Method and device for identifying cross-regional travel behavior of vehicle and electronic equipment

Abstract

The invention discloses a method and a device for identifying a cross-regional travel behavior of a vehicle and electronic equipment. The method comprises the following steps: acquiring multi-source traffic travel data of the vehicle in a target region; the multi-source traffic trip data comprises checkpoint data and expressway toll collection system data; performing vehicle travel track extraction processing on the checkpoint data and the highway toll collection system data to obtain a checkpoint vehicle travel track and a highway vehicle travel track; fusing the checkpoint vehicle travel trajectory and the highway vehicle travel trajectory to obtain a vehicle total travel trajectory; inputting the total travel trajectory of the vehicle into a target integrated learning model, and reconstructing complete travel path data of the vehicle; and performing cross-region travel behavior identification on the complete travel path data of the vehicle according to a preset region division rule to obtain cross-region travel behavior data of the vehicle in the target region. The method can realize vehicle individual travel full-chain cognition, restores the complete travel trajectory of the vehicle, and can be widely applied to the technical field of data processing.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method, apparatus and electronic device for recognizing cross-regional travel behavior of vehicles. Background Technology

[0002] In related technologies, single data sources such as floating car GPS (Global Positioning System) data and highway toll data are typically used to estimate the scale of cross-regional motor vehicle travel through sampling methods. This approach suffers from low data coverage and limited applicability, making it difficult to achieve accurate statistics on cross-regional motor vehicle volume. Furthermore, current research on cross-regional motor vehicle flow focuses on statistical analysis of OD (Origin-Destination) traffic flow between regions, lacking in-depth understanding of individual vehicle travel behavior and a sufficient grasp of the cross-regional travel process during holidays.

[0003] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the Invention

[0004] The embodiments of this application aim to at least partially solve one of the technical problems in the related art. Therefore, the main objective of the embodiments of this application is to propose a method, device, and electronic device for recognizing cross-regional travel behavior of vehicles, capable of realizing full-chain cognition of individual vehicle travel, reconstructing the complete travel trajectory of the vehicle, and thus accurately recognizing cross-regional travel behavior of vehicles.

[0005] To achieve the above objectives, one aspect of this application proposes a method for recognizing cross-regional travel behavior of vehicles, the method comprising:

[0006] Acquire multi-source traffic data of vehicles within the target area; wherein, the multi-source traffic data includes checkpoint data and highway toll system data;

[0007] The vehicle travel trajectory is extracted from the checkpoint data and the highway toll system data respectively to obtain the checkpoint vehicle travel trajectory corresponding to the checkpoint data and the highway vehicle travel trajectory corresponding to the highway toll system data.

[0008] The travel trajectories of vehicles at the checkpoints and those on the highways are fused together to obtain the total travel trajectories of all vehicles within the target area.

[0009] The complete travel trajectories of the vehicles are input into the target ensemble learning model to reconstruct the complete travel path data of the vehicles within the target area;

[0010] According to the preset regional division rules, the complete travel route data of the vehicle is processed to identify cross-regional travel behavior, so as to obtain cross-regional travel behavior data of the vehicle in the target area.

[0011] In some embodiments, after performing cross-regional travel behavior identification processing on the complete vehicle travel path data according to a preset region division rule to obtain cross-regional travel behavior data of vehicles within the target region, the method further includes:

[0012] Based on the cross-regional travel behavior data, the scale of cross-regional travel vehicles within the target area is calculated.

[0013] In some embodiments, the step of extracting vehicle travel trajectories from the checkpoint data and the highway toll system data to obtain the checkpoint vehicle travel trajectory corresponding to the checkpoint data and the highway vehicle travel trajectory corresponding to the highway toll system data includes:

[0014] The checkpoint data is extracted and processed to obtain the first time difference data of vehicles passing through adjacent checkpoints in the target area, and the first time difference data is sorted.

[0015] The checkpoint travel time determination threshold is determined based on the sorting ranking of the first time difference data, and the travel characteristics of vehicles passing through adjacent checkpoints in the target area are determined based on the checkpoint travel time determination threshold, so as to extract the checkpoint vehicle travel trajectory corresponding to the checkpoint data based on the travel characteristics.

[0016] Based on the entrance and exit information of highway toll stations in the highway toll system data, the highway vehicle travel trajectory corresponding to the highway toll system data is extracted.

[0017] In some embodiments, fusing the vehicle travel trajectories at the checkpoint and the vehicle travel trajectories on the highway to obtain the total vehicle travel trajectories within the target area includes:

[0018] The checkpoint data and the highway toll system data are merged to obtain a vehicle travel information summary table, and the vehicle travel trajectory data in the vehicle travel information summary table are sorted.

[0019] Extract the first time difference data of vehicles passing adjacent checkpoints within the target area and the second time difference data of vehicles passing adjacent highway toll stations within the target area from the vehicle travel information summary table;

[0020] The first time difference data and the second time difference data are mixed to obtain mixed time difference data, and the mixed time difference data is sorted.

[0021] Based on the ranking of the mixed time difference data, a data fusion judgment threshold for fusing the checkpoint vehicle travel trajectory and the highway vehicle travel trajectory is determined;

[0022] The travel trajectories of vehicles at the checkpoint and those on the highway are fused according to the data fusion judgment threshold to obtain the total travel trajectories of all vehicles within the target area.

[0023] In some embodiments, the step of identifying cross-regional travel behavior of the complete vehicle travel route data according to a preset regional division rule to obtain cross-regional travel behavior data of vehicles within the target area includes:

[0024] Data extraction is performed on the complete travel route data of the vehicles to obtain the origin and destination information, route information, and route time information of the vehicles within the target area;

[0025] Determine whether the origin and destination of vehicles within the target area are located within the target area based on the origin and destination information of vehicles within the target area;

[0026] If the origin and destination of a vehicle within the target area are located within the target area, then the cross-regional travel behavior of the vehicle within the target area is identified and processed according to the route information, the route time information, and the preset area division rules, to obtain cross-regional travel behavior data of the vehicle within the target area.

[0027] In some embodiments, the method further includes:

[0028] The software map file corresponding to the target area is generated using preset software tools;

[0029] The software map file and the city-level road network map file of the target area are overlaid using a spatial overlay method to extract the set of road segment information within the target area. This set of road segment information is then used as a preset area division rule for identifying cross-regional travel behavior of vehicles.

[0030] In some embodiments, the method further includes:

[0031] Acquire historical floating car trajectory fragments between adjacent roadside vehicle detection devices within the target area;

[0032] The target ensemble learning model is obtained by training the ensemble learning model to be trained based on the historical floating car trajectory fragments.

[0033] To achieve the above objectives, another aspect of this application provides a vehicle cross-regional travel behavior recognition device, the device comprising:

[0034] The multi-source data acquisition module is used to acquire multi-source traffic travel data of vehicles within the target area; wherein, the multi-source traffic travel data includes checkpoint data and highway toll system data;

[0035] The vehicle travel trajectory extraction module is used to extract vehicle travel trajectories from the checkpoint data and the highway toll system data respectively, so as to obtain the checkpoint vehicle travel trajectory corresponding to the checkpoint data and the highway vehicle travel trajectory corresponding to the highway toll system data.

[0036] The vehicle travel trajectory fusion module is used to fuse the vehicle travel trajectories at the checkpoint and the vehicle travel trajectories on the highway to obtain the full travel trajectories of all vehicles within the target area.

[0037] The vehicle route data reconstruction module is used to input the full travel trajectory of the vehicle into the target ensemble learning model and reconstruct the complete travel route data of the vehicle in the target area.

[0038] The cross-regional behavior recognition module is used to identify cross-regional travel behavior of the complete travel route data of the vehicle according to the preset regional division rules, so as to obtain cross-regional travel behavior data of the vehicle in the target area.

[0039] To achieve the above objectives, another aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method described above.

[0040] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods described above.

[0041] The embodiments of this application include at least the following beneficial effects: This application provides a method, device, and electronic device for recognizing cross-regional travel behavior of vehicles. This solution acquires multi-source traffic travel data of vehicles within a target area; the multi-source traffic travel data includes checkpoint data and highway toll system data; the checkpoint data and highway toll system data are processed to extract vehicle travel trajectories, resulting in checkpoint vehicle travel trajectories corresponding to the checkpoint data and highway vehicle travel trajectories corresponding to the highway toll system data; the checkpoint vehicle travel trajectories and highway vehicle travel trajectories are fused to obtain the full travel trajectories of vehicles within the target area; the full travel trajectories of vehicles are input into a target ensemble learning model to reconstruct the complete travel path data of vehicles within the target area; and cross-regional travel behavior recognition processing is performed on the complete travel path data of vehicles according to preset regional division rules to obtain cross-regional travel behavior data of vehicles within the target area. This application embodiment acquires multi-source traffic data of vehicles within the target area, enabling a comprehensive understanding of vehicle travel conditions. This facilitates more accurate analysis of traffic conditions and vehicle travel behavior. Furthermore, fusing checkpoint vehicle travel trajectories and highway vehicle travel trajectories yields more comprehensive vehicle travel information, further enhancing the accuracy of vehicle path and behavior analysis. Simultaneously, by learning vehicle travel trajectories through an integrated learning model, the complete travel path of each vehicle can be reconstructed, allowing for further analysis of vehicle behavior and travel routes. Regional division rules are used to identify the complete travel path of vehicles, thus identifying cross-regional travel behavior. In short, this application embodiment achieves full-chain cognition of individual vehicle travel, reconstructs complete vehicle travel trajectories, and accurately identifies cross-regional travel behavior, providing a basis for traffic management and planning. Attached Figure Description

[0042] Figure 1 This is a flowchart illustrating the steps of a method for recognizing cross-regional travel behavior of a vehicle, as provided in an embodiment of this application.

[0043] Figure 2 This is a flowchart illustrating a method for recognizing cross-regional travel behavior of a vehicle provided in an embodiment of this application;

[0044] Figure 3 This is a flowchart illustrating a method for extracting cross-regional motor vehicle travel volume according to an embodiment of this application;

[0045] Figure 4 This application provides a daily variation chart of the number of vehicles that enter and remain in the central urban area of ​​a city during holidays, as provided in an embodiment of the application.

[0046] Figure 5 This application provides a daily variation chart of the number of vehicles that did not return after leaving the city center during holidays;

[0047] Figure 6 This is a schematic diagram of the structure of a vehicle cross-regional travel behavior recognition device provided in an embodiment of this application;

[0048] Figure 7 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0050] It is understood that the terms “first,” “second,” etc., used in this application may be used herein to describe various concepts, but unless otherwise stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the words “if,” “when,” or “in response to a determination” as used herein may be interpreted as “when…” or “when…” or “in response to a determination.”

[0051] As used in this application, the terms "at least one", "multiple", "each", "any", etc., "at least one" includes one, two or more, "multiple" includes two or more, "each" refers to each of the corresponding multiples, and "any" refers to any one of the multiples.

[0052] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0053] Currently, with rapid urbanization, urban population concentration is becoming increasingly pronounced. During major holidays, a large number of motor vehicle trips, primarily for visiting relatives and friends or traveling, are concentrated within cities in a short period, further leading to a significant increase in cross-regional motor vehicle travel demand. Related technologies typically use single data sources such as floating car GPS (Global Positioning System) data and highway toll data, employing sampling estimation methods to statistically analyze the scale of cross-regional motor vehicle travel. This approach suffers from low data coverage and limited applicability, making it difficult to achieve accurate statistics on the scale of cross-regional motor vehicle travel. Furthermore, current research on cross-regional motor vehicle flow focuses on statistical analysis of OD (Origin-Destination) traffic flow between regions, lacking in-depth understanding of individual vehicle travel behavior and a sufficient grasp of the cross-regional travel process during holidays.

[0054] In view of this, this application provides a method, device, and electronic device for identifying cross-regional travel behavior of vehicles. This solution acquires multi-source traffic travel data of vehicles within a target area; the multi-source traffic travel data includes checkpoint data and highway toll system data; vehicle travel trajectories are extracted from the checkpoint data and highway toll system data respectively to obtain the checkpoint vehicle travel trajectory corresponding to the checkpoint data and the highway vehicle travel trajectory corresponding to the highway toll system data; the checkpoint vehicle travel trajectory and the highway vehicle travel trajectory are fused to obtain the total travel trajectory of vehicles within the target area; the total travel trajectory of vehicles is input into a target ensemble learning model to reconstruct the complete travel path data of vehicles within the target area; and cross-regional travel behavior is identified from the complete travel path data of vehicles within the target area according to a preset regional division rule to obtain the cross-regional travel behavior data of vehicles within the target area. This application embodiment acquires multi-source traffic data of vehicles within the target area, enabling a comprehensive understanding of vehicle travel conditions. This facilitates more accurate analysis of traffic conditions and vehicle travel behavior. Furthermore, fusing checkpoint vehicle travel trajectories and highway vehicle travel trajectories yields more comprehensive vehicle travel information, further enhancing the accuracy of vehicle path and behavior analysis. Simultaneously, by learning vehicle travel trajectories through an integrated learning model, the complete travel path of each vehicle can be reconstructed, allowing for further analysis of vehicle behavior and travel routes. Regional division rules are used to identify the complete travel path of vehicles, thus identifying cross-regional travel behavior. In short, this application embodiment achieves full-chain cognition of individual vehicle travel, reconstructs complete vehicle travel trajectories, and accurately identifies cross-regional travel behavior, providing a basis for traffic management and planning.

[0055] The cross-regional travel behavior recognition method for vehicles provided in this application relates to the field of data processing technology. This method can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or in-vehicle terminal, but is not limited to these. The server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application that implements the cross-regional travel behavior recognition method for vehicles, but is not limited to the above forms.

[0056] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframes, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0057] It should be noted that in all specific embodiments of this application, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. In addition, when embodiments of this application require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirection to confirmation pages. Only after obtaining the user's separate permission or consent is the necessary user-related data required for the proper functioning of these embodiments acquired.

[0058] Please see Figure 1 , Figure 1 This is an optional flowchart of a method for recognizing cross-regional travel behavior of vehicles provided in an embodiment of this application. Figure 1 The method may include, but is not limited to, steps S101 to S105.

[0059] Step S101: Obtain multi-source traffic travel data of vehicles within the target area; wherein, the multi-source traffic travel data includes checkpoint data and highway toll system data;

[0060] The target area refers to a traffic area specifically selected for analysis, monitoring, or control in traffic management, traffic planning, or traffic research. This area can be part of a city, a specific road segment, a traffic hub, or a section of highway with concentrated traffic flow, etc. The selection of the target area is usually based on research objectives and practical needs, such as improving traffic congestion, optimizing traffic flow distribution, and enhancing road safety. It is understood that those skilled in the art can select the target area according to actual needs, and the embodiments of this application do not impose any limitations on this.

[0061] It should be noted that the target analysis area in this application embodiment is mainly applied to major areas within a city (such as the central urban area, key areas, and ring expressways). Identifying cross-regional behavior within an individual area requires constructing a complete cross-regional travel path, which also includes travel paths outside the analysis area. Therefore, the spatial range of the checkpoint data collected in this application embodiment is not limited to the analysis area, but is typically a larger spatial range, such as the entire city area of ​​the target city.

[0062] In this application's embodiments, "vehicle" refers to motor vehicles, such as cars, motorcycles, trucks, and buses, all equipped with identifiable vehicle identification numbers (VINs) and typically operating on roads and participating in traffic. In intelligent transportation systems, vehicles can be identified and tracked in various ways, such as using license plate recognition systems, onboard sensors, or GPS (Global Positioning System) tracking. It is understood that those skilled in the art can select the target vehicle based on the specific circumstances.

[0063] Multi-source traffic data refers to comprehensive data on traffic conditions collected from different information sources. Multi-source data provides a more comprehensive and detailed perspective for traffic analysis, enabling more accurate assessment of traffic conditions and facilitating traffic forecasting and planning. In this embodiment, multi-source traffic data primarily includes checkpoint data and highway toll system data.

[0064] With the rapid development of image recognition technology, urban road high-definition checkpoint systems have been gradually improved. The scale of checkpoint equipment deployment and data quality have been significantly enhanced. Checkpoint data is characterized by comprehensive vehicle types, complete information, and wide coverage. Through checkpoint data, the travel trajectories of motor vehicles on urban expressways and surface roads can be accurately depicted. Checkpoint data typically refers to data about vehicle movement collected by checkpoint systems (such as traffic monitoring cameras) installed on roads. This data can include information such as vehicle speed, travel time, vehicle type, and license plate number. Checkpoint systems can be used for traffic flow statistics, vehicle speed monitoring, and automatic capture of traffic violations.

[0065] With the widespread adoption of non-stop toll collection on highways, the coverage of highway toll system data (including toll station entrance and exit data and gantry data) has reached a high level, making it possible to fully understand the individual travel behavior of motor vehicles on highways. Highway toll system data refers to vehicle traffic data collected through electronic toll collection systems on highways (such as ETC (Electronic Toll Collection System)). This data typically includes vehicle travel time, road segment, direction of travel, vehicle type, license plate number, and payment information. This data allows for analysis of highway traffic flow, vehicle usage frequency, and road segment usage, which is of great significance for highway management and optimization.

[0066] In this embodiment of the application, by acquiring multi-source traffic data of vehicles within the target area, it is possible to comprehensively understand the driving situation of vehicles, including information such as vehicle speed, driving route, and time, which helps to analyze traffic conditions and vehicle travel behavior more accurately.

[0067] Step S102: Extract vehicle travel trajectories from the checkpoint data and the highway toll system data respectively to obtain the checkpoint vehicle travel trajectory corresponding to the checkpoint data and the highway vehicle travel trajectory corresponding to the highway toll system data.

[0068] Among them, vehicle travel trajectory refers to the record of a vehicle's driving path and movement on the road over a period of time, which usually includes information such as the time of each trip, origin, destination, route, travel time, speed, and locations along the way.

[0069] In some embodiments, step S102 may include: extracting and processing checkpoint data to obtain first time difference data of vehicles passing through adjacent checkpoints in the target area, and sorting the first time difference data; determining a checkpoint travel time determination threshold based on the sorting ranking of the first time difference data, and determining the travel characteristics of vehicles passing through adjacent checkpoints in the target area based on the checkpoint travel time determination threshold, so as to extract the checkpoint vehicle travel trajectory corresponding to the checkpoint data based on the travel characteristics; and extracting the highway vehicle travel trajectory corresponding to the highway toll system data based on the entrance and exit information of highway toll stations in the highway toll system data.

[0070] The first time difference data refers to the time difference between vehicles passing through adjacent checkpoints within the target area; specifically, the time difference between vehicles passing through adjacent checkpoints on the road network. The road network refers to the entire transportation network, including all roads, streets, highways, bridges, tunnels, etc., which are connected to form a system where vehicles can travel. The road network can span a city, a region, or multiple cities and regions over a larger area. The first time difference data is sorted in ascending order of time difference.

[0071] The threshold for determining travel time at checkpoints is the threshold for truncation of a vehicle's trajectory between adjacent checkpoints. This threshold applies to all vehicles passing through adjacent checkpoints and is used to determine whether a vehicle passing through two adjacent checkpoints is recorded as traveling in the same trip.

[0072] For example, if the travel time between adjacent checkpoints for a vehicle exceeds the checkpoint travel time threshold, it is considered that the vehicle's previous trip ended at the first checkpoint of that adjacent checkpoint pair. It can be understood that if the travel time between adjacent checkpoints exceeds this threshold, the first checkpoint of that adjacent checkpoint pair is recorded as the destination of the vehicle's previous trip, and the second checkpoint is recorded as the starting point of the vehicle's next trip.

[0073] In this embodiment of the application, the travel characteristics of adjacent checkpoints are whether a vehicle passing through two adjacent checkpoints is recorded as the same trip.

[0074] In specific implementation, the steps of using checkpoint data and highway toll system data during and before the target holiday as basic data to fuse the two types of data and extract vehicle travel trajectory information can include vehicle travel trajectory extraction based on checkpoint data, vehicle travel trajectory extraction based on highway toll system data, and vehicle travel trajectory fusion based on multi-source data.

[0075] Specifically, the process of extracting vehicle travel trajectories based on checkpoint data involves: sorting checkpoint data during and before the target holiday period according to license plate number and passage time fields to obtain the time difference data of all vehicles passing through adjacent checkpoints on the road network; further sorting the time difference data of adjacent checkpoints from smallest to largest; and taking the Y percentile of the ranking (determined according to the actual situation) as the checkpoint travel time judgment threshold. If the travel time between adjacent checkpoints is less than the checkpoint travel time judgment threshold, it is considered that the travel feature record of the vehicle passing through the two adjacent checkpoints is the same trip, so as to further extract the travel trajectories of all vehicles.

[0076] Specifically, the process of extracting vehicle travel trajectories based on highway toll system data involves: acquiring highway toll station information within the target analysis area and extracting historical data from the highway toll system during and before holidays. The extracted toll system data includes toll station entry / exit information and corresponding gantry data for vehicles passing through during this period. The toll station entry / exit information and gantry data are then merged to generate a vehicle location information table including fields such as device number, license plate number, and passage time. Finally, the data is sorted according to license plate number and passage time attributes, with toll station entrances / exits anchored as the start and end points of the travel trajectory, and gantry data used as the waypoints. Thus, the vehicle's highway travel trajectory can be extracted using the start and end points and waypoints of the travel trajectory.

[0077] In this embodiment of the application, by extracting and processing vehicle travel trajectories from checkpoint data and highway toll system data respectively, it is beneficial to understand the driving situation of vehicles on different road sections, providing a foundation for subsequent data fusion and path reconstruction.

[0078] Step S103: The travel trajectories of the vehicles at the checkpoint and the travel trajectories of the vehicles on the highway are fused to obtain the total travel trajectories of all vehicles in the target area.

[0079] Among them, the total vehicle travel trajectory includes the travel trajectories of vehicles at checkpoints and those on highways, which helps to analyze vehicle travel routes and behaviors more accurately.

[0080] In some embodiments, step S103 may include: merging checkpoint data and highway toll system data to obtain a vehicle travel information summary table, and sorting the vehicle travel trajectory data in the vehicle travel information summary table; extracting the first time difference data of vehicles passing adjacent checkpoints and the second time difference data of vehicles passing adjacent highway toll stations in the target area from the vehicle travel information summary table; mixing the first time difference data and the second time difference data to obtain mixed time difference data, and sorting the mixed time difference data; determining the data fusion judgment threshold for fusing checkpoint vehicle travel trajectories and highway vehicle travel trajectories according to the ranking of the mixed time difference data; and fusing the checkpoint vehicle travel trajectories and highway vehicle travel trajectories according to the data fusion judgment threshold to obtain the full travel trajectory of vehicles in the target area.

[0081] The vehicle travel information summary table is formed by using the license plate number and vehicle type fields to create a unique vehicle number. This number is then used as a matching attribute to integrate highway toll system data and checkpoint data within the target analysis area into a single table. Specific data in the table may include fields such as equipment type, equipment number, passage time, and license plate number.

[0082] The sorting rule for vehicle travel trajectory data is to sort the vehicle travel trajectory data in the vehicle travel information summary table according to the license plate number and the time of passage.

[0083] The second time difference data refers to the time difference between vehicles passing through adjacent highway toll stations within the target area.

[0084] For mixed time difference data, it is the time difference data obtained by mixing or merging the first time difference data of vehicles passing through adjacent checkpoints in the target area and the second time difference data of vehicles passing through adjacent highway toll stations in the target area. After obtaining the mixed time difference data, it can be sorted, that is, sorted from smallest to largest according to the vehicle passage time difference data. Finally, the Z percentile of the ranking of the mixed time difference data (determined according to the actual situation) is taken as the data fusion judgment threshold for the fusion of checkpoint vehicle travel trajectory and highway vehicle travel trajectory.

[0085] Among them, the data fusion judgment threshold is the threshold used to determine whether the travel trajectories of vehicles at checkpoints and those on highways have been fused.

[0086] In practical implementation, the steps for vehicle travel trajectory fusion based on multi-source data can be as follows: The data from the highway toll system and checkpoints within the fusion analysis area are compiled into a single table. The table content may include fields such as equipment type, equipment number, passage time, and license plate number. Next, the table is sorted according to the license plate number and passage time fields to obtain the time difference data for all vehicles passing through adjacent checkpoints and highway toll stations. The time difference data for adjacent checkpoints and highway toll stations is further sorted in ascending order, and the Z-th percentile of the ranking is used as the data fusion judgment threshold. If the time difference between the start and end points of the vehicle travel trajectory extracted from the checkpoint and the start and end points of the same vehicle's highway travel trajectory is less than this threshold, the checkpoint vehicle travel trajectory and the highway vehicle travel trajectory are further merged into the same trip; otherwise, they are considered two independent trips.

[0087] In this embodiment of the application, by fusing the vehicle travel trajectories at checkpoints and those on highways, more comprehensive vehicle travel information can be obtained, enabling more accurate analysis of vehicle travel paths and behaviors.

[0088] Step S104: Input the full travel trajectory of the vehicles into the target ensemble learning model to reconstruct the complete travel path data of the vehicles in the target area;

[0089] In some embodiments, the method may further include: acquiring historical floating car trajectory segments between adjacent roadside vehicle detection devices within the target area; and training the ensemble learning model to be trained based on the historical floating car trajectory segments to obtain the target ensemble learning model. Typical ensemble learning models include random forest models, Adaboost, GBDT, XGBOOST, etc., all of which can be used to reconstruct complete travel path data of vehicles within the target area. In this embodiment, the random forest model is preferred.

[0090] Among them, floating car trajectory, also known as floating car GPS data, has the characteristics of high precision, high sampling frequency and moderate coverage. It can restore vehicle trajectory without relying on roadside equipment and has significant advantages in depicting the details of motor vehicle trajectory.

[0091] In practical implementation, a random forest model can be trained based on historical floating car trajectory fragments between adjacent sampling devices, using date type, travel time, vehicle type, and departure time as feature variables to reconstruct complete vehicle travel path data, thereby further extracting cross-regional behavioral feature information for each vehicle trip. Specifically, firstly, historical floating car trajectory data for a certain number of days before the target holiday is obtained. Then, historical travel trajectory fragments between adjacent roadside vehicle detection devices are extracted, and features such as date type, travel time, vehicle type, and departure time of different trajectory fragments are extracted. These feature variables are then used to train a random forest model to obtain the target random forest model. Based on the extracted checkpoint vehicle travel trajectories and highway vehicle travel trajectories, the target random forest model is fed with the date type, travel time, vehicle type, and departure time features of the vehicle travel data to be reconstructed. The target random forest model outputs the complete road network travel path of the vehicle to be reconstructed through adjacent devices, further generating information including the origin and destination, route segments, and entry and exit times of the route segments.

[0092] In this embodiment, the complete travel trajectories of vehicles are input into a target random forest model. By learning from the vehicle travel trajectory segments through the random forest model, the complete travel path of the vehicle can be reconstructed, enabling more accurate analysis of vehicle travel behavior and routes. Specifically, by integrating existing checkpoint data and highway toll system data, the complete travel path of individual motor vehicles under a multi-level urban road network can be reconstructed, further providing possibilities for the identification of cross-regional travel behavior of all motor vehicles.

[0093] Step S105: Based on the preset area division rules, the complete travel route data of the vehicle is processed to identify cross-regional travel behavior, thereby obtaining cross-regional travel behavior data of the vehicle within the target area.

[0094] Among them, cross-regional travel behavior data can be used to determine whether a vehicle's travel path involves entering or leaving the analysis area.

[0095] In some embodiments, the method may further include: generating a software map file corresponding to the target area using a preset software tool; overlaying the software map file and the city-level road network map file of the target area using a spatial overlay method to extract a set of road segment information within the target area, and using the set of road segment information as a preset area division rule for identifying the cross-regional travel behavior of vehicles.

[0096] The preset software tool can be GIS (Geographic Information System) software. For the relevant technical principles of GIS software, please refer to the relevant technical content. This application embodiment will not elaborate on them here.

[0097] The software map file can be a GIS map file representing the spatial extent of the target analysis area, generated through GIS software. The spatial overlay method can be a GIS analysis technique that aims to overlay the map file of the analysis area with a city-level road network map file. Through this overlay process, road network segments located within the analysis area can be identified.

[0098] A city-level road network map file is a map file that includes geographic information data of all roads, streets, highways, bridges, and other transportation facilities in the city. The road segment information set is a collection of all road segments (or road sections) within a specific analysis area.

[0099] In practice, the process of defining the target analysis area and urban road network data, and extracting the set of road network and road segment information contained in the target analysis area can be as follows: generate a GIS map file of the spatial range of the target analysis area using GIS software, combine it with the city-level road network map file, extract the set of road segment information in the area through spatial overlay, and use the set of road segment information as the basis for determining the cross-regional behavior of vehicle routes.

[0100] In some embodiments, step S105 may include: extracting data from the complete travel route data of the vehicle to obtain the origin and destination information, route information, and route time information of the vehicle in the target area; determining whether the origin and destination of the vehicle in the target area is located in the target area based on the origin and destination information of the vehicle in the target area; if the origin and destination of the vehicle in the target area is located in the target area, then performing cross-regional travel behavior identification processing on the vehicle in the target area based on the route information, route time information, and preset area division rules to obtain cross-regional travel behavior data of the vehicle in the target area.

[0101] In the specific implementation, for a single vehicle trip, the system sequentially extracts and determines whether the origin and destination are within the analysis area. Simultaneously, based on the route information along the travel path and combined with the road segment information set within the analysis area, it determines whether the vehicle's travel path involves entering or leaving the analysis area. It should be noted that all travel paths need to be iteratively analyzed to obtain the cross-regional travel behavior of all vehicles.

[0102] In this embodiment of the application, cross-regional travel behavior is identified by processing the complete travel path data of vehicles according to preset regional division rules, so as to obtain cross-regional travel behavior data of vehicles in the target area: by processing the complete travel path of vehicles by regional division rules, cross-regional travel behavior of vehicles can be identified, thereby accurately identifying cross-regional travel behavior of vehicles and providing a basis for traffic management and planning.

[0103] In some other embodiments, after step S105, the method may further include: calculating the cross-regional travel vehicle scale data of vehicles within the target area based on cross-regional travel behavior data.

[0104] The cross-regional travel vehicle scale data can include the number of external vehicles that entered the target analysis area and did not leave within each statistical period, and the number of internal vehicles that left the target analysis area and did not return within each statistical period.

[0105] In the specific implementation, based on the vehicle cross-regional behavior feature information extracted in step S105, the number of external vehicles entering the target analysis area and the number of vehicles leaving the target analysis area are counted according to a certain time granularity. That is, the number of external vehicles that enter the target analysis area and do not leave, and the number of vehicles that leave the target analysis area and do not return are counted.

[0106] Specifically, vehicles that have not appeared within the target analysis area for a certain number of days before the holiday are considered external vehicles. Within each statistical time unit, if an external vehicle simultaneously meets the conditions of being within the target analysis area at the end of the time unit and not having left the target analysis area during that time unit, it is considered to be in a state of having entered and not left. This process is repeated for all external vehicles that have appeared within the target analysis area to obtain the number of external vehicles that entered and did not leave during each statistical period. Conversely, vehicles that are within the target analysis area at the start time for a certain number of days before the holiday are considered internal vehicles. Within each statistical time unit, if an internal vehicle simultaneously meets the conditions of not being within the target analysis area at the end of the time unit and not having entered the target analysis area during that time unit, it is considered to be in a state of having left and not returned. This process is repeated for all internal vehicles to obtain the number of internal vehicles that left and did not return during each statistical period.

[0107] In this embodiment of the application, accurately grasping the scale of cross-regional motor vehicle travel during holidays is of great reference value for urban traffic management during holidays.

[0108] To explain in detail the principle of the technical solution of the present invention, the overall process of the present invention will be described below with reference to some specific embodiments. It is easy to understand that the following is an explanation of the technical principle of the present invention and should not be regarded as a limitation of the present invention.

[0109] Please see Figure 2 , Figure 2 This is a flowchart illustrating a method for recognizing cross-regional travel behavior of vehicles provided in an embodiment of this application; please refer to [link / reference]. Figure 3 , Figure 3This is a flowchart illustrating a method for extracting cross-regional motor vehicle travel volume according to an embodiment of this application; as shown below. Figure 2 and Figure 3 As shown, based on checkpoint data, floating car GPS data, and highway toll system data, and leveraging the high coverage of checkpoint and highway toll system data, as well as the advantage of floating car GPS data in depicting detailed vehicle trajectories, this approach achieves comprehensive understanding of vehicle travel behavior across multiple urban road networks. Based on this, it enables accurate statistics on cross-regional vehicle travel during holidays. Specifically, firstly, the analysis area and urban road network data are clearly defined, and a set of road network segment information within the analysis area is extracted. Then, based on checkpoint and highway toll system data before and after the target holiday, vehicle travel trajectory information is extracted, including travel time, origin and destination locations, and route locations. Next, based on historical floating car trajectory fragments between adjacent sampling devices, a random forest model is trained using date type, travel time, vehicle type, and departure time as feature variables to reconstruct and obtain complete vehicle travel paths. Based on the complete vehicle travel paths and the analysis area division rules, cross-regional behavioral characteristics of each vehicle trip are further extracted. Based on the extracted cross-regional behavioral characteristics, the scale of external vehicles that entered and did not leave, and internal vehicles that left and did not return, is statistically analyzed at a certain time granularity during and before holidays. Accurately grasping the scale of cross-regional motor vehicle travel during holidays is of great reference value for urban traffic management during holidays.

[0110] for Figure 3 The specific steps are as follows: Vehicles that have not appeared in the target analysis area within a certain number of days before the holiday are considered external vehicles. Within each statistical time unit, if an external vehicle simultaneously meets the conditions of being within the target analysis area at the end of the time unit and not having left the target analysis area within that time unit, it is considered to be in a state of having entered and not left. This process is repeated for all external vehicles that have appeared in the target analysis area to obtain the number of external vehicles that have entered and not left within each statistical period. Additionally, vehicles that are located within the target analysis area at the start time of a certain number of days before the holiday are considered internal vehicles. Within each statistical time unit, if an internal vehicle simultaneously meets the conditions of not being within the target analysis area at the end of the time unit and not having entered the target analysis area within that time unit, it is considered to be in a state of having left and not returned. This process is repeated for all internal vehicles to obtain the number of internal vehicles that have left and not returned within each statistical period.

[0111] It should be noted that this embodiment only provides a brief illustrative description of the general process of the vehicle cross-regional travel behavior recognition method. Detailed descriptions of each step can be found in the relevant content of the foregoing embodiments, and will not be repeated here. It is understood that the present invention does not impose any limitations on this.

[0112] The following is a detailed description and explanation of the solutions in the embodiments of the present invention, using specific application examples:

[0113] In the specific implementation, the central urban area of ​​a certain city is taken as the analysis area, and the analysis time range is the Spring Festival travel season of 2024 (January 26, 2024 to March 5, 2024, of which the Spring Festival holiday is from February 10, 2024 to February 17, 2024). An example is provided below:

[0114] It should be noted that, in the embodiments of the present invention, the preset implementation conditions are: 1. The license plate detection rate and data status at the checkpoint are good, and the occurrence of license plate missed detection or license plate recognition errors is rare; 2. The deployment density of checkpoint equipment should not be too low; 3. The data status of the highway toll system (including toll station entrance and exit data and gantry data) is good.

[0115] Specifically, the steps for identifying cross-regional travel behavior of vehicles are as follows:

[0116] Step S1: Extract the set of road segment numbers within the central urban area using geospatial overlay analysis. Based on checkpoint data within the target time range, sort the data by license plate number and passage time field to obtain the time difference data of all vehicles passing through adjacent checkpoints in the road network. Further sort the time difference data of adjacent checkpoints from smallest to largest. Then, take Y=85, that is, the 85th percentile of the time difference data ranking, as the checkpoint travel time judgment threshold. Repeat the above method to extract the travel trajectory of all vehicles. Please refer to Table 1, which is a schematic table of checkpoint record information corresponding to a complete trip of a motor vehicle (Note: when the checkpoint sequence number in the table is 1, it indicates the starting checkpoint of this trip; when the checkpoint sequence number is the maximum value of a single trip, it indicates the ending checkpoint of this trip).

[0117]

[0118] Table 1

[0119] Step S2: Obtain information on highway toll stations within the central urban area and extract historical data from the corresponding highway toll system during holidays and a certain number of days before and after. The extracted highway toll system data includes toll station entry and exit information for vehicles passing through during the period, as well as the corresponding gantry data. Merge the toll station entry and exit information and gantry data to generate a vehicle location information table including fields such as equipment number, license plate number, and passage time. Finally, sort the vehicle location information table according to license plate number and passage time attributes. Use the toll station entrance / exit as the starting and ending points of the travel trajectory, and the gantry data as the waypoints of the travel trajectory. Thus, the highway travel trajectory of a vehicle can be extracted using the starting and ending points and waypoints of the travel trajectory. Please refer to Table 2, which is a schematic table of highway toll station entrance / exit record information.

[0120] Toll station number license plate number Through time High-speed access type **2 *****28 2024-02-08 19:00:02 Enter **5 *****32 2023-02-08 19:01:20 out **0 *****56 2023-02-08 19:02:31 out

[0121] Table 2

[0122] Please refer to Table 3, which is a schematic table of highway gantry data information.

[0123] gantry number license plate number Through time **************52 *****45 2024-02-08 12:00:03 **************52 *****12 2023-02-08 12:01:25 **************52 *****47 2023-02-08 12:01:39

[0124] Table 3

[0125] Next, the data from the highway toll system and checkpoints within the central urban area are integrated into a single data summary table. This summary table includes fields such as equipment type, equipment number, passage time, and license plate number. The data in the summary table is then sorted according to the license plate number and passage time fields. Furthermore, the time difference data for all vehicles passing through adjacent checkpoints and highway toll stations is obtained. This time difference data is further sorted from smallest to largest, and Z=85, the 85th percentile of the time ranking, is used as the data fusion judgment threshold. If the time difference between the start and end points of a vehicle's travel trajectory based on a checkpoint and the start and end points of the same vehicle's highway trajectory is less than this data fusion judgment threshold, the checkpoint vehicle travel trajectory and the highway vehicle travel trajectory are further merged into a single trip; otherwise, they are considered two independent trips. Please refer to Table 4, which is a schematic table of travel trajectory record information for a vehicle after integrating checkpoint data and highway toll system data (Note: Equipment serial number 1 indicates the starting device for this trip, and equipment serial number equal to the maximum value for a single trip indicates the ending device for this trip).

[0126]

[0127] Table 4

[0128] Step S3: Obtain historical floating car trajectory data within a certain time period before the target holiday. Extract historical travel trajectory segments between adjacent roadside vehicle detection devices, and extract date type, travel time, vehicle type, and departure time features of different trajectory segments between adjacent devices. Use these feature variables to train a random forest model. Based on the vehicle travel trajectories extracted in Step S2, input the date type, travel time, vehicle type, and departure time features of vehicle travel into the random forest model. The random forest model outputs the complete road network travel path reconstructed between adjacent devices, further generating information including the origin and destination, road segments, and entry and exit times of the road segments. For a single vehicle trip, sequentially extract and determine whether the origin and destination are within the central urban area; simultaneously, based on the road segment information in the travel path, combined with the set of road segments within the central urban area, determine whether the travel path involves entering or leaving the central urban area. Iteratively determine all travel paths to obtain the cross-central urban area travel behavior of all vehicles. Please refer to Table 5, which is a schematic table of the complete route information for a single vehicle trip after reconstruction (Note: When the road segment sequence number is 1, it indicates that the road segment is the starting road segment of this trip; when the road segment sequence number is the maximum value for a single trip, it indicates that the road segment is the ending road segment of this trip). Please refer to Table 6, which is a schematic table of cross-regional travel behavior characteristics information for a single vehicle trip.

[0129]

[0130] Table 5

[0131]

[0132] Table 6

[0133] Step S4: Based on the extracted vehicle cross-city traffic behavior characteristics, count the number of external vehicles entering and internal vehicles leaving the city on a daily basis, including holidays and the days preceding and following holidays. Let X = 15, meaning vehicles not present in the city center during the 15 days before the Spring Festival holiday (the start of the Spring Festival travel rush) are considered external vehicles. If an external vehicle is present in the city center at 24:00 on a given day and has not left the city center that day, it is considered to have entered and not left. Repeat this process for all external vehicles present in the city center to obtain the daily number of external vehicles that entered and did not leave. Please refer to [link to relevant documentation]. Figure 4 , Figure 4This application provides a daily variation chart of the number of vehicles that entered and did not leave the central urban area of ​​a city during holidays, according to an embodiment of the application. Vehicles located within the central urban area 15 days before the Spring Festival travel rush (the start of the travel rush) are considered internal vehicles. If an internal vehicle is both outside the central urban area at 24:00 on a given day and has not entered the central urban area that day, it is considered to be in a state of having left and not returning. This process is repeated for all internal vehicles to obtain the daily number of internal vehicles that have left and not returned. Please refer to... Figure 5 , Figure 5 This is a daily variation chart of the number of vehicles that did not return after leaving the city center during holidays, provided by an embodiment of this application.

[0134] This application embodiment acquires multi-source traffic travel data of vehicles within a target area; the multi-source traffic travel data includes checkpoint data and highway toll system data; vehicle travel trajectories are extracted from the checkpoint data and highway toll system data respectively to obtain the checkpoint vehicle travel trajectory corresponding to the checkpoint data and the highway vehicle travel trajectory corresponding to the highway toll system data; the checkpoint vehicle travel trajectory and the highway vehicle travel trajectory are fused to obtain the full travel trajectory of vehicles within the target area; the full travel trajectory of vehicles is input into a target ensemble learning model to reconstruct the complete travel path data of vehicles within the target area; cross-regional travel behavior is identified and processed based on preset regional division rules to obtain cross-regional travel behavior data of vehicles within the target area. This application embodiment acquires multi-source traffic data of vehicles within the target area, enabling a comprehensive understanding of vehicle travel conditions. This facilitates more accurate analysis of traffic conditions and vehicle travel behavior. Furthermore, fusing checkpoint vehicle travel trajectories and highway vehicle travel trajectories yields more comprehensive vehicle travel information, further enhancing the accuracy of vehicle path and behavior analysis. Simultaneously, by learning vehicle travel trajectories through an integrated learning model, the complete travel path of each vehicle can be reconstructed, allowing for further analysis of vehicle behavior and travel routes. Regional division rules are used to identify the complete travel path of vehicles, thus identifying cross-regional travel behavior. In short, this application embodiment achieves full-chain cognition of individual vehicle travel, reconstructs complete vehicle travel trajectories, and accurately identifies cross-regional travel behavior, providing a basis for traffic management and planning.

[0135] Compared with related technologies, the embodiments of this application have significant advantages in the following aspects: 1. Current research on cross-regional motor vehicle travel focuses on the aggregation and analysis of vehicle OD traffic between regions, lacking a complete understanding of the travel process of individual vehicles and an insufficient understanding of the cross-regional travel process of motor vehicles during holidays. The embodiments of this application can achieve a full-chain understanding of individual motor vehicle travel, reconstruct the complete travel trajectory of vehicles, and accurately identify cross-regional motor vehicle travel behavior. 2. Related technologies typically use single data sources such as floating car GPS data and highway toll data to statistically analyze the scale of cross-regional motor vehicle travel in the form of sampling estimation. The data coverage is low and the applicable scenarios are relatively limited, making it difficult to achieve accurate statistics on the scale of cross-regional motor vehicles. At the same time, checkpoint data and highway toll system data have comprehensive coverage in urban surface roads and highway scenarios, respectively. Floating car GPS data has significant advantages in depicting the details of motor vehicle trajectories. The embodiments of this application achieve a full understanding of motor vehicle travel behavior across multiple levels of urban road networks by integrating the above data. Based on this, accurate statistics on the scale of cross-regional motor vehicles during holidays can be achieved. 3. By accurately identifying the scale of cross-regional travel during holidays, traffic management departments can more accurately grasp the changing trends of active vehicle scale within the region during holidays, predict traffic congestion time points in advance, and formulate targeted traffic management policies to ensure that road operation is at a reasonable level during holidays.

[0136] Please see Figure 6 This application embodiment also provides a vehicle cross-regional travel behavior recognition device 600, which can implement the above-mentioned vehicle cross-regional travel behavior recognition method. The device 600 includes:

[0137] The multi-source data acquisition module 601 is used to acquire multi-source traffic travel data of vehicles within the target area; wherein, the multi-source traffic travel data includes checkpoint data and highway toll system data;

[0138] The vehicle travel trajectory extraction module 602 is used to extract vehicle travel trajectories from the checkpoint data and the highway toll system data respectively, so as to obtain the checkpoint vehicle travel trajectory corresponding to the checkpoint data and the highway vehicle travel trajectory corresponding to the highway toll system data.

[0139] The vehicle travel trajectory fusion module 603 is used to fuse the vehicle travel trajectories at the checkpoint and the vehicle travel trajectories on the highway to obtain the full travel trajectories of all vehicles in the target area.

[0140] The vehicle route data reconstruction module 604 is used to input the full travel trajectory of the vehicle into the target ensemble learning model and reconstruct the complete travel route data of the vehicle in the target area.

[0141] The cross-regional behavior recognition module 605 is used to perform cross-regional travel behavior recognition processing on the complete travel route data of the vehicle according to the preset regional division rules, so as to obtain the cross-regional travel behavior data of the vehicle in the target area.

[0142] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0143] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the aforementioned method for recognizing cross-regional travel behavior of vehicles. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0144] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0145] Please see Figure 7 , Figure 7 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes:

[0146] The processor 701 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0147] The memory 702 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 702 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 702 and is called by the processor 701 to execute the vehicle cross-regional travel behavior recognition method of the embodiments of this application.

[0148] The input / output interface 703 is used to implement information input and output;

[0149] The communication interface 704 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0150] Bus 705 transmits information between various components of the device (e.g., processor 701, memory 702, input / output interface 703, and communication interface 704);

[0151] The processor 701, memory 702, input / output interface 703, and communication interface 704 are connected to each other within the device via bus 705.

[0152] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned method for recognizing cross-regional travel behavior of vehicles.

[0153] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0154] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0155] The cross-regional travel behavior recognition method, device, electronic device, and storage medium provided in this application embodiment acquire multi-source traffic travel data of vehicles within a target area. This multi-source traffic travel data includes checkpoint data and highway toll system data. Vehicle travel trajectories are extracted from both the checkpoint data and highway toll system data to obtain the checkpoint vehicle travel trajectory corresponding to the checkpoint data and the highway vehicle travel trajectory corresponding to the highway toll system data. The checkpoint vehicle travel trajectory and the highway vehicle travel trajectory are then fused to obtain the total travel trajectory of all vehicles within the target area. This total travel trajectory is input into a target ensemble learning model to reconstruct the complete travel path data of vehicles within the target area. Cross-regional travel behavior recognition processing is performed on the complete travel path data of vehicles according to preset regional division rules to obtain the cross-regional travel behavior data of vehicles within the target area. This application embodiment acquires multi-source traffic data of vehicles within the target area, enabling a comprehensive understanding of vehicle travel conditions. This facilitates more accurate analysis of traffic conditions and vehicle travel behavior. Furthermore, fusing checkpoint vehicle travel trajectories and highway vehicle travel trajectories yields more comprehensive vehicle travel information, further enhancing the accuracy of vehicle path and behavior analysis. Simultaneously, by learning vehicle travel trajectories through an integrated learning model, the complete travel path of each vehicle can be reconstructed, allowing for further analysis of vehicle behavior and travel routes. Regional division rules are used to identify the complete travel path of vehicles, thus identifying cross-regional travel behavior. In short, this application embodiment achieves full-chain cognition of individual vehicle travel, reconstructs complete vehicle travel trajectories, and accurately identifies cross-regional travel behavior, providing a basis for traffic management and planning.

[0156] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0157] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0158] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0159] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0160] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0161] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0162] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0163] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0164] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0165] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0166] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for recognizing cross-regional travel behavior of vehicles, characterized in that, The method includes: Acquire multi-source traffic data of vehicles within the target area; wherein, the multi-source traffic data includes checkpoint data and highway toll system data; The vehicle travel trajectory is extracted from the checkpoint data and the highway toll system data respectively to obtain the checkpoint vehicle travel trajectory corresponding to the checkpoint data and the highway vehicle travel trajectory corresponding to the highway toll system data. The travel trajectories of vehicles at the checkpoints and those on the highways are fused together to obtain the total travel trajectories of all vehicles within the target area. The complete travel trajectories of the vehicles are input into the target ensemble learning model to reconstruct the complete travel path data of the vehicles within the target area; According to the preset regional division rules, the complete travel route data of the vehicle is processed to identify cross-regional travel behavior, so as to obtain cross-regional travel behavior data of the vehicle in the target area.

2. The method according to claim 1, characterized in that, After performing cross-regional travel behavior identification processing on the complete vehicle travel path data according to preset region division rules to obtain cross-regional travel behavior data of vehicles within the target region, the method further includes: Based on the cross-regional travel behavior data, the scale of cross-regional travel vehicles within the target area is calculated.

3. The method according to claim 1, characterized in that, The step of extracting vehicle travel trajectories from the checkpoint data and the highway toll system data to obtain the checkpoint vehicle travel trajectory corresponding to the checkpoint data and the highway vehicle travel trajectory corresponding to the highway toll system data includes: The checkpoint data is extracted and processed to obtain the first time difference data of vehicles passing through adjacent checkpoints in the target area, and the first time difference data is sorted. The checkpoint travel time determination threshold is determined based on the sorting ranking of the first time difference data, and the travel characteristics of vehicles passing through adjacent checkpoints in the target area are determined based on the checkpoint travel time determination threshold, so as to extract the checkpoint vehicle travel trajectory corresponding to the checkpoint data based on the travel characteristics. Based on the entrance and exit information of highway toll stations in the highway toll system data, the highway vehicle travel trajectory corresponding to the highway toll system data is extracted.

4. The method according to claim 1, characterized in that, The process of fusing the travel trajectories of vehicles at the checkpoints and those on the highways to obtain the total travel trajectories of all vehicles within the target area includes: The checkpoint data and the highway toll system data are merged to obtain a vehicle travel information summary table, and the vehicle travel trajectory data in the vehicle travel information summary table are sorted. Extract the first time difference data of vehicles passing adjacent checkpoints within the target area and the second time difference data of vehicles passing adjacent highway toll stations within the target area from the vehicle travel information summary table; The first time difference data and the second time difference data are mixed to obtain mixed time difference data, and the mixed time difference data is sorted. Based on the ranking of the mixed time difference data, a data fusion judgment threshold for fusing the checkpoint vehicle travel trajectory and the highway vehicle travel trajectory is determined; The travel trajectories of vehicles at the checkpoint and those on the highway are fused according to the data fusion judgment threshold to obtain the total travel trajectories of all vehicles within the target area.

5. The method according to claim 1, characterized in that, The step of identifying cross-regional travel behavior in the complete travel route data of the vehicles according to preset regional division rules, to obtain cross-regional travel behavior data of vehicles within the target area, includes: Data extraction is performed on the complete travel route data of the vehicles to obtain the origin and destination information, route information, and route time information of the vehicles within the target area; Determine whether the origin and destination of vehicles within the target area are located within the target area based on the origin and destination information of vehicles within the target area; If the origin and destination of a vehicle within the target area are located within the target area, then the cross-regional travel behavior of the vehicle within the target area is identified and processed according to the route information, the route time information, and the preset area division rules, to obtain cross-regional travel behavior data of the vehicle within the target area.

6. The method according to claim 1, characterized in that, The method further includes: The software map file corresponding to the target area is generated using preset software tools; The software map file and the city-level road network map file of the target area are overlaid using a spatial overlay method to extract the set of road segment information within the target area. This set of road segment information is then used as a preset area division rule for identifying cross-regional travel behavior of vehicles.

7. The method according to claim 1, characterized in that, The method further includes: Acquire historical floating car trajectory fragments between adjacent roadside vehicle detection devices within the target area; The target ensemble learning model is obtained by training the ensemble learning model to be trained based on the historical floating car trajectory fragments.

8. A vehicle cross-regional travel behavior recognition device, characterized in that, The device includes: The multi-source data acquisition module is used to acquire multi-source traffic travel data of vehicles within the target area; wherein, the multi-source traffic travel data includes checkpoint data and highway toll system data; The vehicle travel trajectory extraction module is used to extract vehicle travel trajectories from the checkpoint data and the highway toll system data respectively, so as to obtain the checkpoint vehicle travel trajectory corresponding to the checkpoint data and the highway vehicle travel trajectory corresponding to the highway toll system data. The vehicle travel trajectory fusion module is used to fuse the vehicle travel trajectories at the checkpoint and the vehicle travel trajectories on the highway to obtain the full travel trajectories of all vehicles within the target area. The vehicle route data reconstruction module is used to input the full travel trajectory of the vehicle into the target ensemble learning model and reconstruct the complete travel route data of the vehicle in the target area. The cross-regional behavior recognition module is used to identify cross-regional travel behavior of the complete travel route data of the vehicle according to the preset regional division rules, so as to obtain cross-regional travel behavior data of the vehicle in the target area.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 7.

Images