danger, and facilitate users.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of transportation, in particular to a vehicle use analysis method and device based on vehicle trajectory, equipment and medium. BACKGROUND

[0002] With the continuous development of technology and the continuous improvement of people's living standards, cars have become an important tool in people's daily life, especially private cars have become the preferred means of transportation for people. However, there are some motor vehicle drivers who use private cars for illegal operation to gain benefits. Since the true purpose of the private car cannot be known, it is easy to cause accidents, which undoubtedly brings unknown safety hazards to passengers. Therefore, in order to improve the safety of passengers traveling by private car, it is necessary to monitor and analyze the true purpose of different private cars. SUMMARY

[0003] Therefore, it is necessary to solve the above problems, and a vehicle use analysis method, device, computer equipment and storage medium based on vehicle trajectory are provided to solve the technical problem that the purpose of the private car cannot be known in the prior art, resulting in low travel safety.

[0004] In a first aspect, the present application provides a vehicle use analysis method based on vehicle trajectory, the method comprising:

[0005] Obtaining vehicle running trajectory data of all vehicles within a preset time, and determining a vehicle running trajectory corresponding to a single vehicle according to the vehicle running trajectory data; wherein the vehicle running trajectory is a curve composed of trajectory points of a single vehicle running;

[0006] Determining candidate trajectory points of the vehicle running trajectory by a Douglas-Pok road thinning algorithm;

[0007] Matching the candidate trajectory points with preset road data and preset POI information at the same time to determine a target running trajectory;

[0008] Analyzing the target running trajectory according to a preset vehicle use determination rule to determine a vehicle use corresponding to the target running trajectory.

[0009] Optionally, the candidate trajectory points of the vehicle running trajectory are determined by the Douglas-Pok road thinning algorithm, comprising:

[0010] Taking the vehicle running trajectory as a candidate curve;

[0011] Taking the starting trajectory point and the ending trajectory point on the candidate curve as candidate trajectory points;

[0012] calculating a vertical distance of each intermediate point to the candidate curve;

[0013] selecting an intermediate point with a maximum vertical distance as an intermediate demarcation point, wherein the maximum vertical distance is greater than or equal to a preset distance threshold;

[0014] taking a straight line formed by connecting the intermediate demarcation point and an adjacent candidate trajectory point as the candidate curve;

[0015] performing the step of taking a starting trajectory point and an ending trajectory point on the candidate curve as a candidate trajectory point until a maximum vertical distance of an intermediate point on the candidate curve to the candidate curve is less than a preset distance threshold;

[0016] taking all the obtained candidate trajectory points as candidate trajectory points of the vehicle running trajectory.

[0017] Optionally, after the step of calculating a vertical distance of each intermediate point to the candidate curve, the method further comprises:

[0018] discarding an intermediate point with a vertical distance to the candidate curve less than a preset distance threshold.

[0019] Optionally, the step of obtaining vehicle running trajectory data of all vehicles within a preset time and determining a vehicle running trajectory corresponding to a single vehicle according to the vehicle running trajectory data comprises:

[0020] obtaining driving messages of all vehicles within a preset time; wherein the driving messages comprise vehicle identifiers, driving geographic coordinates, and driving time of the driving geographic coordinates of each vehicle;

[0021] processing the driving messages to obtain vehicle driving data of all vehicles;

[0022] grouping the vehicle driving data according to vehicle identifiers to obtain single-vehicle driving data;

[0023] sorting the single-vehicle driving data according to driving time to obtain a vehicle running trajectory corresponding to each single vehicle.

[0024] Optionally, the step of matching the candidate trajectory points with preset road data and preset POI information to determine a target running trajectory comprises:

[0025] obtaining road data in an open-source geographic database, wherein the open-source geographic database is configured with a spatial index; and the road data comprises geographic data of each road route;

[0026] obtaining geographic coordinates of all candidate trajectory points;

[0027] matching geographical coordinates of all candidate trajectory points with geographical data of each road route through the spatial index to obtain a candidate road trajectory;

[0028] matching the start trajectory point and the end trajectory point on the candidate road trajectory with preset POI information through the spatial index to obtain a plurality of sub-running trajectories; wherein the POI information is used to indicate a geographical point on a road route;

[0029] taking the plurality of sub-running trajectories as a target running trajectory corresponding to a single vehicle.

[0030] Optionally, the preset vehicle purpose includes a legal operating vehicle and an illegal operating vehicle, and the operating vehicle includes, but is not limited to, a compliant operating vehicle, a network car and a taxi.

[0031] Optionally, the analysis of the target running trajectory according to the preset vehicle purpose determination rule to determine the vehicle purpose corresponding to the target running trajectory includes:

[0032] obtaining a target running trajectory corresponding to each single vehicle; wherein the target running trajectory includes a plurality of sub-running trajectories;

[0033] if there is a sub-running trajectory in the target running trajectory that is regular within a preset driving period, and the start trajectory point and the end trajectory point of the sub-running trajectory are located in a commercial living area, then it is determined that the vehicle purpose corresponding to the target running trajectory is a compliant operating vehicle;

[0034] if there is a sub-running trajectory in the target running trajectory that is irregular within a preset driving period, and the number of occurrences is greater than a preset number, then it is determined that the vehicle purpose corresponding to the target running trajectory is a network car or a taxi;

[0035] if there is a sub-running trajectory in the target running trajectory that indicates to and fro a fixed position within a preset driving period, and the end start point of the target running trajectory is located in a living area, then it is determined that the vehicle purpose corresponding to the target running trajectory is an illegal operating vehicle.

[0036] In a second aspect, the present application provides a vehicle purpose analysis device based on vehicle trajectory, the device comprising:

[0037] an acquisition unit configured to acquire vehicle running trajectory data of all vehicles within a preset time, and determine a vehicle running trajectory corresponding to a single vehicle according to the vehicle running trajectory data; wherein the vehicle running trajectory is a curve composed of trajectory points of a single vehicle running;

[0038] a trajectory point determination unit configured to determine candidate trajectory points of the vehicle running trajectory through a Douglas-Peucker road thinning algorithm.

[0039] a running track determination unit, configured to match the candidate track points with preset road data and preset POI information simultaneously to determine a target running track;

[0040] a judgment unit, configured to analyze the target running track according to a preset vehicle use determination rule to determine a vehicle use corresponding to the target running track.

[0041] In a third aspect, an embodiment of the present application further provides a computer device, including a memory and a processor, the memory stores a computer program, and the computer program is executed by the processor to make the processor execute the following steps:

[0042] an acquisition unit, configured to acquire vehicle running track data of all vehicles within a preset time, and determine a vehicle running track corresponding to each vehicle according to the vehicle running track data; wherein the vehicle running track is a curve composed of track points of a single vehicle;

[0043] a track point determination unit, configured to determine candidate track points of the vehicle running track by a Douglas-Peucker road thinning algorithm;

[0044] a running track determination unit, configured to match the candidate track points with preset road data and preset POI information simultaneously to determine a target running track;

[0045] a judgment unit, configured to analyze the target running track according to a preset vehicle use determination rule to determine a vehicle use corresponding to the target running track.

[0046] In a fourth aspect, an embodiment of the present application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to make the processor execute the following steps:

[0047] an acquisition unit, configured to acquire vehicle running track data of all vehicles within a preset time, and determine a vehicle running track corresponding to each vehicle according to the vehicle running track data; wherein the vehicle running track is a curve composed of track points of a single vehicle;

[0048] a track point determination unit, configured to determine candidate track points of the vehicle running track by a Douglas-Peucker road thinning algorithm;

[0049] a running track determination unit, configured to match the candidate track points with preset road data and preset POI information simultaneously to determine a target running track;

[0050] The judgment unit is used to analyze the target running trajectory according to the preset vehicle use determination rules and determine the vehicle use corresponding to the target running trajectory.

[0051] The embodiments of the present invention have the following beneficial effects:

[0052] The system obtains the trajectory of a single vehicle by collecting vehicle trajectory data within a preset time period. Candidate trajectory points are calculated based on the Douglas algorithm to eliminate non-candidate trajectory points, reducing computational complexity. At the same time, the system determines the target trajectory based on road data and POI information, making the target trajectory of a single vehicle more consistent with the actual use of the vehicle and improving calculation accuracy. Furthermore, the system analyzes the target trajectory of each vehicle according to vehicle usage determination rules to obtain the true purpose of the vehicle, thereby improving the efficiency of identifying different vehicle uses, enhancing passenger safety when traveling in private cars, greatly reducing safety hazards, and providing convenience for users. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0054] in:

[0055] Figure 1 This is a flowchart illustrating the vehicle usage analysis method based on vehicle trajectory in the embodiments of this application;

[0056] Figure 2 For this application Figure 1 A flowchart illustrating the detailed steps of step 101 in the illustrated embodiment;

[0057] Figure 3 For this application Figure 1 A flowchart illustrating the detailed steps of step 102 in the illustrated embodiment;

[0058] Figure 4 For this application Figure 1 A flowchart illustrating the detailed steps of step 103 in the illustrated embodiment;

[0059] Figure 5 This is a schematic diagram of the vehicle usage analysis device based on vehicle trajectory in an embodiment of this application.

[0060] Figure 6 This is a structural block diagram of the computer device in the embodiments of this application. Detailed Implementation

[0061] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described, obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work belong to the scope of protection of the present application.

[0062] Please refer to Figure 1 The flowchart of the vehicle use analysis method based on vehicle trajectory in the embodiments of the present application is shown in the figure, the method comprises:

[0063] Step 101, obtaining vehicle running trajectory data of all vehicles in a preset time, and determining vehicle running trajectory corresponding to each vehicle according to the vehicle running trajectory data; wherein the vehicle running trajectory is a curve composed of trajectory points of single vehicle running;

[0064] In the embodiments of the present application, the vehicle running trajectory data can be the data collected by the positioning device configured on each vehicle, which contains vehicle driving trajectory points of all vehicles. The vehicle running trajectory data includes vehicle identification of each vehicle, driving time of trajectory points of vehicle running, geographical coordinates of trajectory points, driving direction and driving speed and other information data. The geographical coordinates are latitude and longitude coordinates. The vehicle identification is used to uniquely determine the vehicle. That is, the vehicle running trajectory data corresponding to all vehicles can be grouped according to the vehicle identification, so as to obtain the vehicle running trajectory data corresponding to each single vehicle. It should be noted that the vehicle running trajectory data is a discrete trajectory point set, and the vehicle running trajectory corresponding to each single vehicle is a curve composed of discrete trajectory points.

[0065] In this step, obtaining vehicle running trajectory data of all vehicles in a preset time is specifically collecting vehicle running trajectory data of all vehicles driving in a day. The preset time is usually set as a day. Of course, the preset time can be set according to the demand, which is not limited. Based on the vehicle identification corresponding to each trajectory point in the vehicle running trajectory data, the vehicle running trajectory data can be grouped, so as to determine the vehicle running trajectory data corresponding to each single vehicle. After obtaining the vehicle running trajectory data corresponding to each single vehicle, the discrete trajectory points are connected to obtain the vehicle running trajectory corresponding to each single vehicle.

[0066] Step 102, determining candidate trajectory points of the vehicle running trajectory by Douglas-Pok road thinning algorithm;

[0067] In the embodiment of the present application, the Douglas-Peucker road thinning algorithm is a trajectory point thinning algorithm, the thinned points can maintain the general outline of the original trajectory points as much as possible, and some unnecessary points are removed, thereby greatly improving the processing efficiency. The algorithm can greatly retain trajectory points with large spatial feature information and has short running time, reduces the algorithm execution time, and meets the real-time data processing requirements. The principle is to virtually connect a straight line between the first and last points of each curve, calculate the distance between all points and the straight line, find the maximum distance value dmax, compare dmax with the preset distance threshold D: if dmax < D, all intermediate points on the curve are removed; if dmax ≥ D, the corresponding coordinate point of dmax is retained, and the curve is divided into two parts with the point as a boundary, and the algorithm is repeatedly used for the two parts. It should be noted that the size of the control preset distance threshold can control the granularity of thinning.

[0068] In this step, the Douglas-Peucker road thinning algorithm is used to thin the vehicle running trajectory, and the candidate trajectory points closest to the vehicle running trajectory are obtained. That is, the curve composed of sequentially connected candidate trajectory points is approximately equal to the vehicle running trajectory. It should be understood that the candidate trajectory points retain the maximum spatial feature information, so that the curve composed of the connected lines can be equivalent to the vehicle running trajectory.

[0069] Step 103, match the candidate trajectory points with the preset road data and the preset POI information at the same time, and determine the target running trajectory;

[0070] In the embodiment of the present application, the road data is data reflecting the road route, and the road data is stored in an open source road database hbase. The open source road database is configured with a spatial index to query the required information through the spatial index. The POI (Point of Information) is an information point. In a geographic information system, a POI can be a house, a shop, a mailbox, a bus stop, etc. Each POI contains four aspects of information, name, category, coordinate, and classification. Through the POI information point, users can be reminded of the branch of the road condition and the detailed information of the surrounding buildings, and can also conveniently find various places needed in navigation and select the most convenient and smooth road for path planning.

[0071] In this step, the candidate trajectory points obtained in step 102 are matched with the road data in the open source road database, the candidate trajectory points are screened, and the curve composed of the screened candidate trajectory points is close to the actual road condition. At the same time, based on the fact that the POI information point contains detailed road condition information, especially contains geographic coordinates, the matched running trajectory is matched again based on the spatial index and the geographic coordinates (GPS information) of the starting trajectory point and the ending trajectory point of the running trajectory, and finally the target running trajectory is obtained. The target running trajectory is approximately the vehicle running trajectory actually traveled by the single vehicle. The target running trajectory is reduced relative to the trajectory points of the curve composed of the initial candidate trajectory points, thereby reducing the calculation amount and shortening the processing time, thereby improving the processing efficiency.

[0072] It should be noted that the target running trajectory of the single vehicle can be divided into multiple sub-running trajectories based on the POI information point. That is, each sub-running trajectory is composed of a starting trajectory point and an ending trajectory point, and all sub-running trajectories compose the target running trajectory.

[0073] In step 104, the target running trajectory is analyzed according to a preset vehicle use determination rule to determine the vehicle use corresponding to the target running trajectory.

[0074] In the embodiment of the present application, the preset vehicle use determination rule is used to indicate the rule of the vehicle running trajectory of different vehicles. The vehicle use includes legal operating vehicles and illegal operating vehicles, wherein the operating vehicles include but are not limited to compliant operating vehicles, online car hailing vehicles and taxis, etc. such as minivans. The target running trajectory of the single vehicle is analyzed according to whether the running trajectory route rule within the preset time period, the number of times of driving, the region where the starting trajectory point and the ending trajectory point are located, etc. to determine whether there is a target running trajectory that meets the preset vehicle use determination rule, thereby determining the vehicle use corresponding to the target running trajectory. In this way, by identifying the vehicle use of the single vehicle, the safety of riding a vehicle is improved and the safety hidden danger is reduced.

[0075] Based on steps 101 to 104, the vehicle running trajectory of the single vehicle is obtained through the vehicle running trajectory data of the vehicle within the preset time, the candidate trajectory points of the vehicle running trajectory are determined based on the Douglas-Pok road thinning algorithm to remove non-candidate trajectory points and reduce the calculation complexity, the target running trajectory is determined based on the road data and the POI information, so that the target running trajectory of the single vehicle is more consistent with the actual use of the vehicle, the calculation accuracy is improved, and then the target running trajectory of each vehicle is analyzed according to the vehicle use determination rule, thereby obtaining the real use of the vehicle, improving the efficiency of identifying different vehicle uses, improving the safety of passengers riding private cars, greatly reducing safety hidden dangers, and facilitating users.

[0076] In order to further understand the technical solutions of the present application, the following specific embodiments are described as follows:

[0077] In a feasible manner, as shown in Figure 2 the refinement steps of step 101 include:

[0078] S1011, obtaining driving messages of all vehicles within a preset time; wherein the driving messages include vehicle identification, driving geographic coordinates and driving time of each vehicle;

[0079] S1012, processing the driving messages to obtain vehicle driving data of all vehicles;

[0080] S1013, grouping the vehicle driving data according to the vehicle identification to obtain several single vehicle driving data;

[0081] S1014, sorting the single vehicle driving data according to the driving time respectively to obtain the vehicle running track corresponding to each single vehicle.

[0082] Specifically, the driving messages of all vehicle daily driving are obtained by the engine tool spark, and the driving messages are used to record the driving of vehicle daily driving. The driving messages include vehicle identification, driving geographic coordinates and driving time of each vehicle and other data. The driving geographic coordinates can be obtained by satellite positioning, which includes driving longitude coordinate and driving latitude coordinate.

[0083] Then the driving messages are processed, specifically, the effective data of the driving messages are extracted to reduce invalid operations. The information of the vehicle identification, driving geographic coordinates and driving time of the driving geographic coordinates of each vehicle in the driving messages are extracted as effective data, so as to generate an elastic distributed data set based on these effective data. The elastic distributed data set is the vehicle driving data of all vehicles. Based on step 101, the vehicle driving data includes vehicle identification, driving time of trajectory points of vehicle running, geographic coordinates where the trajectory points are located and the like, therefore, the vehicle identification in the vehicle driving data is obtained, the vehicle driving data is grouped according to the vehicle identification to obtain several single vehicle driving data. It can be understood that each single vehicle driving data includes vehicle identification, driving time of trajectory points of vehicle running, geographic coordinates where the trajectory points are located and other information data. Then the discrete trajectory points in each single vehicle driving data are sorted according to the driving time of the trajectory points of vehicle running in time sequence, and then the sorted discrete trajectory points are connected to obtain the vehicle running track corresponding to each single vehicle. It can be understood that the trajectory points on the vehicle running track of each single vehicle are marked with geographic coordinates, driving time and vehicle identification and the like.

[0084] In one possible implementation, as shown in FIG. 10, the refinement step of step 102 includes: Figure 3

[0085] S1021, taking the vehicle running trajectory as a candidate curve;

[0086] S1022, taking the start trajectory point and the end trajectory point on the candidate curve as candidate trajectory points;

[0087] S1023, taking the trajectory points on the candidate curve other than the candidate trajectory points as intermediate points, and calculating the perpendicular distance of each intermediate point to the candidate curve;

[0088] S1024, taking the intermediate point with the maximum perpendicular distance and the maximum perpendicular distance greater than or equal to a preset distance threshold as an intermediate demarcation point;

[0089] S1025, taking the straight line formed by connecting the intermediate demarcation point and the adjacent candidate trajectory point as a candidate curve;

[0090] S1026, performing the step of taking the start trajectory point and the end trajectory point on the candidate curve as candidate trajectory points until the maximum perpendicular distance of the intermediate point on the candidate curve to the candidate curve is less than the preset distance threshold;

[0091] S1027, taking all the candidate trajectory points obtained as the candidate trajectory points of the vehicle running trajectory.

[0092] Specifically, (1) connecting the start trajectory point and the end trajectory point of the vehicle running trajectory, taking other points on the vehicle trajectory point as intermediate points, calculating the perpendicular distance of the intermediate points to the straight line, and finding the point corresponding to the maximum perpendicular distance and greater than the preset distance threshold as the intermediate demarcation point (also referred to as the maximum intermediate point); (2) connecting the intermediate demarcation point and the adjacent candidate trajectory point to obtain two straight lines, which is equivalent to dividing the vehicle running trajectory with the intermediate demarcation point; then repeating (1) (2) until the maximum perpendicular distance is less than the preset distance threshold, i.e., no maximum intermediate point can be found, and then connecting all the maximum intermediate points, the start trajectory point and the end trajectory point in sequence to form a new vehicle running trajectory. The new vehicle running trajectory is similar to the original vehicle running trajectory, but the trajectory points on the new vehicle running trajectory are less than the trajectory points on the original vehicle running trajectory.

[0093] It can be understood that the intermediate points with the perpendicular distance to the candidate curve less than the preset distance threshold are discarded, i.e., unnecessary trajectory points that do not affect the general outline of the vehicle running trajectory are removed, thereby reducing the calculation amount and reducing the calculation complexity.

[0094] In order to better understand steps S1021 to S1027, a specific embodiment is used for illustration as follows:​

[0095] Suppose the preset distance threshold is D, the trajectory points on the vehicle running trajectory A of the vehicle A are:

[0096] 1, 2, 3, 4, 5, 6, 7, 8, 9, 10

[0097] Step 1: determine the starting trajectory point and the ending trajectory point of the vehicle running trajectory A as 1 and 10, and points 2 to 9 as intermediate points of the vehicle running trajectory A;

[0098] Step 2: connect points 1 and 10 to form a straight line L1;

[0099] Step 3: calculate the perpendicular distances of the intermediate points, i.e. points 2 to 9, to the straight line L1 as d2-d9;

[0100] Step 4: select the maximum value of d2-d9, and suppose it is d9, and take d9 as the maximum perpendicular distance of the straight line L1;

[0101] Step 5: if d9≥D, take the trajectory point 9 corresponding to d9 as an intermediate demarcation point, and execute Step 7, at this time, the trajectory points 1, 10 and 9 are reserved as candidate trajectory points; if d9<D, execute Step 6;

[0102] Step 6: stop taking all the obtained candidate trajectory points (the maximum perpendicular distance of the straight line formed by each intermediate point to the adjacent candidate trajectory point is less than the preset distance threshold), points 1 and 10, as the candidate trajectory points of the vehicle running trajectory A;

[0103] Step 7: connect points 9 and 1 to form a straight line L2, and connect points 9 and 10 to form a straight line L3; it is equivalent to dividing the vehicle running trajectory A by the intermediate demarcation point 9;

[0104] It can be seen that the starting trajectory point and the ending trajectory point of the straight line L2 are points 1 and 9, and the remaining trajectory points are intermediate points, and the starting trajectory point and the ending trajectory point of the straight line L3 are points 9 and 10, and the remaining trajectory points are intermediate points;

[0105] Step 8: repeat Step 2 to calculate the perpendicular distances of the intermediate points, i.e. points 2 to 8, to the straight line L2; similarly, calculate the perpendicular distances of the intermediate points, i.e. points 2 to 8, to the straight line L3;

[0106] Step 9: repeat Step 4, and suppose the maximum perpendicular distance of L2 is d4, and the maximum perpendicular distance of L3 is d7;

[0107] Step 10: for L2: repeat Step 5, if d4≥D, take the trajectory point 4 corresponding to d4 as an intermediate demarcation point, execute Step 7, and retain the trajectory points 1, 4, 9 and 10;

[0108] For L3: repeat step 5, if d7≥D, then the trajectory point 7 corresponding to d7 is taken as an intermediate demarcation point, step 7 is performed, and trajectory points 1, 7, 9, and 10 are retained; the straight lines L1, L2, and L3 are summarized, and the points 1, 4, 7, 9, and 10 are taken as candidate trajectory points.

[0109] Similarly, for the straight line L2: if d4

[0110] Finally, the candidate trajectory points obtained are connected to form a curve B, which is approximate to the vehicle running trajectory A and is more simplified and smoother relative to the actual trajectory A.

[0111] In a feasible manner, as shown in FIG. 10, the refinement step of step 103 includes: Figure 4

[0112] S1031, acquiring road data in an open source geographic database, wherein the open source geographic database is configured with a spatial index; the road data includes geographic data of each road route;

[0113] S1032, acquiring geographic coordinates of all candidate trajectory points;

[0114] S1033, matching the geographic coordinates of all candidate trajectory points with the geographic data of each road route through the spatial index to obtain candidate road trajectories;

[0115] S1034, matching the start and end trajectory points on the candidate road trajectories with preset POI information through the spatial index to obtain a plurality of sub-running trajectories; wherein the POI information is used to indicate geographic points on the road route;

[0116] S1035, taking the plurality of sub-running trajectories as target running trajectories corresponding to a single vehicle.

[0117] Specifically, the open source geographic database not only stores road data but also is configured with a spatial index. The road data includes geographic data of each road route. The candidate trajectory points are matched through the geographic data and the spatial index, the non-matching candidate trajectory points are removed to obtain candidate road trajectories, and then the start and end trajectory points on the candidate road trajectories are matched with POI information again through the spatial index to obtain target running trajectories. The target running trajectories include a plurality of sub-running trajectories, that is, the candidate road trajectories are classified through POI information points to obtain a plurality of sub-running trajectories.

[0118] ​In an implementable manner, the refining step of step 105 comprises:

[0119] obtaining a target running track corresponding to each single vehicle; wherein the target running track comprises a plurality of sub-running tracks;

[0120] if there is a sub-running track in the target running track that is regular within a preset driving time period, and the starting track point and the ending track point of the sub-running track are located in a commercial living area, it is determined that the vehicle use corresponding to the target running track is a compliant commercial vehicle;

[0121] if there is a sub-running track in the target running track that is irregular within a preset driving time period, and the number of occurrences is greater than a preset number, it is determined that the vehicle use corresponding to the target running track is a network car or a taxi;

[0122] if there is a sub-running track in the target running track that indicates to and fro a fixed position within a preset driving time period, and the starting point of the target running track is located in a living area, it is determined that the vehicle use corresponding to the target running track is an illegal commercial vehicle.

[0123] Specifically, if the vehicle running track is generally to and fro a fixed two points, and the daily driving end point is in a residential area, the vehicle use can be judged as illegal use, i.e. illegal commercial vehicle; if there are several track lines in the vehicle running track that are relatively regular, such as the track lines are almost consistent, the proportion is high, and the starting point and ending point POI information are residential area and office building, the vehicle use is legal use, i.e. legal commercial vehicle; if the track lines are irregular and the driving frequency is high, the vehicle can be a network car or a taxi.

[0124] In this way, the vehicle running track of a single vehicle is obtained through the vehicle running track data of the vehicle within a preset time, the candidate track points of the vehicle running track are determined based on the Douglas-Puke road thinning algorithm to remove non-candidate track points and reduce the calculation complexity, the target running track is determined based on the road data and POI information, so that the target running track of a single vehicle is more in line with the actual use of the vehicle, the calculation accuracy is improved, and then the target running track of each vehicle is analyzed according to the vehicle use determination rule, so as to obtain the real use of the vehicle, improve the efficiency of identifying different vehicle uses, improve the travel safety of passengers riding private cars, greatly reduce the safety hidden danger, and facilitate users.

[0125] Please refer to Figure 5 The structure of the vehicle use analysis device based on vehicle track in the embodiment of the application is shown in the schematic diagram, which comprises:

[0126] The acquisition unit 10 is configured to acquire vehicle running track data of all vehicles within a preset time, and determine a vehicle running track corresponding to a single vehicle according to the vehicle running track data; wherein the vehicle running track is a curve composed of track points of the single vehicle.

[0127] The track point determination unit 20 is configured to determine candidate track points of the vehicle running track by using a Douglas-Peucker road thinning algorithm.

[0128] The running track determination unit 30 is configured to match the candidate track points with preset road data and preset POI information at the same time, and determine a target running track.

[0129] The judgment unit 40 is configured to analyze the target running track according to a preset vehicle use determination rule, and determine a vehicle use corresponding to the target running track.

[0130] It should be noted that the related content of the acquisition unit 10, the track point determination unit 20, the running track determination unit 30 and the judgment unit 40 can refer to the content described in Figures 1 to 4 , which will not be repeated here.

[0131] In the embodiments of the present application, the vehicle running track of a single vehicle is obtained through the vehicle running track data of the vehicle within a preset time, the candidate track points of the vehicle running track are determined based on the Douglas-Peucker road thinning algorithm, so as to remove the non-candidate track points and reduce the calculation complexity; the target running track is determined based on the road data and the POI information, so that the target running track of the single vehicle is more in line with the actual use of the vehicle, the calculation accuracy is improved, and then the target running tracks of the vehicles are analyzed according to the vehicle use determination rule, so as to obtain the real use of the vehicles, improve the efficiency of identifying different vehicle uses, improve the travel safety of passengers riding in private cars, greatly reduce the safety hazards, and facilitate the user.

[0132] Figure 6 An internal structure diagram of a computer device in an embodiment is shown. The computer device can be a terminal or a server. As shown in Figure 6 , the computer device includes a processor 20, a memory 22 and a communication interface 23 connected through a bus 24. The memory 22 includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system, and can also store a computer program, which is executed by the processor 20, so that the processor implements the age recognition method. The internal memory can also store a computer program, which is executed by the processor 20, so that the processor 20 executes the age recognition method. Those skilled in the art can understand that Figure 6The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. A specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0133] In one embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, the computer program being executed by the processor 20 to cause the processor to perform the following steps:

[0134] Obtaining vehicle running track data of all vehicles within a preset time, and determining a vehicle running track corresponding to a single vehicle according to the vehicle running track data; wherein the vehicle running track is a curve composed of track points of a single vehicle running;

[0135] Determining candidate track points of the vehicle running track by a Douglas-Peucker road thinning algorithm;

[0136] Matching the candidate track points with preset road data and preset POI information at the same time to determine a target running track;

[0137] Analyzing the target running track according to a preset vehicle use determination rule to determine a vehicle use corresponding to the target running track.

[0138] In one embodiment, a computer readable storage medium is provided, storing a computer program, the computer program being executed by a processor to cause the processor to perform the following steps:

[0139] Obtaining vehicle running track data of all vehicles within a preset time, and determining a vehicle running track corresponding to a single vehicle according to the vehicle running track data; wherein the vehicle running track is a curve composed of track points of a single vehicle running;

[0140] Determining candidate track points of the vehicle running track by a Douglas-Peucker road thinning algorithm;

[0141] Matching the candidate track points with preset road data and preset POI information at the same time to determine a target running track;

[0142] Analyzing the target running track according to a preset vehicle use determination rule to determine a vehicle use corresponding to the target running track.

[0143] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The program can be stored in a non-volatile computer readable storage medium, and when the program is executed, the processes of the above-mentioned embodiment methods can be included. Any reference to memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0144] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0145] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A method for vehicle usage analysis based on vehicle trajectory, characterized in that, The method includes: Acquire vehicle trajectory data of all vehicles within a preset time period, and determine the vehicle trajectory of a single vehicle based on the vehicle trajectory data; wherein, the vehicle trajectory is a curve composed of trajectory points of a single vehicle. Candidate trajectory points for the vehicle's running trajectory are determined using the Douglas-Puk road thinning algorithm; The candidate trajectory points are simultaneously matched with preset road data and preset POI information to determine the target running trajectory. The target trajectory is analyzed according to the preset vehicle usage determination rules to determine the vehicle usage corresponding to the target trajectory; The step of analyzing the target trajectory according to a preset vehicle usage determination rule to determine the vehicle usage corresponding to the target trajectory includes: Obtain the target trajectory corresponding to each individual vehicle; wherein, the target trajectory includes several sub-trajectories; If there is a sub-trajectory in the target trajectory that follows a pattern within a preset driving period, and the starting and ending points of the sub-trajectory are located in a commercial and residential area, then the vehicle corresponding to the target trajectory is determined to be a compliant commercial vehicle. If there are sub-trajectories in the target trajectory that are irregular within a preset driving period and appear more often than a preset number of times, then the vehicle corresponding to the target trajectory is determined to be a ride-hailing vehicle or a taxi. If a sub-trajectory in the target trajectory indicates a round trip to a fixed location within a preset travel period, and the starting and ending points of the target trajectory are located in a residential area, then the vehicle corresponding to the target trajectory is determined to be an illegal operating vehicle.

2. The method according to claim 1, characterized in that, The process of determining candidate trajectory points for the vehicle's trajectory using the Douglas-Puk road thinning algorithm includes: The vehicle trajectory is used as a candidate curve; The starting and ending trajectory points on the candidate curves are used as candidate trajectory points; Take the trajectory points on the candidate curve other than the candidate trajectory points as intermediate points, and calculate the vertical distance from each intermediate point to the candidate curve. The midpoint of the maximum vertical distance, which is greater than or equal to a preset distance threshold, is selected as the midpoint. The straight line formed by connecting the intermediate dividing point with the adjacent candidate trajectory points is used as the candidate curve. The step of selecting the starting trajectory point and the ending trajectory point on the candidate curve as candidate trajectory points is performed until the maximum vertical distance from the midpoint on the candidate curve to the candidate curve is less than a preset distance threshold is executed. All the obtained candidate trajectory points are used as candidate trajectory points for the vehicle's running trajectory.

3. The method according to claim 2, characterized in that, The step of taking the trajectory points on the candidate curve other than the candidate trajectory points as intermediate points and calculating the vertical distance from each intermediate point to the candidate curve further includes: Discard any midpoints whose vertical distance to the candidate curve is less than a preset distance threshold.

4. The method according to claim 1, characterized in that, The step of acquiring vehicle trajectory data of all vehicles within a preset time period and determining the vehicle trajectory corresponding to a single vehicle based on the vehicle trajectory data includes: Obtain all vehicle driving messages within a preset time period; wherein, the driving message includes the vehicle identifier, driving geographical coordinates, and driving time at the driving geographical coordinates of each vehicle. The driving messages are processed to obtain the driving data of all vehicles. The vehicle driving data is grouped according to the vehicle identifier to obtain several individual vehicle driving data. The driving data of several individual vehicles are sorted according to the driving time to obtain the vehicle trajectory corresponding to each individual vehicle.

5. The method according to claim 1, characterized in that, The step of simultaneously matching the candidate trajectory points with preset road data and preset POI information to determine the target trajectory includes: Obtain road data from an open-source geodatabase, wherein the open-source geodatabase is configured with a spatial index; the road data includes the geographic data of each road route; Obtain the geographic coordinates of all candidate trajectory points; The spatial index is used to match the geographic coordinates of all candidate trajectory points with the geographic data of each road route to obtain candidate road trajectories. The spatial index is used to match the starting and ending trajectory points on the candidate road trajectory with preset POI information to obtain several sub-trajectories; wherein, the POI information is used to indicate geographical points on the road route; Several sub-trajectories are used as the target trajectory for a single vehicle.

6. A vehicle usage analysis device based on vehicle trajectory, characterized in that, The device includes: The acquisition unit is used to acquire vehicle trajectory data of all vehicles within a preset time period, and determine the vehicle trajectory corresponding to a single vehicle based on the vehicle trajectory data; wherein, the vehicle trajectory is a curve composed of trajectory points of a single vehicle. The trajectory point determination unit is used to determine candidate trajectory points for the vehicle's running trajectory using the Douglas-Puk road thinning algorithm. The trajectory determination unit is used to simultaneously match the candidate trajectory points with preset road data and preset POI information to determine the target trajectory. The judgment unit is used to analyze the target running trajectory according to the preset vehicle use determination rules and determine the vehicle use corresponding to the target running trajectory. The judgment unit is specifically used to obtain the target running trajectory corresponding to each individual vehicle; wherein, the target running trajectory includes several sub-running trajectories; If there is a sub-trajectory in the target trajectory that follows a pattern within a preset driving period, and the starting and ending points of the sub-trajectory are located in a commercial and residential area, then the vehicle corresponding to the target trajectory is determined to be a compliant commercial vehicle. If there are sub-trajectories in the target trajectory that are irregular within a preset driving period and appear more often than a preset number of times, then the vehicle corresponding to the target trajectory is determined to be a ride-hailing vehicle or a taxi. If a sub-trajectory in the target trajectory indicates a round trip to a fixed location within a preset travel period, and the starting and ending points of the target trajectory are located in a residential area, then the vehicle corresponding to the target trajectory is determined to be an illegal operating vehicle.

7. A computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the steps of the method as claimed in any one of claims 1 to 6.

8. A computer device comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the method as claimed in any one of claims 1 to 6.

Images