Illegal operating vehicle identification method, medium and equipment

Abstract

The invention discloses an illegal operating vehicle identification method, a medium and equipment. The illegal operating vehicle identification method comprises the following steps: acquiring travel path information of all motor vehicle objects in a preset analysis area; based on the travel path information, determining a plurality of travel trajectories corresponding to each motor vehicle individual object in a preset analysis area, and obtaining a travel information table of the total motor vehicle object; based on the travel information table, determining travel spatial-temporal feature information of the full-quantity motor vehicle objects; determining illegal operating vehicle judgment conditions by taking the travel spatio-temporal characteristic information of each motor vehicle individual object with the operation permission as a reference; and determining the motor vehicle individual object which does not have the operation permission in the preset analysis area and meets the illegal operating vehicle judgment condition as an illegal operating vehicle. According to the method, the coverage of all motor vehicle objects in the regional road network can be realized, illegal operating vehicles can be quickly and accurately identified, the traffic management efficiency can be improved, and the management cost can be reduced.

Description

Technical Field

[0001] This application relates to the technical field of traffic management, and in particular, to a method, medium, and device for identifying illegal operation vehicles. Background Art

[0003] Traditional methods for cracking down on illegal operation vehicles mainly rely on manual fixed-point law enforcement, identifying illegal operation behaviors by randomly checking passing vehicles. However, this method lacks extensive data support, has limited law enforcement efficiency, and is difficult to effectively curb the spread of illegal operation vehicles. Although certain progress has been made in the existing research on intelligent identification of illegal operation vehicles, mainly using video recognition methods and identification methods based on GPS (Global Positioning System) data sources to identify illegal operation vehicles, these methods still have many limitations. For example, video recognition methods usually use image recognition technology to identify illegal operation vehicles based on vehicle appearance features, mainly applied to the identification of fake license plate taxis, with a relatively single application scenario. Affected by its deployment cost and image processing computing power cost, it is difficult to achieve wide coverage. The existing GPS data methods usually use methods such as vehicle travel spatio-temporal feature analysis and trajectory mining to extract features for identifying illegal operation vehicles. However, the GPS data sources of this method are usually relatively single, such as only targeting taxi vehicles, with insufficient sample penetration rate, and it is difficult to comprehensively grasp the travel behavior characteristics of various operation vehicles, such as rental online car-hailing minibuses, highway passenger coaches, etc. In addition, for potential illegal operation vehicles without GPS data, such as private cars without GPS data, the existing methods cannot effectively identify them. Summary of the Invention

[0004] This application mainly provides a method, medium, and device for identifying illegal operation vehicles, aiming to solve the technical problem that the existing methods for identifying illegal operation vehicles lack comprehensiveness.

[0005] To solve the above technical problem, the technical solution adopted in this application is: providing a method for identifying illegal operation vehicles. The method for identifying illegal operation vehicles includes: obtaining the travel path information of all motor vehicle objects within a preset analysis area, where the all motor vehicle objects include multiple individual motor vehicle objects; based on the travel path information, determining several travel trajectories corresponding to each of the individual motor vehicle objects within the preset analysis area, and obtaining the travel information table of the all motor vehicle objects; based on the travel information table, determining the travel spatio-temporal feature information of the all motor vehicle objects; taking the travel spatio-temporal feature information of each of the individual motor vehicle objects with operation permits as a benchmark, determining the determination conditions for illegal operation vehicles; and determining the individual motor vehicle objects within the preset analysis area that do not have the operation permit and meet the determination conditions for illegal operation vehicles as illegal operation vehicles.

[0006] In some embodiments, obtaining the travel path information of all motor vehicle objects within the preset analysis area includes: obtaining all multi-source vehicle passing data within the preset analysis area, where each of the multi-source vehicle passing data includes vehicle passing time information, license plate number information, and vehicle type information; dividing the multi-source vehicle passing data with the same license plate number information and vehicle type information and adjacent in time sequence of the vehicle passing time information into the same travel path of the same motor vehicle individual object to obtain the travel path information of all motor vehicle objects within the preset analysis area; wherein, when the time difference between the vehicle passing time information of two pieces of the multi-source vehicle passing data is less than a preset adjacent threshold, it is determined that the corresponding two pieces of the multi-source vehicle passing data are adjacent in time sequence.

[0007] In some embodiments, the multi-source vehicle passing data includes checkpoint data and highway toll system data.

[0008] In some embodiments, based on the travel path information, determining several travel trajectories corresponding to each motor vehicle individual object within the preset analysis area to obtain the travel information table of all motor vehicle objects includes: obtaining the road network map data within the preset analysis area; based on the road network map data, reconstructing the travel path information by using a preset shortest path algorithm to determine several travel trajectories corresponding to each motor vehicle individual object within the preset analysis area, and obtaining the travel information table of all motor vehicle objects.

[0009] In some embodiments, the travel spatio-temporal characteristic information includes average daily travel duration, average daily travel distance, average daily number of stopping locations, and proportion of stopping points in key areas; based on the travel information table, determining the travel spatio-temporal characteristic information of all motor vehicle objects includes: obtaining the traffic zone data within the preset analysis area; performing spatial superposition of the traffic zone data and the travel information table to determine the average daily number of stopping locations and the proportion of stopping points in key areas of each motor vehicle individual object; based on the travel information table, calculating the average daily travel duration and the average daily travel distance of each motor vehicle individual object.

[0010] In some embodiments, the traffic cell data includes regular traffic cell data and traffic cell data for key areas, and at least one of popular scenic spot data, business district data, and hub interest point data is marked in the traffic cell data for key areas; superimposing the traffic cell data and the travel information table spatially to determine the average daily number of stopping locations and the proportion of stopping locations in key areas for each of the individual motor vehicle objects, including: based on the traffic cell data, determining the starting cell number and the ending cell number of each of the individual motor vehicle objects corresponding to the travel information table, to obtain a plurality of traffic cell numbers corresponding to each of the individual motor vehicle objects; removing duplicates from each of the traffic cell numbers and then counting to determine the average daily number of stopping locations and the proportion of stopping locations in key areas for each of the individual motor vehicle objects.

[0011] In some embodiments, the individual motor vehicle object includes a car object; determining the illegal operation vehicle determination condition based on the travel spatio-temporal characteristic information of each of the individual motor vehicle objects with an operation permit, including: sorting each of the car objects with an operation permit among the full amount of motor vehicle objects in descending order according to the average daily travel duration, the average daily travel distance, and the average daily number of stopping locations; determining the car illegal travel duration threshold based on a preset first percentile, determining the car illegal travel distance threshold based on a preset second percentile, and determining the car illegal number of stopping locations threshold based on a preset third percentile; when the average daily travel duration of the car object is greater than the car illegal travel duration threshold, and the average daily travel distance of the car object is greater than the car illegal travel distance threshold, and the average daily number of stopping locations of the car object is greater than the car illegal number of stopping locations threshold, determining that the car object meets the illegal operation vehicle determination condition.

[0012] In some embodiments, the individual motor vehicle object includes a bus object; based on the travel spatio-temporal characteristic information of each of the individual motor vehicle objects with operating permits, determining the conditions for determining illegal operation vehicles further includes: sorting each of the bus objects with operating permits among the full amount of motor vehicle objects from largest to smallest according to the daily average travel duration, the daily average travel distance, the number of daily average stop locations, and the proportion of stop points in key areas; determining a bus illegal travel duration threshold based on a preset fourth percentile, determining a bus illegal travel distance threshold based on a preset fifth percentile, determining a bus illegal stop location number threshold based on a preset sixth percentile, and determining a bus illegal key area stop point proportion threshold based on a preset seventh percentile; when the daily average travel duration of the bus object is greater than the bus illegal travel duration threshold, and the daily average travel distance of the bus object is greater than the bus illegal travel distance threshold, and the number of daily average stop locations of the bus object is greater than the bus illegal stop location number threshold, and the proportion of stop points in key areas of the bus object is greater than the bus illegal key area stop point proportion threshold, it is determined that the bus object meets the conditions for determining illegal operation vehicles.

[0013] To solve the above technical problem, another technical solution adopted by this application is: to provide a storage medium, on which program data is stored, and characterized in that when the program data is executed by a processor, the steps of the illegal operation vehicle identification method as described above are implemented.

[0014] To solve the above technical problem, another technical solution adopted by this application is: to provide a computer device, which includes a processor and a memory connected to each other, the memory stores a computer program, and when the processor executes the computer program, the steps of the illegal operation vehicle identification method as described above are implemented.

[0015] The beneficial effects of this application are as follows: Different from the prior art, this application discloses a method, medium, and device for identifying illegal operating vehicles. By obtaining the travel path information of motor vehicles within a preset analysis area, this application determines the travel trajectories of each vehicle based on this information, generates a travel information table, and then analyzes this information to determine the travel spatio-temporal characteristics of the vehicles. Taking the characteristics of legally operating vehicles as a benchmark, this application sets the determination conditions for illegal operating vehicles to identify illegal operating vehicles without operating permits and meeting these determination conditions within the preset analysis area. It achieves coverage of all motor vehicle objects under the regional road network, can accurately grasp the spatio-temporal characteristics of all motor vehicle travel, expands the scope of illegal operating vehicle identification, can quickly and efficiently identify various illegal operating vehicles within the preset analysis area, and can also accurately identify potential illegal operating vehicles without navigation and positioning data, realizing the conversion from passive law enforcement to active law enforcement, effectively reducing traffic law enforcement costs and potential safety hazards, improving law enforcement efficiency, being conducive to enhancing the effectiveness and accuracy of cracking down on illegal operations, maintaining traffic order, ensuring public safety, and promoting the healthy development of the transportation industry. Description of the Drawings

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of this application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings, where:

[0017] Figure 1 is a flowchart showing an embodiment of the method for identifying illegal operating vehicles provided by this application;

[0018] Figure 2 is Figure 1 a flowchart showing an embodiment of step 10 in the embodiment;

[0019] Figure 3 is Figure 1 a flowchart showing an embodiment of step 20 in the embodiment;

[0020] Figure 4 is Figure 1 a flowchart showing an embodiment of step 30 in the embodiment;

[0021] Figure 5 is Figure 4 a flowchart showing an embodiment of step 32 in the embodiment;

[0022] Figure 6 is Figure 1 a flowchart showing an embodiment of step 40 in the embodiment;

[0023] Figure 7 Yes Figure 1 It is a schematic flowchart of another embodiment of step 40 in the embodiment;

[0024] Figure 8 It is a schematic structural diagram of an embodiment of the storage medium provided by the present application;

[0025] Figure 9 It is a schematic structural diagram of an embodiment of the computer device provided by the present application. Specific embodiments

[0026] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. 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 of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0027] The terms "first", "second", and "third" in the embodiments of the present application are only for the purpose of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first", "second", and "third" may explicitly or implicitly include at least one of such features. In the description of the present application, the meaning of "a plurality" is at least two, such as two, three, etc., unless otherwise specifically defined. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes unlisted steps or units, or optionally further includes other steps or units inherent to these processes, methods, products, or devices.

[0028] Referring to "embodiment" herein means that the specific features, structures, or characteristics described in conjunction with the embodiment may be included in at least one embodiment of the present application. The phrase appears in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein may be combined with other embodiments.

[0029] The present application provides an illegal operation vehicle identification method. Refer to Figure 1 , Figure 1 It is a schematic flowchart of an embodiment of the illegal operation vehicle identification method provided by the present application. The illegal operation vehicle identification method includes:

[0030] Step 10: Obtain the travel path information of all motor vehicle objects within the preset analysis area, where the all motor vehicle objects include multiple individual motor vehicle objects.

[0031] In this embodiment, the preset analysis area refers to a specific geographical range for identifying illegal operation vehicles. For example, it can be one or more cities, districts or counties according to administrative divisions or traffic management divisions, or it can be defined according to a distance range, such as 50 km, 100 km or 200 km, etc. The preset analysis area is set according to the supervision requirements of law enforcement departments and the convenience of actual operation. For example, it can be set as a high-demand area such as the urban central area, around tourist attractions, or around the venue of large-scale events. To obtain the travel path information of all motor vehicle objects, various data collection methods can be used, such as through the urban traffic monitoring system, vehicle GPS positioning data, mobile communication base station data, etc., to ensure the comprehensiveness and accuracy of the data. The all motor vehicle objects include multiple individual motor vehicle objects. An individual motor vehicle object refers to each specific motor vehicle, including but not limited to various types of vehicles such as cars, buses, and trucks. Obtaining the travel path information of these individual motor vehicle objects is to accurately identify the individual motor vehicle objects engaged in illegal operation among all motor vehicle objects subsequently.

[0032] Step 20: Based on the travel path information, determine the correspondence of each individual motor vehicle object within the preset analysis area

[0033] In this embodiment, the all motor vehicle objects are all the motor vehicles detected and recorded within the preset analysis area, including but not limited to various types of vehicles such as cars, buses, and trucks. The travel path information of an individual motor vehicle object refers to the information of the path passed by each individual motor vehicle on the road, including but not limited to one or more of the information such as license plate number, vehicle type, equipment number, coordinates, passing time, and the number of the corresponding acquisition device collected during the driving process. By obtaining the travel path information of all motor vehicle objects within the preset analysis area, the motor vehicle travel situation in this area can be comprehensively mastered, providing basic data support for subsequent identification of illegal operation vehicles.

[0034] Optionally, refer to Figure 2 , in an embodiment, to obtain the travel path information of all motor vehicle objects within the preset analysis area, the following steps can be executed:

[0035] Step 11: Obtain all multi-source passing vehicle data within the preset analysis area. Each multi-source passing vehicle data includes passing time information, license plate number information, and vehicle type information.

[0036] Step 12: Divide multi-source vehicle passing data with the same license plate number information and vehicle type information and adjacent passing time information in time series into the same travel path of the same motor vehicle individual object, so as to obtain the travel path information of all motor vehicle objects in the preset analysis area. Among them, when the time difference between the passing time information of two multi-source vehicle passing data is less than the preset adjacent threshold, it is determined that the corresponding two multi-source vehicle passing data are adjacent in time series.

[0037] In this alternative embodiment, the multi-source vehicle passing data refers to vehicle passing record data collected from different sources, including the start and end times, start and end locations, and passing location information of each travel path of the vehicle. These data can be data obtained by real-time monitoring and collection through devices such as cameras and sensors installed on the road in the electronic police system, or data obtained by cooperating with the vehicle positioning and navigation system or the vehicle networking system, or data obtained by integrating existing traffic checkpoint data, highway toll system data and other data resources of the traffic management department. All of these multi-source vehicle passing data include passing time information, license plate number information and vehicle type information. Among them, the passing time information refers to the time stamp when the vehicle passes a specific location, the license plate number information refers to the license plate number of the vehicle, and the vehicle type information includes the type of the vehicle, such as a car, a bus and a truck, etc. By integrating these information, the driving path of the vehicle in the preset analysis area can be constructed.

[0038] In this alternative embodiment, when the license plate number information and the vehicle type information are the same, it indicates that the corresponding multi-source information corresponds to the same vehicle object. On this basis, the driving order of the vehicle is judged by the time difference of the passing time information, so that the passing data adjacent in time series can be divided into the same travel path of the same vehicle object. Among them, the preset adjacent threshold for determining adjacent time series is a time interval set according to the actual traffic flow and vehicle driving speed, and is used to distinguish whether the vehicles are in the same travel process. For example, if the passing time difference between two vehicles is less than 5 minutes, it can be considered that they belong to the same travel process. The preset adjacent threshold can specifically be determined by statistical methods. Specifically, the multi-source vehicle passing data corresponding to each vehicle object can be arranged in time series, the time difference between the passing times before and after each multi-source vehicle passing data is determined, and the time differences are sorted from small to large, and the percentile value is selected, such as taking the 85th percentile as the preset adjacent threshold. Thus, when the time difference between the passing times before and after is less than this threshold, it is determined that the corresponding multi-source vehicle passing data are adjacent in time series and correspond to the same travel path. In this way, the multi-source vehicle passing data can be effectively integrated into complete vehicle travel path information, expanding the scope of identification of illegal operation vehicles and providing accurate data support for subsequent identification of illegal operation vehicles.

[0039] Optionally, in one embodiment, the multi-source vehicle passing data includes checkpoint data and highway toll system data.

[0040] In this alternative embodiment, the bayonet data refers to the vehicle passing data collected by monitoring points set on traffic arteries. Such data usually includes information such as the license plate number, vehicle type, passing time, bayonet number, and bayonet sequence number of the vehicle. The highway toll system data, on the other hand, comes from highway toll stations and gantries. Among them, the passing vehicle data collected by toll stations usually includes information such as license plate number, vehicle type, passing time, toll station number, and type of entering or leaving the highway. The passing vehicle data collected by gantries usually includes information such as gantry number, license plate number, vehicle type, and passing time. By integrating the bayonet data and the highway toll system data, it is possible to more comprehensively cover the driving conditions of vehicles on different sections, thereby improving the accuracy of identifying illegal operation vehicles and achieving full coverage of all motor vehicle objects under the regional road network.

[0041] In this alternative embodiment, the obtained travel path information can determine the same motor vehicle individual object according to the license plate number information and vehicle type information, integrate it into the same travel path information, and arrange it according to the passing time, and integrate it into structured data such as tables, databases, or serialized texts for subsequent fast and accurate analysis and use, reducing the computing power cost of processing. For example, a travel path information table can be obtained by fusing multi-source passing vehicle data. Each entry of travel path information in this table is used to record the passing vehicle situation during a single trip. Each entry correspondingly includes information corresponding to attributes such as license plate number, vehicle type, device recording time, travel number, passing device number, device type, and sequence number. Among them, the license plate number, vehicle type, and travel number of adjacent travel path information in time sequence are the same, indicating the same trip of the same motor vehicle individual object.

[0042] Step 20: Based on the travel path information, determine several travel trajectories corresponding to each motor vehicle individual object within the preset analysis area to obtain a travel information table of all motor vehicle objects.

[0043] In this embodiment, based on the obtained travel path information, the paths of each trip of the same individual motor vehicle object can be determined, that is, the multi-source vehicle passing data collected during the travel process, and the relevant data of the same trip are integrated together. Therefore, through the travel path information, a travel information table can be further analyzed and obtained, and the travel conditions of each trip of the individual motor vehicle object are reflected through the travel information table. For example, the first device recording time in ascending order of time for the same trip can be recorded as the departure time of this trip, and the last device recording time can be recorded as the arrival time of this trip. According to the positioning of the relevant collection devices, the corresponding starting point coordinates and ending point coordinates can be determined. Based on the combined road network information or the trip planning information of the device, the travel distance of this trip can be determined. Each entry in the travel information table obtained in this way can represent various information of a single trip of the same object. For example, the license plate number and vehicle type in the aforementioned travel path information can continue to be used to determine the individual motor vehicle object corresponding to this entry, and the travel number is used to uniquely identify this single trip, and the information such as the departure time, arrival time, starting point coordinates, ending point coordinates, and travel distance corresponding to this trip that can be easily analyzed is recorded. The obtained travel information table can effectively represent the several travel trajectories corresponding to each individual motor vehicle object in the preset area, and can provide detailed data support for the subsequent identification of illegal operation vehicles.

[0044] Optionally, referring to Figure 3 , in one embodiment, based on the travel path information, to determine the several travel trajectories corresponding to each individual motor vehicle object in the preset analysis area and obtain the travel information table of all motor vehicle objects, the following steps can be executed:

[0045] Step 21: Obtain the road network map data in the preset analysis area.

[0046] Step 22: Based on the road network map data, use the preset shortest path algorithm to reconstruct the travel path information to determine the several travel trajectories corresponding to each individual motor vehicle object in the preset analysis area and obtain the travel information table of all motor vehicle objects.

[0047] In this alternative embodiment, the road network map data includes digitized road network map data within the analysis areas of the high-speed and expressway network and the ground road network. These data can abstract road segments in the physical world into network nodes, and the connectivity between adjacent road segments into edges in the network, generating a road network model and further constructing a directed road network graph. These data usually contain information such as the starting point and ending point of the road, road type, road length, road width, speed limit information, traffic signal positions, driving distances between road points, and route planning. The road network map data can be obtained by constructing the road network model of the analysis area using classic complex network models such as Space C, Space L, and graph theory-based road network analysis methods, or provided by traffic management departments or relevant agencies, or obtained from professional map service providers and data sharing platforms. Through these data, a road network model within the preset analysis area can be constructed, providing a basis for subsequent path reconstruction.

[0048] In this alternative embodiment, reconstructing the travel path information using a preset shortest path algorithm means using the road network map data and existing travel path information to calculate the possible shortest paths of vehicles within the preset analysis area through an algorithm. The shortest path algorithm can specifically be classic path planning algorithms such as Dijkstra's algorithm, A* search algorithm, Bellman-Ford algorithm, and Floyd-Warshall algorithm. In this way, the driving trajectory of vehicles in the actual road network can be simulated, and a more accurate travel information table can be obtained. For example, through Dijkstra's algorithm, the complete travel path between the process records of adjacent vehicle timings can be reconstructed in the road network model in sequence, obtaining the complete travel trajectory of each trip of all motor vehicle objects in the road network model, obtaining the travel distance information of each trip of the individual motor vehicle object under the road network model, and thus obtaining the travel information table of all motor vehicle objects, which can more accurately reflect the actual driving situation of vehicles and provide a more reliable basis for the identification of illegal operating vehicles.

[0049] Step 30: Based on the travel information table, determine the travel spatio-temporal characteristic information of all motor vehicle objects.

[0050] In this embodiment, the travel spatio-temporal feature information refers to the feature data related to time and space manifested by a motor vehicle during travel. By analyzing the travel information table, the travel patterns and features of individual motor vehicle objects at different time periods and different locations can be extracted, such as travel frequency, travel duration, travel distance, average travel distance, etc. These feature information are crucial for identifying illegal operation vehicles because illegal operation vehicles often appear frequently in certain hot spots within a specific time period, and their travel routes may be significantly different from those of legally operated vehicles. For example, according to a travel information table obtained as described above, the travel duration can be determined based on the departure time and arrival time, the travel route can be determined based on the starting coordinate and ending coordinate, the travel frequency can be determined based on the number of trips within a preset time period, and the average travel distance can be determined based on the travel distance, etc. Through these spatio-temporal feature information, the travel behavior features of the vehicle can be constructed, providing a basis for subsequent identification of illegal operation vehicles.

[0051] Optionally, referring to Figure 4 , in one embodiment, based on the travel information table, to determine the travel spatio-temporal feature information of all motor vehicle objects, the following steps can be executed:

[0052] Step 31: Obtain traffic zone data within a preset analysis area.

[0053] Step 32: Perform spatial overlay of the traffic zone data and the travel information table to determine the daily average number of stop locations of each individual motor vehicle object and the proportion of stop points in key areas.

[0054] Step 33: Based on the travel information table, calculate the daily average travel duration and daily average travel distance of each individual motor vehicle object.

[0055] In this optional embodiment, the traffic zone data is a type of geographic information data used to describe and analyze traffic flow and travel behavior. It divides the preset analysis area into multiple zones, and each zone represents a traffic analysis unit. These data usually include information such as the zone number, location, area, demographic data, etc. By performing spatial overlay analysis of the traffic zone data and the travel information table, the stop behavior of individual motor vehicle objects in different zones can be identified, thereby determining the daily average number of stop locations and the proportion of stop points in key areas. For example, the number of stops of each individual motor vehicle object in each traffic zone can be counted, and then the average value can be calculated to obtain the daily average number of stop locations. At the same time, the distribution of stop points of individual motor vehicle objects in specific hot spots or key areas can be analyzed to obtain the proportion of stop points in key areas.

[0056] In this alternative embodiment, the calculation of the average daily travel duration and average daily travel distance of each individual motor vehicle object is based on the travel duration and travel distance information determined by the trigger time and arrival time in the travel information table, and is obtained through statistical analysis. Specifically, the average daily travel duration refers to the sum of the travel durations of each trip of an individual motor vehicle object within a certain time range, such as three days, one week, or one month, divided by the number of days in that time range. The average daily travel distance refers to the sum of the travel distances of each trip of an individual motor vehicle object within the same time range, divided by the number of days in that time range. Through these calculations, the travel behavior characteristics of each individual motor vehicle object can be obtained, and the high-frequency points and stopovers of illegal operation vehicles can be grasped, providing an important reference basis for the subsequent identification of illegal operation vehicles.

[0057] Optionally, in one embodiment, the traffic zone data includes conventional traffic zone data and key area traffic zone data, and at least one of popular scenic spot data, business district data, and hub interest point data is marked in the key area traffic zone data.

[0058] In this alternative embodiment, the conventional traffic zone data refers to the standard area division data used in general traffic flow analysis, which covers the main traffic flow areas in a city or region. These data are usually divided by traffic management departments according to factors such as urban planning, road network, and traffic flow, and are used to analyze and monitor traffic conditions. The division of conventional traffic zone data helps to simplify the traffic analysis process, making the analysis of traffic flow, travel patterns, and traffic congestion more intuitive and manageable.

[0059] In this alternative embodiment, the key area traffic zone data is a refined division based on the conventional traffic zone data for specific areas or areas with special traffic characteristics. These areas may include tourist hotspots, commercial centers, transportation hubs, etc., which usually have high traffic flow and complex traffic conditions. In these areas, the traffic zone data will be more detailed and may include at least one of popular scenic spot data, business district data, and hub interest point data. For example, the popular scenic spot data can include information such as the name, location, and opening hours of the scenic spot; the business district data can include information such as the scope of the business district, main commercial facilities, and passenger flow; the hub interest point data can include information such as the location and operating hours of transportation hubs such as airports, railway stations, and long-distance bus stations. Through these detailed data, the traffic demand and travel patterns within a specific area can be analyzed and predicted more accurately.

[0060] Optionally, refer to Figure 5 , in one embodiment, the traffic zone data and the travel information table are spatially overlaid to determine the average daily number of stop locations of each individual motor vehicle object and the proportion of stop points in key areas, which can be executed according to the following steps:

[0061] Step 321: Based on the traffic community data, determine the starting community number and the ending community number of each motor vehicle individual object corresponding to the travel information table, and obtain multiple traffic community numbers corresponding to each motor vehicle individual object.

[0062] Step 322: Count the traffic zone numbers after removing duplicates to determine the average daily number of stops for each individual motor vehicle object and the percentage of stops in key areas.

[0063] In this optional embodiment, the starting cell number and the end cell number are obtained by matching the traffic cell data with the travel information table. Since the starting cell and the end cell of each trip are possible stops in each traffic cell, the calculation of the average number of stops per day and the proportion of stops in key areas only needs to consider the starting cell and the end cell, so that the starting cell number and the end cell number are used as the traffic cell numbers for subsequent calculations.

[0064] In this optional embodiment, after deduplication of the numbers of each traffic zone, the numbers are counted, which can effectively exclude duplicate stops and ensure the accuracy of the statistical results. By counting, the number of stops of each individual motor vehicle in different traffic zones can be obtained, and then the average number of stops per day can be calculated. The calculation of the percentage of stops in key areas is based on the ratio of the number of stops in a specific hot spot or key area to the total number of stops. Based on the average number of stops per day and the percentage of stops in key areas, it is helpful to identify vehicles that frequently move in specific areas, providing strong data support for the identification of illegal vehicles.

[0065] Step 40: Based on the travel time and space characteristic information of each motor vehicle individual object with operating permit, determine the illegal operating vehicle judgment conditions.

[0066] In this embodiment, the operating license refers to the relevant information that is legally registered by the traffic management department or a third-party company authorized by the traffic management department and is allowed to engage in passenger-carrying operations, such as taxi business operating license, transport vehicle business operating license, commercial vehicle business operating license, online car-hailing business operating license, etc. Individual motor vehicle objects with operating licenses usually follow specific operating rules and standards, including but not limited to driving routes, service areas, operating hours, etc. By analyzing the travel spatiotemporal characteristics of these legally operating vehicles, the behavior patterns of legally operating vehicles under normal operating conditions can be determined, thereby highlighting the travel spatiotemporal characteristics of illegal operating vehicles.

[0067] In this embodiment, based on the travel spatio-temporal characteristic information of legal operating vehicles, a series of thresholds and rules are set to distinguish legal and illegal operating vehicles, and thus the determination conditions for illegal operating vehicles can be obtained. For example, a threshold for travel frequency can be set. If the number of trips of a vehicle within a specific time period exceeds this threshold, it may be determined as an illegal operation. Similarly, a threshold for travel distance can be set. If the average travel distance of a vehicle far exceeds the normal range of legal operating vehicles, this may indicate that the vehicle is engaged in illegal operating activities. In addition, the distribution of travel time can also be considered. Legal operating vehicles usually operate within specific service time periods, while illegal operating vehicles may travel frequently during abnormal time periods. Through these determination conditions, a discrimination model for illegal operating vehicles is also formed. Based on the travel information table, this model can determine the corresponding travel spatio-temporal characteristic information, and thus can quickly and efficiently identify the vehicles suspected of illegal operation within the preset analysis area according to the corresponding determination conditions for illegal operating vehicles.

[0068] Optionally, referring to Figure 6 , in an embodiment, the individual motor vehicle object includes a car object. Based on the travel spatio-temporal characteristic information of each individual motor vehicle object with an operation permit, the determination conditions for illegal operating vehicles are determined, and the following steps can be executed:

[0069] Step 41: Sort the car objects with operation permits among the full amount of motor vehicle objects in descending order according to the daily average travel duration, daily average travel distance, and the number of daily average stopping locations.

[0070] Step 42: Determine the illegal travel duration threshold for cars based on a preset first percentile, determine the illegal travel distance threshold for cars based on a preset second percentile, and determine the illegal number of stopping locations threshold for cars based on a preset third percentile.

[0071] Step 43: When the daily average travel duration of the car object is greater than the illegal travel duration threshold for cars, and the daily average travel distance of the car object is greater than the illegal travel distance threshold for cars, and the number of daily average stopping locations of the car object is greater than the illegal number of stopping locations threshold for cars, it is determined that the car object meets the determination conditions for illegal operating vehicles.

[0072] In this alternative embodiment, a method for setting the determination conditions for determining a car as an illegally operated vehicle is specified. Among them, since car objects operating legally usually follow a certain operation mode, therefore, by statistically analyzing the travel spatio-temporal characteristic information of these legally operated car objects, a relatively accurate reference range of normal operation behavior can be obtained. For example, through sorting analysis, it can be found that most legally operated cars are concentrated within a certain numerical range in terms of the average daily travel duration, average daily travel distance, and the number of average daily stop locations. Based on this, corresponding percentile thresholds, such as the first, second, and third percentiles, can be set as the reference criteria for determining illegal operation behavior.

[0073] In this alternative embodiment, the preset percentile thresholds are statistically obtained based on the travel characteristic data of legally operated car objects, and they represent the upper bounds of the respective travel spatio-temporal characteristic information indicators of normal operation behavior. For example, if the average daily travel duration of a car object exceeds the preset first percentile threshold, this may mean that the vehicle's operation time within a day is abnormally long and exceeds the scope of normal operation. Similarly, if the average daily travel distance exceeds the preset second percentile threshold, or the number of average daily stop locations exceeds the preset third percentile threshold, these may all indicate that the vehicle is suspected of illegal operation. Usually, when the average daily travel duration, average daily travel distance, and the number of average daily stop sites of a car object are all greater than the corresponding thresholds, it can be more accurately determined as an illegally operated vehicle. Through this method, potential illegally operated vehicles among cars can be effectively screened out, providing strong evidence for traffic management departments. Furthermore, corresponding management measures can be taken to achieve comprehensive monitoring and effective management of illegally operated vehicles, ensuring traffic order and public safety.

[0074] Optionally, referring to Figure 7 , in one embodiment, the motor vehicle individual object includes a bus object. Based on the travel spatio-temporal characteristic information of each motor vehicle individual object with an operation permit, the determination conditions for illegally operated vehicles are determined, and the following steps can be executed:

[0075] Step 44: Sort the large bus objects with operation permits among the full amount of motor vehicle objects from largest to smallest according to the average daily travel duration, average daily travel distance, the number of average daily stop locations, and the proportion of stop points in key areas.

[0076] Step 45: Determine the large bus illegal travel duration threshold based on the preset fourth percentile, determine the large bus illegal travel distance threshold based on the preset fifth percentile, determine the large bus illegal number of stop locations threshold based on the preset sixth percentile, and determine the large bus illegal proportion of stop points in key areas threshold based on the preset seventh percentile.

[0077] Step 46: When the average daily travel duration of the coach object is greater than the illegal travel duration threshold of the coach, the average daily travel distance of the coach object is greater than the illegal travel distance threshold of the coach, the average daily number of stops of the coach object is greater than the illegal number of stops threshold of the coach, and the proportion of stops at key areas of the coach object is greater than the illegal proportion of stops at key areas threshold of the coach, it is determined that the coach object meets the criteria for an illegally operating vehicle.

[0078] In this alternative embodiment, different from the criteria for determining an illegally operating vehicle for a car object, for the determination of an illegally operating coach object, the proportion of stops at key areas needs to be further considered. Specifically, since the operation mode of a coach object usually involves long-distance transportation and stops at multiple key areas, its operation behavior has prominent characteristics in the spatio-temporal feature information of the proportion of stops at key areas. Therefore, by statistically analyzing the spatio-temporal travel feature information of coach objects with operating permits, including the proportion of stops at key areas, a reference range reflecting the normal operation behavior of coach objects can be obtained. Then, corresponding percentile thresholds, such as the fourth, fifth, sixth, and seventh percentiles, can be set based on this reference range as the reference criteria for determining illegal operation behavior, which can effectively determine whether a coach object has the characteristics of an illegally operating vehicle.

[0079] In this alternative embodiment, the preset percentile thresholds are statistically obtained based on the travel feature data of legally operating coach objects, which represent the upper bounds of the spatio-temporal travel feature information indicators of normal operation behavior. For example, if the average daily travel duration of a coach object exceeds the preset fourth percentile threshold, this may mean that the vehicle's operation time in a day is abnormally long, exceeding the scope of normal operation. Similarly, if the average daily travel distance exceeds the preset fifth percentile threshold, or the average daily number of stops exceeds the preset sixth percentile threshold, these may all indicate that the vehicle is suspected of illegal operation. In particular, if the proportion of stops at key areas exceeds the preset seventh percentile threshold, this may indicate that the vehicle's stopping behavior in specific hot spots or key areas is abnormally frequent, which is inconsistent with legal operation behavior. Generally, when the average daily travel duration, average daily travel distance, and average daily number of stops of a coach object are all greater than the corresponding thresholds, and the proportion of stops at key areas is greater than the seventh percentile threshold, it can be more accurately determined that the vehicle is an illegally operating vehicle. Through this method, potential illegally operating vehicles among coaches can be effectively screened out, providing strong evidence for traffic management departments. Then, corresponding management measures can be taken to achieve comprehensive monitoring and effective management of illegally operating vehicles, ensuring traffic order and public safety.

[0080] Step 50: Determine the individual motor vehicle objects within the preset analysis area that do not have an operating permit and meet the criteria for an illegally operating vehicle as illegally operating vehicles.

[0081] In this embodiment, after determining the judgment conditions for illegal operation vehicles as described above, all individual motor vehicle objects within the preset analysis area can be screened. First, through the operation permit information, those individual motor vehicle objects with legal operation permits can be excluded first. For the remaining individual motor vehicle objects, the judgment conditions for illegal operation vehicles can be further applied for screening. Specifically, for each individual motor vehicle object that has not been excluded, it can be checked whether indicators such as the average daily travel duration, average daily travel distance, average daily number of stops, and the proportion of stops at key areas meet the judgment conditions for illegal operation vehicles. If an individual motor vehicle object meets the judgment conditions for illegal operation vehicles in all the above indicators, it is determined as an illegal operation vehicle.

[0082] Through this series of screening and judgment processes in this embodiment, various illegal operation vehicles within the preset analysis area can be quickly and efficiently identified. The finally determined illegal operation vehicles will provide a clear law enforcement basis for the traffic management department, which helps to improve the law enforcement efficiency and accuracy, and realizes the transformation from passive law enforcement to active law enforcement, that is, actively identifying illegal operation vehicles before potential safety accidents, rather than dealing with them after illegal operation vehicles cause safety accidents or obvious abnormalities are exposed. It can effectively reduce the traffic law enforcement cost and potential safety hazards, improve the law enforcement efficiency, be conducive to enhancing the effectiveness and accuracy of cracking down on illegal operations, maintaining traffic order, ensuring public safety, and promoting the healthy development of the transportation industry.

[0083] Refer to Figure 8 , Figure 8 which is a schematic structural diagram of an embodiment of the storage medium provided by the present application.

[0084] The storage medium 60 stores program data 61, and when the program data 61 is executed by a processor, it implements the method for identifying illegal operation vehicles as described in Figures 1 to 7 .

[0085] The program data 61 is stored in a storage medium 60 and includes several instructions for causing a network device (which can be a router, a personal computer, a server, etc.) or a processor to execute all or part of the steps of the methods described in various embodiments of the present application.

[0086] Optionally, the storage medium 60 can be various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc that can store the program data 61.

[0087] Refer to Figure 9 , Figure 9 which is a schematic structural diagram of an embodiment of the computer device provided by the present application.

[0088] The computer device 70 includes a processor 72 and a memory 71 that are interconnected. The memory 71 stores a computer program. When the processor 72 executes the computer program, the method for identifying illegal operating vehicles as described in Figures 1 to 7 is implemented. Among them, the memory 71 may include a storage medium 70 or may be other separately developed memories.

[0089] Different from the prior art, the present application discloses a method, medium, and device for identifying illegal operating vehicles. By obtaining the travel path information of motor vehicles in a preset analysis area, determining the travel trajectories of each vehicle based on this information, generating a travel information table, and then analyzing this information to determine the travel spatio-temporal characteristics of the vehicles, and setting the determination conditions for illegal operating vehicles based on the characteristics of legal operating vehicles, to identify illegal operating vehicles without operating permits and meeting the determination conditions in the preset analysis area, it realizes the coverage of all motor vehicle objects under the regional road network, can accurately master the travel spatio-temporal characteristics of all motor vehicles, expands the scope of identifying illegal operating vehicles, can quickly and efficiently identify various illegal operating vehicles in the preset analysis area, and can also accurately identify potential illegal operating vehicles without navigation and positioning data, realizing the conversion from passive law enforcement to active law enforcement, effectively reducing the traffic law enforcement cost and potential safety hazards, improving the law enforcement efficiency, being beneficial to improving the effectiveness and accuracy of cracking down on illegal operations, maintaining traffic order, ensuring public safety, and promoting the healthy development of the transportation industry.

[0090] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the storage medium embodiment and the computer device embodiment, since they are basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0091] The present application can be used in many general-purpose or special-purpose computing system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on.

[0092] In several embodiments provided by the present application, it should be understood that the disclosed methods, storage media, and computer devices can be implemented in other ways. For example, the storage medium embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0093] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0094] In addition, in each embodiment of the present application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0095] The above are only the embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present application.

Claims

1. A method for identifying illegally operated vehicles, characterized in that: include: Acquire travel path information of all motor vehicle objects in a preset analysis area, wherein the all motor vehicle objects include a plurality of individual motor vehicle objects; Based on the travel path information, determining a number of travel trajectories corresponding to each of the individual motor vehicle objects in the preset analysis area, and obtaining a travel information table of all motor vehicle objects; Based on the travel information table, determining travel spatiotemporal characteristic information of all motor vehicle objects; Determining the illegal operation vehicle determination conditions based on the travel time and space characteristic information of each motor vehicle individual object with operation permit; The motor vehicle individual object in the preset analysis area that does not have the operating license and meets the illegal operation vehicle determination conditions is determined as an illegal operation vehicle.

2. The method for identifying illegally operated vehicles according to claim 1, characterized in that: The obtaining of travel path information of all motor vehicle objects in a preset analysis area includes: Acquire a full amount of multi-source vehicle passing data in the preset analysis area, each of the multi-source vehicle passing data including vehicle passing time information, license plate number information and vehicle model information; The multi-source vehicle passing data with the same license plate number information and vehicle model information and adjacent vehicle passing time information are divided into the same travel path of the same motor vehicle individual object, so as to obtain the travel path information of all motor vehicle objects in the preset analysis area; When the time difference of the vehicle passing time information of two pieces of the multi-source vehicle passing data is less than a preset adjacent threshold, it is determined that the corresponding two pieces of the multi-source vehicle passing data are adjacent in time sequence.

3. The method for identifying illegally operated vehicles according to claim 2, characterized in that: The multi-source vehicle passing data includes checkpoint data and highway toll system data.

4. The method for identifying illegally operated vehicles according to claim 1, characterized in that: The determining, based on the travel path information, a plurality of travel trajectories corresponding to each of the individual motor vehicle objects in the preset analysis area, and obtaining a travel information table of all motor vehicle objects includes: Acquire road network map data within the preset analysis area; Based on the road network map data, a preset shortest path algorithm is used to reconstruct the travel path information to determine a number of travel trajectories corresponding to each of the individual motor vehicle objects in the preset analysis area, and obtain a travel information table for all motor vehicle objects.

5. The method for identifying illegally operated vehicles according to claim 1, characterized in that: The travel time and space characteristic information includes the average daily travel time, the average daily travel distance, the average daily number of stops, and the proportion of stops in key areas; The determining, based on the travel information table, travel spatiotemporal characteristic information of all motor vehicle objects includes: Acquiring traffic zone data within the preset analysis area; Spatially superimposing the traffic community data with the travel information table to determine the average daily number of stops for each individual motor vehicle object and the proportion of stops in the key area; Based on the travel information table, the average daily travel duration and the average daily travel distance of each of the individual motor vehicle objects are calculated.

6. The method for identifying illegally operated vehicles according to claim 5, characterized in that: The traffic area data includes conventional traffic area data and key area traffic area data, wherein the key area traffic area data is annotated with at least one of popular scenic spot data, business district data and hub point of interest data; The traffic community data is spatially superimposed with the travel information table to determine the average daily number of stops for each individual motor vehicle object and the proportion of stops in the key area, including: Based on the traffic cell data, determine the starting cell number and the ending cell number of each of the individual motor vehicle objects corresponding to the travel information table, and obtain multiple traffic cell numbers corresponding to each of the individual motor vehicle objects; The numbers of the traffic communities are deduplicated and then counted to determine the average daily number of stops for each individual motor vehicle object and the proportion of stops in the key areas.

7. The method for identifying illegally operated vehicles according to claim 5, characterized in that: The motor vehicle individual object includes a passenger car object; The determination of illegal operating vehicle determination conditions based on the travel time-space characteristic information of each motor vehicle individual object with operating permit includes: Sort the passenger car objects with the operating license in the total number of motor vehicle objects from large to small according to the average daily travel time, the average daily travel distance and the average daily number of stop locations; Determine the threshold of illegal travel duration of passenger cars based on the preset first percentile, determine the threshold of illegal travel distance of passenger cars based on the preset second percentile, and determine the threshold of the number of illegal parking locations of passenger cars based on the preset third percentile; When the average daily travel duration of the passenger car object is greater than the illegal travel duration threshold of the passenger car, and the average daily travel distance of the passenger car object is greater than the illegal travel distance threshold of the passenger car, and the average daily number of stopping locations of the passenger car object is greater than the illegal number of stopping locations threshold of the passenger car, it is determined that the passenger car object meets the illegal operation vehicle judgment conditions.

8. The method for identifying illegally operated vehicles according to claim 5, characterized in that: The motor vehicle individual object includes a bus object; The determining of the illegal operation vehicle determination condition based on the travel time-space characteristic information of each motor vehicle individual object with operation permit further includes: Sort the large buses with the operating license among all the motor vehicle objects from large to small according to the average daily travel time, the average daily travel distance, the average daily number of stops and the proportion of stops in key areas; The threshold for illegal bus travel duration is determined based on the preset fourth percentile, the threshold for illegal bus travel distance is determined based on the preset fifth percentile, the threshold for the number of illegal bus stops is determined based on the preset sixth percentile, and the threshold for the proportion of illegal bus stops in key areas is determined based on the preset seventh percentile; When the average daily travel duration of the bus object is greater than the illegal travel duration threshold of the bus, and the average daily travel distance of the bus object is greater than the illegal travel distance threshold of the bus, and the average daily number of stop locations of the bus object is greater than the number threshold of illegal stop locations of the bus, and the proportion of stop points in key areas of the bus object is greater than the threshold of the proportion of illegal stop points of the bus in key areas, it is determined that the bus object meets the illegal operating vehicle judgment conditions.

9. A storage medium having program data stored thereon, characterized in that: When the program data is executed by a processor, the steps of the method for identifying illegally operated vehicles as described in any one of claims 1 to 8 are implemented.

10. A computer device, characterized in that: It comprises a processor and a memory connected to each other, the memory stores a computer program, and when the processor executes the computer program, the steps of the method for identifying illegally operated vehicles as described in any one of claims 1 to 8 are implemented.

Images