Methods, equipment, media and products for urban traffic network topology construction and traffic matching based on individual-level GPS trajectory data

Abstract

The present application discloses a method, device, medium and product for constructing a metropolitan area traffic network topology and matching traffic based on individual-level GPS trajectory data, which relates to the field of urban transportation. First, the original GPS trajectory points are connected to form an original GPS trajectory line; then the original GPS trajectory line is evenly interrupted to form a revised GPS trajectory point; candidate intersections are identified based on the revised GPS trajectory points; directed road segments are extracted based on the candidate intersections, and then an optimized road topology network is generated and candidate directed road segments are screened out; candidate trajectory routes are generated based on the starting and ending points of the original GPS trajectory line and the candidate directed road segments; the target trajectory route and target directed road segment that best match the original GPS trajectory line are determined from the candidate trajectory routes; directional road traffic is formed based on all target trajectory routes and target directed road segments. The use of the method of the present application can improve the computational efficiency of the construction of the metropolitan area traffic network topology and traffic matching, and reduce the computing power requirements for hardware equipment.

Description

Technical Field

[0001] The present application relates to the field of urban transportation technology, and in particular to a method, device, medium and product for constructing a metropolitan area transportation network topology and matching traffic based on individual-level GPS trajectory data. Background Art

[0002] GPS individual vehicle trajectory data processing technology has become a relatively mature component of urban transportation research and related applications, and methods for extracting GPS trajectories and matching them to spatial networks are relatively mature. However, the integration of technologies for directly generating spatial network topologies using GPS trajectories and matching them to topological networks currently faces operational efficiency challenges and algorithmic design limitations. For example, using PCs and desktop databases, existing computational methods struggle to achieve minute-by-minute processing and backtracking of daily motor vehicle or motorcycle GPS trajectory data for urban areas within a 50-60km radius in China (i.e., within a typical metropolitan area or a one-hour traffic circle). Algorithmically, matching GPS trajectory paths across entire urban road sections is computationally inefficient. Existing methods for matching GPS trajectories to electronic map road networks require high road accuracy. Customizing road maps also presents efficiency and accuracy challenges and places significant demands on the computing power of the hardware. Summary of the Invention

[0003] The purpose of this application is to provide a method, device, medium and product for constructing the topology of a metropolitan area traffic network and matching traffic based on individual-level GPS trajectory data, so as to improve the computational efficiency of the topology construction and traffic matching of the metropolitan area traffic network and reduce the computing power requirements of the hardware equipment.

[0004] To achieve the above objectives, this application provides the following solutions.

[0005] In a first aspect, the present application provides a method for constructing a metropolitan area transportation network topology and matching traffic based on individual-level GPS trajectory data, including:

[0006] Connect the original GPS track points to form a continuous original GPS track line;

[0007] Evenly interrupt the original GPS track line to form the corrected GPS track points;

[0008] Identify candidate intersections based on the corrected GPS trajectory points;

[0009] Extract directed road segments based on candidate intersections;

[0010] Generate an optimized road topology network based on directed road segments;

[0011] Screen out candidate directed road segments based on the corrected GPS trajectory points and the optimized road topology network;

[0012] Generate candidate trajectory routes based on the starting and ending points of the original GPS trajectory and the candidate directed road segments;

[0013] Determine the trajectory route and its corresponding directed road segment that best matches the original GPS trajectory line from the candidate trajectory routes as the target trajectory route and target directed road segment;

[0014] Directional road traffic is generated based on all target trajectory routes and target directional road segments.

[0015] Optionally, connecting the original GPS track points to form a continuous original GPS track line specifically includes:

[0016] Arrange all the original GPS track points contained in each unique travel code in ascending order of timestamps and connect them in sequence to form a continuous original GPS track line, which is recorded as point set T = {p1, p2, ..., p n}, each point p i Including spatial coordinates (x i ,y i ) and timestamp t i ; n is the number of midpoints in the original GPS trajectory.

[0017] Optionally, evenly interrupting the original GPS track line to form corrected GPS track points specifically includes:

[0018] According to the segmentation conditions|p i+1 -p i |≥d th The original GPS trajectory line is evenly interrupted, and the interrupted trajectory segments are smoothed using Kalman filtering or sliding average method to form the corrected GPS trajectory points;

[0019] Each corrected GPS track point constitutes a corrected GPS track point set T'={P1, P2, ..., P N}, where N is the number of corrected GPS track points; d th is the distance threshold.

[0020] Optionally, identifying candidate intersections based on the corrected GPS trajectory points specifically includes:

[0021] Perform density estimation and cluster analysis on the corrected GPS track points to identify several clusters;

[0022] The high-density cluster center of each group is defined as the candidate intersection c k .

[0023] Optionally, extracting a directed road segment based on a candidate intersection specifically includes:

[0024] From the corrected GPS trajectory point set T'={P1,P2,...,P N} extract the intersections that pass through each pair of candidate intersections (c i ,c j ) of the trajectory segment T ij ; where c i ,c j ∈c k ;

[0025] Calculate trajectory segment T ij Direction vector Used to represent a directed road segment; where |T ij | represents the number of trajectory segments.

[0026] Optionally, generating an optimized road topology network based on the directed road segments specifically includes:

[0027] The candidate intersection c k As a vertex V={c k}, the directed road segment As an edge Construct a road topology network G = (V, E) and calculate the weight of each edge based on the road flow;

[0028] Graph optimization methods are used to eliminate redundant edges in the road topology network and generate an optimized road topology network.

[0029] Optionally, screening out candidate directed road segments based on the corrected GPS track points and the optimized road topology network specifically includes:

[0030] For each corrected GPS track point P i , based on the formula L ij ={l j |d(P i ,l j )≤50}Calculate P i All road sections within 50 meters L ij ; where d(P i ,l j ) represents the corrected GPS track point P i To section l j Distance; road section l j Selected from the optimized road topology network;

[0031] Using the formula θ i =arctan 2(y i -y i-1 ,xi -x i-1 )Calculate P i Compared with the previous corrected GPS track point P i-1 The direction angle θ between i ;

[0032] Using the formula Δθ ij =|θ i -φ j |Calculate the direction angle θ i Matched road segment l j The direction angle φ j The absolute value difference Δθ between ij ;

[0033] When Δθ ij When ≤90°, determine the corresponding road section l i are the selected candidate directional road segments.

[0034] In the second aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the method for constructing a metropolitan area transportation network topology and traffic matching based on individual-level GPS trajectory data.

[0035] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for constructing a metropolitan area transportation network topology and matching traffic based on individual-level GPS trajectory data.

[0036] In a fourth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the method for constructing a metropolitan area transportation network topology and matching traffic based on individual-level GPS trajectory data.

[0037] According to the specific embodiments provided in this application, this application discloses the following technical effects.

[0038] The present application provides a method, device, medium and product for constructing a metropolitan area traffic network topology and matching traffic based on individual-level GPS trajectory data. By using GPS trajectory data to identify road intersections and candidate directed road sections, the difficulty of data input and cleaning of new metropolitan area road networks is avoided. In the process of generating a road topology network, the original GPS trajectory line is evenly interrupted, which can better abstract multiple lane road sections into a multi-segment line, which is conducive to simplifying the complexity of the road network, while improving computing efficiency and overcoming the problem of GPS trajectory drift, providing redundancy for more accurate matching of GPS trajectories. By using the method of initially screening candidate directed road sections, secondarily screening candidate trajectory lines, and finally screening the most suitable trajectory lines and their corresponding directed road sections, the computing power pressure caused by the matching traffic of the entire road network topology is avoided, while meeting a higher quality of traffic matching results. The method of the present application improves the computing efficiency of the construction of the metropolitan area road network topology and traffic matching, and does not require much computing power from the hardware equipment, and can be deployed on a conventional PC for use. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0040] Figure 1 This is a flowchart of a method for constructing a metropolitan area transportation network topology and matching traffic flow based on individual-level GPS trajectory data in this application;

[0041] Figure 2 A schematic diagram of multiple original GPS track lines formed by cleaning original GPS track points in an exemplary embodiment;

[0042] Figure 3 A schematic diagram of a trajectory line formed by uniformly interrupted corrected GPS trajectory points in an exemplary embodiment;

[0043] Figure 4 An optimized road topology network diagram generated in an exemplary embodiment;

[0044] Figure 5 FIG. 4 is a schematic diagram of road traffic in different directions formed in an exemplary embodiment. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0046] The purpose of this application is to propose a method, device, medium and product for constructing the topology of a metropolitan area traffic network and matching traffic based on individual-level GPS trajectory data, so as to improve the computational efficiency of the topology construction and traffic matching of the metropolitan area traffic network and reduce the computing power requirements of the hardware equipment.

[0047] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0048] In an exemplary embodiment, Figure 1 As shown, a method for constructing a metropolitan area transportation network topology and matching traffic flow based on individual-level GPS trajectory data is provided, including the following steps 1 to 9.

[0049] Step 1: Connect the original GPS track points to form a continuous original GPS track line.

[0050] For each trip of each individual vehicle such as a motor vehicle or motorcycle, all GPS track data obtained are assigned a unique trip code. This application arranges all original GPS track points contained in each unique trip code in ascending order of timestamps and connects them in sequence to form a continuous original GPS track line, which is recorded as point set T = {p1, p2, ..., p n}, where each point (i.e. GPS track point) p i Including spatial coordinates (x i ,y i ) and timestamp t i ; n is the number of midpoints in the original GPS trajectory.

[0051] Step 2: Evenly interrupt the original GPS track line to form the corrected GPS track points.

[0052] According to the segmentation condition (1), the original GPS trajectory line T is evenly interrupted to form several interrupted trajectory segments. Each trajectory segment can be recorded as (p' i ,p' i+1 ) or (p' i-1 ,p' i ). where p' i-1 For point p' i The previous point, p' i+1For point p' i The last point.

[0053] |p i+1 -p i |≥d th (1)

[0054] d th Considering that the general distance between major intersections in China is more than 250 meters (based on the 8km / km specified in the national standard GB / T51328-2018), 2 The road network density is the reference standard), the red line width of a single road generally does not exceed 80 meters (calculated based on a maximum of eight lanes in both directions plus space for pedestrians and non-motor vehicles), and the calculation accuracy and other requirements, it is preferred to set the interruption distance at 100 meters, that is, set |p i+1 -p i |=100. Using this distance as the basis for the interruption method, we can more accurately abstract multiple lanes of a road into a single polyline, whose length and width meet the general scale requirements for Chinese roads.

[0055] Furthermore, the Kalman filter or sliding average method is used to analyze the interrupted trajectory segments (p' i-1 ,p' i ) is smoothed to form a corrected GPS track point. In an exemplary embodiment, the smoothing formula is as follows:

[0056]

[0057] Where α is a random number between 0 and 1. As the corrected GPS track point. For the convenience of subsequent description, the corresponding Denoted as P i , similarly, each point P i Including spatial coordinates (x i ,y i ) and timestamp t i Each corrected GPS track point P i The modified GPS trajectory point set T'={P1,P2,...,P N}, where N is the number of corrected GPS track points.

[0058] Step 3: Identify candidate intersections based on the corrected GPS trajectory points.

[0059] First, the corrected GPS trajectory point P i Density estimation and cluster analysis are performed to identify clusters. Intersections are then evaluated and detected.

[0060] Specifically, the corrected GPS trajectory point P is calculated using formula (3): i The local density ρ(P i ), using Gaussian kernel density estimation, where σ is the kernel bandwidth parameter:

[0061]

[0062] Use a density-based clustering algorithm (such as DBSCAN) to identify high-density areas. The formula is as follows:

[0063] C k ={P i ∣ρ(P i )>ρ th , and satisfy the neighborhood connection condition} (4)

[0064] where ρ th is the density threshold. C k represents the kth group.

[0065] The high-density cluster center c of each group k Defined as candidate intersection locations:

[0066]

[0067] where |C k | represents the number of clusters. The high-density cluster center of each cluster is defined as the candidate intersection c k .

[0068] Step 4: Extract directed road segments (or road sections) based on candidate intersections.

[0069] In the road segment extraction phase, trajectory segmentation is first performed to extract the trajectory segments that pass through each pair of candidate intersections from the trajectory T'. Then, direction vector calculation is performed.

[0070] Specifically, from the corrected GPS trajectory point set T'={P1,P2,...,P N} extract the intersections that pass through each pair of candidate intersections (c i ,c j ) of the trajectory segment T ij =(P i ,P j ). where c i ,c j ∈c k , that is, each pair of candidate intersections (c i ,c j ) are selected from the candidate intersection c identified in step 3 k .

[0071] Furthermore, the trajectory segment T is calculated using formula (6)ij Direction vector Used to represent directed road segments:

[0072]

[0073] where |T ij | represents the number of trajectory segments.

[0074] For each road segment with multiple lanes, it is better to use the GPS 100-meter interruption method in step 2 to abstract it into a single line. Then, after steps 3 and 4, multiple lanes can form a bidirectional topological road segment, which is called a directed road segment in this application. The direction vector of the road segment is represented by express.

[0075] Step 5: Generate an optimized road topology network based on the directed road segments.

[0076] First, generate a topological network. Specifically, the candidate intersection c k As a vertex V={c k}, the directed road segment As an edge Construct a road topology network G = (V, E) and calculate the weight w for each edge based on road traffic ij :

[0077]

[0078] Road traffic volume refers to the number of trips on a road.

[0079] Then, topology optimization is performed. Specifically, a minimum spanning tree (MST) or other graph optimization methods are used to eliminate redundant edges in the road topology network G = (V, E) to generate an optimized road topology network.

[0080] Step 6: Filter out candidate directed road segments based on the corrected GPS trajectory points and the optimized road topology network.

[0081] Step 6 uses the GPS track points corrected in step 2 and the basic distribution road topology network formed in steps 3 to 5 as input to screen candidate directional road segments. First, screen the candidate road buffer to reduce the amount of calculation and avoid the meaningless increase in the amount of calculation of the direction angle of the entire road network topology. Specifically, the corrected GPS track point P i , calculate all road sections L within 50 meters of each trajectory point ij As a buffer zone. Secondly, the direction angle difference is calculated for the road section L filtered through the 50-meter range. ij Perform secondary screening. Each evenly interrupted trajectory point P i , calculate the difference between the previous trajectory point P i-1 The direction angle θi , and the trajectory point direction angle θ i The direction angle φ that matches the road topology j For comparison, if the absolute value difference Δθ ij If the angle is greater than 90° (i.e., it deviates to the left or right by more than 90°), it is considered that the trajectory point P should not be i With road section l i The specific method for screening candidate directed road segments is as follows.

[0082] For each corrected GPS track point P i , calculate P based on formula (8) i All road sections within 50 meters L ij :

[0083] L ij ={l j |d(P i ,l j )≤50} (8)

[0084] Where d(P i ,l j ) represents the corrected GPS track point P i To section l j Distance; road section l j Selected from the optimized road topology network in step 5.

[0085] Next, use formula (9) to calculate P i Compared with the previous corrected GPS track point P i-1 The direction angle θ between i :

[0086] θ i =arctan2(y i -y i-1 ,x i -x i-1 ) (9)

[0087] Where (x i ,y i ) and (x i-1 ,y i-1 ) are points P i and point P i-1 The spatial coordinates of .

[0088] Next, use formula (10) to calculate the direction angle θ i Matched road segment l j The direction angle φ j The absolute value difference Δθ between ij :

[0089] Δθij =|θ i -φ j | (10)

[0090] Among them, the matching road segment l j The direction angle φ j It refers to the angle between the line connecting the corrected GPS track points and the road section at the same location.

[0091] When Δθ ij When ≤90°, determine the corresponding road section l i are the selected candidate directional road segments.

[0092] Step 7: Generate candidate trajectory routes based on the starting and ending points of the original GPS trajectory and the candidate directed road segments.

[0093] First, the starting and ending points of the original GPS trajectory corresponding to each trip code are selected, i.e., the origin and destination points of the original GPS trajectory. The possible roads between the starting and ending points are the candidate roads selected in step 6. Next, the Dijkstra shortest path algorithm is executed on the candidate roads to generate several candidate trajectory routes whose directions and origin and destination points all match the original GPS trajectory.

[0094] Step 8: Determine the trajectory route and its corresponding directed road segment that best matches the original GPS trajectory line from the candidate trajectory routes as the target trajectory route and target directed road segment.

[0095] The D* algorithm uses the shortest sum of distances from each original GPS track point to the nearest segment in each candidate track line as the criterion to determine the most suitable path. This criterion allows us to determine the track line that best matches the original GPS track line from among the candidate track lines. The track line that best matches the original GPS track line and its corresponding segment are used as the target track line and target directed segment.

[0096] Step 9: Generate directional road traffic based on all target trajectory lines and target directed road segments.

[0097] This application is aimed at the traffic network topology within the scope of a metropolitan area or a one-hour traffic circle, in which different trips of different vehicles correspond to different trip codes and different GPS trajectory data. The above steps 1 to 8 describe a method for matching the target trajectory route and the target directional road section for each original GPS trajectory line. For all candidate trajectory routes and trajectory points within the metropolitan area, all the most suitable target trajectory routes and target directional road sections are determined according to the principle of the shortest distance from the original GPS trajectory line to the candidate trajectory route. By statistically analyzing all target trajectory routes and target directional road sections on the optimized road topology network, the road flow of each road section can be obtained. And because the road sections of this application all have direction vectors, directional road flow can be formed.

[0098] The present invention proposes a highly integrated and efficient method for constructing the topology of a metropolitan area traffic network and matching traffic flow, which mainly solves the limitations of efficiency and design in the matching and distribution of traditional GPS trajectory data with road networks. By using GPS trajectory data to identify road intersections and candidate directed road segments, the difficulty of data input and cleaning of new metropolitan area road networks is avoided. In the method of generating a road topology network, taking 100 meters as a benchmark, it is possible to better abstract multiple lane road segments into a multi-segment line, which is conducive to simplifying the complexity of the road network, while improving computational efficiency and overcoming the problem of GPS trajectory drift, and providing redundancy for more accurate matching of GPS trajectories. By using the method of initial screening of the road network using a trajectory point buffer, secondary screening using Dijkstra start and end points, and final screening using the shortest distance between trajectory points, the computing pressure caused by matching traffic to the entire road network topology is avoided, while meeting a higher quality of results. This method can efficiently extract transportation networks such as public transportation, motor vehicle lanes, and non-motor vehicle lanes within China's metropolitan areas, while quickly generating road traffic flows that include simplified topological road network directions. It also supports the re-creation, matching, and backtracking of travel trajectories for single, multiple, or metropolitan area road segments, improving the computational efficiency of metropolitan area transportation network topology construction and traffic flow matching. Furthermore, this application method requires minimal computing power from hardware devices and can be deployed on a regular PC.

[0099] Figures 2 to 5 An exemplary embodiment of the method of the present application for urban traffic network topology construction and flow matching is shown, wherein the blue line segment represents the generation process of the road network topology. Specifically, the multiple original GPS track lines formed by cleaning the original GPS track points in step 1 are as follows: Figure 2 As shown. The trajectory line formed by the corrected GPS trajectory points formed by uniform interruption in step 2 is as follows Figure 3 As shown. The optimized road topology network generated after steps 3 to 5 is as follows Figure 4 As shown. The directional road traffic formed through steps 6 to 9 is reflected in the road topology network as follows Figure 5As shown, the red section has the heaviest traffic, followed by yellow and then green.

[0100] In an exemplary embodiment, the present application also provides a computer device, which can be a server or a terminal. The computer device includes a processor, a memory, an input / output interface, and a communication interface. The processor, the memory, and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the method for constructing a metropolitan area traffic network topology and matching traffic based on individual-level GPS trajectory data is implemented.

[0101] In an exemplary embodiment, the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for constructing a metropolitan area transportation network topology and matching traffic based on individual-level GPS trajectory data.

[0102] In an exemplary embodiment, the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the method for constructing a metropolitan area transportation network topology and matching traffic based on individual-level GPS trajectory data.

[0103] It will be understood by those skilled in the art that all or part of the processes in the above-mentioned embodiment method can be completed by hardware related to computer program instructions, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the process of the embodiment of the above-mentioned method. Among them, any reference to memory or other media in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0104] It should be noted that the information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0105] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0106] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for constructing metropolitan area transportation network topology and matching traffic flow based on individual-level GPS trajectory data, characterized in that: include: Connect the original GPS track points to form a continuous original GPS track line; Arrange all the original GPS track points contained in each unique travel code in ascending order of timestamps and connect them in sequence to form a continuous original GPS track line, which is recorded as point set T = {p1, p2, ..., p n }, each point p i Including spatial coordinates (x i ,y i ) and timestamp t i ; n is the number of midpoints of the original GPS trajectory; Evenly interrupt the original GPS track line to form the corrected GPS track points; According to the segmentation condition (1), the original GPS trajectory line T is evenly interrupted to form several interrupted trajectory segments, each of which is recorded as (p′ i ,p′ i+1 ) or (p′ i-1 ,p′ i ); where p′ i-1 is point p′ i The previous point, p′ i+1 is point p′ i The last point of |p i+1 -p i |≥d th (1) d th For the distance threshold, set the interruption distance to 100 meters; Use Kalman filtering or sliding average method to smooth the interrupted trajectory segment (p′i-1, p′i) to form the corrected GPS trajectory point. The smoothing formula is as follows: Where α is a random number between 0 and 1; the smoothed trajectory points As the corrected GPS track point, the corresponding Denoted as P i ; Each point P i Including spatial coordinates (x i ,y i ) and timestamp t i ; Each corrected GPS track point P i The modified GPS trajectory point set T′={P1,P2,...,P N }, where N is the number of corrected GPS track points; Identify candidate intersections based on the corrected GPS trajectory points; First, the corrected GPS trajectory point P i Perform density estimation and cluster analysis to identify clusters; then, evaluate and detect intersections; Specifically, the corrected GPS trajectory point P is calculated using formula (3): i The local density ρ(P i ), using Gaussian kernel density estimation, where σ is the kernel bandwidth parameter: Use density-based clustering algorithm to identify high-density areas. The formula is as follows: C k ={P i |ρ(P i )>ρ th , and satisfy the neighborhood connection condition} (4) where ρ th is the density threshold; C k represents the kth group; The high-density cluster center c of each group k Defined as candidate intersection locations: where |C k | represents the number of clusters; the high-density cluster center of each cluster is defined as the candidate intersection c k ; Extract directed road segments based on candidate intersections; In the road segment extraction stage, trajectory segmentation is first performed to extract the trajectory segments that pass through each pair of candidate intersections from the trajectory T′; then, direction vector calculation is performed; Specifically, from the corrected GPS trajectory point set T′={P1, P2, ..., P N } extract the intersections that pass through each pair of candidate intersections (c i ,c j ) of the trajectory segment T ij =(P i , P j ); where c i ,c j ∈c k , that is, each pair of candidate intersections (c i ,c j ) are selected from the identified candidate intersections c k ; Furthermore, the trajectory segment T is calculated using formula (6) ij Direction vector Used to represent directed road segments: where |T ij | represents the number of trajectory segments; For each road segment with multiple lanes, the GPS 100-meter interruption method is used to abstract it into a single line; then, after the above steps, multiple lanes can form a bidirectional topological road segment, called a directed road segment, and the direction vector of the road segment is expressed as express; Generate an optimized road topology network based on directed road segments; Screen out candidate directed road segments based on the corrected GPS trajectory points and the optimized road topology network; Generate candidate trajectory routes based on the starting and ending points of the original GPS trajectory and the candidate directed road segments; Determine the trajectory route and its corresponding directed road segment that best matches the original GPS trajectory line from the candidate trajectory routes as the target trajectory route and target directed road segment; Directional road traffic is generated based on all target trajectory routes and target directional road segments.

2. The method for constructing a metropolitan area transportation network topology and matching traffic volume based on individual-level GPS trajectory data according to claim 1, characterized in that: Generating an optimized road topology network based on the directed road segments specifically includes: The candidate intersection c k As a vertex V={c k }, the directed road segment As an edge Construct a road topology network G = (V, E) and calculate the weight of each edge based on the road flow; Graph optimization methods are used to eliminate redundant edges in the road topology network and generate an optimized road topology network.

3. The method for constructing a metropolitan area transportation network topology and matching traffic volume based on individual-level GPS trajectory data according to claim 2, characterized in that: The method of screening candidate directed road segments based on the corrected GPS track points and the optimized road topology network specifically includes: For each corrected GPS track point P i , based on the formula L ij ={l j |d(P i ,l j )≤50}Calculate P i All road sections within 50 meters L ij ; where d(P i ,l j ) represents the corrected GPS track point P i To section l j Distance; road section l j Selected from the optimized road topology network; Using the formula θ i =arctan 2(y i -y i-1 , x i -x i-1 )Calculate P i Compared with the previous corrected GPS track point P i-1 The direction angle θ between i ; Using the formula Δθ ij =|θ i -φ j |Calculate the direction angle θ i Matched road segment l j The direction angle φ j The absolute value difference Δθ between ij ; When Δθ ij When ≤90°, determine the corresponding road section l j are the selected candidate directional road segments.

4. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the method for constructing a metropolitan area transportation network topology and traffic matching based on individual-level GPS trajectory data as described in any one of claims 1 to 3.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for constructing a metropolitan area transportation network topology and matching traffic based on individual-level GPS trajectory data according to any one of claims 1 to 3 is implemented.

6. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for constructing a metropolitan area transportation network topology and matching traffic based on individual-level GPS trajectory data according to any one of claims 1 to 3 is implemented.

Images