A method, device, and computer medium for identifying the supply capacity of a transient transportation network

Abstract

The present invention proposes a method, device and computer medium for identifying the supply capacity of a transient traffic network. The method measures the road operation of the road network based on the data of the road vehicle license plate recognition system, calculates the congestion index based on the average shortest path length by considering the deterioration of the road network, trains a K-Means classifier based on the congestion index, and uses the trained K-Means classifier to classify the operation status of the road section at different time periods to obtain the supply capacity of the traffic network. The advantages of the present invention are that a congestion index based on the average shortest path length is designed to evaluate the supply capacity of the road network, which can efficiently and accurately reflect the supply capacity of the traffic network. In addition, the present invention realizes the demand for real-time reflection of the supply capacity of the traffic network by obtaining the data of the road vehicle license plate recognition system.

Description

Technical Field

[0001] The present invention relates to the technical field of road traffic network supply capacity analysis, and in particular to a method, device and computer medium for identifying transient traffic network supply capacity. Background Art

[0002] The uncertainty of traffic demand makes it difficult for traffic managers to accurately grasp the operation of urban road networks. Understanding the operation of road networks is crucial for formulating reasonable traffic control plans. Therefore, there is an urgent need for efficient and accurate methods to determine the remaining supply capacity of road networks.

[0003] At present, the research on the surplus supply capacity of the transportation network at home and abroad is mainly carried out from the perspective of road network traffic reliability evaluation. The research on traffic reliability evaluation began with connectivity reliability analysis, which was proposed by Mine and Kawai in 1982. The probability of a connectivity relationship between two nodes is used to measure connectivity reliability. However, this method is not applicable to urban road networks in general.

[0004] In the existing technology, the method of determining connectivity reliability by comprehensively considering section flow and road capacity can meet the needs of measuring the basic traffic capacity of the road network under abnormal conditions, but it is not applicable to the evaluation under normal traffic conditions; the method of judging the remaining supply capacity of the traffic network based on travel time reliability does not take into account the impact of the road use rights of many road users (including pedestrians) on road flow distribution.

[0005] In summary, there is an urgent need for an efficient, feasible and usable method for identifying the supply capacity of a transportation network that can accurately reflect the operating status of the entire road network using actual road condition data to solve the problems existing in the prior art. Summary of the invention

[0006] The present invention aims to provide a method, device and computer medium for identifying transient traffic network supply capacity. The specific technical solution is as follows:

[0007] A method for identifying transient traffic network supply capacity, the specific steps are as follows:

[0008] Step S1: Obtaining road vehicle license plate recognition system data and real, physical traffic network G m Specifically, determine the area, obtain the road vehicle license plate recognition system data in the area; build a real, physical traffic network G based on the road segment set and node set in the area m ;

[0009] Step S2: Obtain the traffic network G under different road degradation conditions nSpecifically, according to the data of the road vehicle license plate recognition system, it is determined whether the road section within the time period is a deteriorated road section, based on the deteriorated road section and the traffic network G m Get the traffic network G under different road degradation conditions n ;

[0010] Step S3: Calculate the congestion index and the number of reasonable classifications. Specifically, according to the traffic network G obtained in step S2 n The congestion index in each time period is calculated based on the average shortest path length; based on the traffic network G m and transportation network G n The normalized spectral distance average value is used to determine the number of categories of the K-Means clustering algorithm, that is, the reasonable number of classifications;

[0011] Step S4: training a K-Means classifier, specifically, obtaining an evaluation index data set of the road network in each time period based on the congestion index in step S3, and training a K-Means classifier according to the evaluation index data set and the reasonable classification number;

[0012] Step S5: Obtaining the traffic network supply capacity result, specifically, obtaining the traffic network supply capacity result based on the trained K-Means classifier and congestion index.

[0013] Specifically, in step S1, the road vehicle license plate recognition system data includes the road capacity, free flow time and OD (Origin-Destination) data of each road.

[0014] Specifically, in step S2, the traffic network G is obtained. n The method is as follows: For the traffic network G m , determine whether removing the degraded road section affects the connectivity of any OD pair. If it affects the connectivity of any OD pair, the degraded road section is retained; if it does not affect the connectivity of any OD pair, the degraded road section is removed from the road section set; after removing the degraded road section, a new road section set is obtained, and the traffic network G is obtained after updating based on the new road section set n .

[0015] Specifically, in step S2, the method for determining the deteriorated road section is as follows:

[0016] like It means that the road section a is in a deteriorated state within the time period p; if This means that the road section a is not in a deteriorated state within the time period p;

[0017] in, represents the average road travel time of vehicles on road section a in time period p; δ is the degradation coefficient; Represents the free flow time of section a.

[0018] Specifically, in step S3, the congestion index T p The expression is as follows:

[0019]

[0020] Among them, Q p represents the total traffic volume of the road network in time period p; represents the traffic volume from node i to node j in time period p; Indicates the actual duration of the shortest path from node i to node j in time period p; represents the shortest free flow time from node i to node j; N represents the traffic network G m or transportation network G n The set of all nodes in .

[0021] Specifically, in step S3, the traffic network G m and transportation network G n The normalized spectral distance d NSD (G m , G n ) is calculated as follows:

[0022]

[0023] in, Represents the adjacency matrix X m The i-th component of the corresponding eigenvalue, X m Represents the traffic network G m The corresponding adjacency matrix; Represents the adjacency matrix X n The i-th component of the corresponding eigenvalue, X n Represents the traffic network G n The corresponding adjacency matrix.

[0024] Specifically, in step S3, the average value of the normalized spectral distance The calculation formula is as follows:

[0025]

[0026] Among them, C h represents the hth type of road network; k h It indicates the number of road networks contained in the h-th type of road network; H indicates the number of reasonable classifications.

[0027] In addition, the present invention also provides a device for identifying transient traffic network supply capacity, comprising:

[0028] Memory for storing computer programs;

[0029] A processor is used to implement the above-mentioned transient traffic network supply capacity identification method when executing the computer program.

[0030] In addition, the present invention also proposes a computer medium, on which a computer program is stored, and when the computer program is executed by a processor, the transient traffic network supply capacity identification method as described above is implemented.

[0031] The application of the technical solution of the present invention has the following beneficial effects:

[0032] The present invention achieves the purpose of reflecting the supply capacity of the traffic network in real time by acquiring the data of the road vehicle license plate recognition system, which plays a vital role in formulating a reasonable traffic control plan.

[0033] The present invention designs a congestion index based on the average shortest path length, and judges the supply capacity of a road section in a traffic network according to the congestion index, thereby realizing efficient and accurate reflection of the supply capacity of the traffic network.

[0034] In addition to the above-described purposes, features and advantages, the present invention has other purposes, features and advantages. The present invention will be further described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The drawings constituting a part of this application are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0036] Figure 1 is a flow chart of the steps of a method for identifying supply capacity of a transient transportation network;

[0037] Figure 2 It is the result of the transportation network supply capacity of a certain square. DETAILED DESCRIPTION

[0038] The embodiments of the present invention are described in detail below with reference to the accompanying drawings, but the present invention can be implemented in many different ways as defined and covered by the claims.

[0039] The uncertainty of traffic demand makes it difficult for traffic managers to accurately grasp the operation of urban road networks. Understanding the operation of road networks is crucial to formulating reasonable traffic control plans. In order to solve the problem of using road vehicle license plate recognition system data to obtain the real-time operation status of urban roads, the real-time vehicle travel time on the road is extracted and analyzed to obtain the real-time operation status of urban roads. This embodiment proposes a method, device and computer medium for identifying the supply capacity of a transient traffic network.

[0040] Embodiment 1:

[0041] This embodiment implements a method for identifying transient traffic network supply capacity, and the specific steps are as follows:

[0042] Step S1: Obtaining road vehicle license plate recognition system data and real, physical traffic network G m Specifically, determine the area, obtain the road vehicle license plate recognition system data in the area; construct a traffic network G based on the road segment set and node set in the area m ;

[0043] Step S2: Obtain the traffic network G under different road degradation conditions n Specifically, according to the data of the road vehicle license plate recognition system, it is determined whether the road section within the time period is a deteriorated road section, based on the deteriorated road section and the traffic network G m Get the traffic network G under different road degradation conditions n ;

[0044] Step S3: Calculate the congestion index and the number of reasonable classifications. Specifically, according to the traffic network G obtained in step S2 n The congestion index in each time period is calculated based on the average shortest path length; based on the traffic network G m and transportation network G n The normalized spectral distance average value is used to determine the number of categories of the K-Means clustering algorithm, that is, the reasonable number of classifications;

[0045] Step S4: training a K-Means classifier, specifically, obtaining an evaluation index data set of the road network in each time period based on the congestion index in step S3, and training a K-Means classifier according to the evaluation index data set and the reasonable classification number;

[0046] Step S5: Obtaining the traffic network supply capacity result, specifically, obtaining the traffic network supply capacity result based on the trained K-Means classifier and congestion index.

[0047] Specifically, in step S1, the road vehicle license plate recognition system data includes the road capacity, free flow time, and OD (Origin-Destination, i.e., origin-destination matrix) data of each road.

[0048] Specifically, in step S2, the traffic network G is obtained. n The method is as follows: For the traffic network G m, determine whether removing the degraded road section affects the connectivity of any OD pair. If it affects the connectivity of any OD pair, the degraded road section is retained; if it does not affect the connectivity of any OD pair, the degraded road section is removed from the road section set; after removing the degraded road section, a new road section set is obtained, and the traffic network G is obtained after updating based on the new road section set n .

[0049] It should be noted that the transportation network G m and transportation network G n The difference between them is the set of road segments, and their node sets are the same.

[0050] Specifically, in step S2, the method for determining the deteriorated road section is as follows:

[0051] like It means that the road section a is in a deteriorated state within the time period p; if This means that the road section a is not in a deteriorated state within the time period p;

[0052] in, represents the average road travel time of vehicles on road section a in time period p; δ is the degradation coefficient, and the preferred δ in this embodiment is 0.4; Represents the free flow time of section a.

[0053] Specifically, in step S3, the congestion index T p The expression is as follows:

[0054]

[0055] Among them, Q p represents the total traffic volume of the road network in time period p; represents the traffic volume from node i to node j in time period p; Indicates the actual duration of the shortest path from node i to node j in time period p; represents the shortest free flow time from node i to node j; N represents the traffic network G m or transportation network G n The set of all nodes in .

[0056] Specifically, in step S3, the traffic network G m and transportation network G n The normalized spectral distance d NSD (G m , G n ) is calculated as follows:

[0057]

[0058] in, Represents the adjacency matrix Xm The i-th component of the corresponding eigenvalue, X m Represents the traffic network G m The corresponding adjacency matrix; Represents the adjacency matrix X n The i-th component of the corresponding eigenvalue, X n Represents the traffic network G n The corresponding adjacency matrix.

[0059] Specifically, the average value of the normalized spectral distance The calculation formula is as follows:

[0060]

[0061] Among them, C h represents the hth type of road network; k h It indicates the number of road networks contained in the h-th type of road network; H indicates the number of reasonable classifications.

[0062] Applying the above technical solution, the specific test cases are as follows:

[0063] The experiment selected a road network near a square and analyzed its transportation network supply capacity within two weeks.

[0064] like Figure 2 The traffic network supply capacity results of a certain square are shown, where category 1 indicates good road network supply capacity; category 2 indicates average road network supply capacity; category 3 indicates poor road network supply capacity; and category 4 indicates extremely poor road network supply capacity.

[0065] The analysis of the traffic network supply capacity identification results shows that the remaining supply capacity of the road network is significantly deteriorated during the morning and evening peak hours, that is, the remaining supply capacity of the road network is poor, and the road network is mostly in category 3 state, and the road network may be in an extremely poor state of remaining supply capacity during the evening peak hours, that is, the road network is category 4. And compared with weekdays, the remaining supply capacity of the road network is better during the morning and evening peak hours on weekends (6th, 7th, 13th), that is, the traffic network supply capacity identification results are in line with the actual situation. It can be concluded that the transient traffic network supply capacity identification method implemented in this embodiment can accurately identify the road traffic supply capacity.

[0066] This embodiment measures the road network operation status based on the road vehicle license plate recognition system data, and then constructs a congestion index based on the average shortest path length to measure the road network degradation. According to the above index results, a K-Means classifier is trained, and the trained K-Means classifier is used to classify the operation status of the road network in different time periods to obtain the transportation network supply capacity. The method proposed in this embodiment can reflect the transportation network supply capacity in real time, efficiently and accurately.

[0067] Embodiment 2:

[0068] This embodiment implements a transient traffic network supply capacity identification device, including:

[0069] Memory for storing computer programs;

[0070] A processor is used to implement the method for identifying the supply capacity of a transient traffic network as described in Example 1 when executing the computer program.

[0071] Embodiment 3:

[0072] This embodiment implements a computer medium on which a computer program is stored. When the computer program is executed by a processor, the method for identifying the supply capacity of a transient traffic network as described in Embodiment 1 is implemented.

[0073] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0074] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0075] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for identifying transient traffic network supply capacity, characterized in that: The specific steps are as follows: Step S1: Obtaining road vehicle license plate recognition system data and real, physical traffic network G m Specifically, determine the area, obtain the road vehicle license plate recognition system data in the area; build a real, physical traffic network G based on the road segment set and node set in the area m ; Step S2: Obtain the traffic network G under different road degradation conditions n Specifically, according to the data of the road vehicle license plate recognition system, it is determined whether the road section within the time period is a deteriorated road section, based on the deteriorated road section and the traffic network G m Get the traffic network G under different road degradation conditions n ; Step S3: Calculate the congestion index and the number of reasonable classifications. Specifically, according to the traffic network G obtained in step S2 n The congestion index in each time period is calculated based on the average shortest path length; based on the traffic network G m and transportation network G n The normalized spectral distance average value is used to determine the number of categories of the K-Means clustering algorithm, that is, the reasonable number of classifications; Step S4: training a K-Means classifier, specifically, obtaining an evaluation index data set of the road network in each time period based on the congestion index in step S3, and training a K-Means classifier according to the evaluation index data set and the reasonable classification number; Step S5: Obtaining the traffic network supply capacity result, specifically, obtaining the traffic network supply capacity result based on the trained K-Means classifier and congestion index.

2. The method for identifying transient traffic network supply capacity according to claim 1, characterized in that: In step S1, the road vehicle license plate recognition system data includes the road capacity, free flow time and OD (Origin-Destination) data of each road.

3. The method for identifying transient traffic network supply capacity according to claim 2, characterized in that: In step S2, the traffic network G is obtained. n The method is as follows: For the traffic network G m , determining whether removing the degraded road section affects the connectivity of any OD pair, if it affects the connectivity of any OD pair, retaining the degraded road section; if it does not affect the connectivity of any OD pair, removing the degraded road section from the road section set; After removing the deteriorated road sections, a new road section set is obtained, and the traffic network G is obtained after updating based on the new road section set. n .

4. The method for identifying transient traffic network supply capacity according to claim 3, characterized in that: In step S2, the method for determining the deteriorated road section is as follows: like It means that the road section a is in a deteriorated state within the time period p; if This means that the road section a is not in a deteriorated state within the time period p; in, represents the average road travel time of vehicles on road section a in time period p; δ is the degradation coefficient; Represents the free flow time of section a.

5. The method for identifying transient traffic network supply capacity according to claim 4, characterized in that: In step S3, the congestion indicator T p The expression is as follows: Among them, Q p represents the total traffic volume of the road network in time period p; represents the traffic volume from node i to node j in time period p; Indicates the actual duration of the shortest path from node i to node j in time period p; represents the shortest free flow time from node i to node j; N represents the traffic network G m or transportation network G n The set of all nodes in .

6. The method for identifying transient traffic network supply capacity according to claim 5, characterized in that: In step S3, the traffic network G m and transportation network G n The normalized spectral distance d NSD (G m , G n ) is calculated as follows: in, Represents the adjacency matrix X m The i-th component of the corresponding eigenvalue, X m Represents the traffic network G m The corresponding adjacency matrix; Represents the adjacency matrix X n The i-th component of the corresponding eigenvalue, X n Represents the traffic network G n The corresponding adjacency matrix.

7. The method for identifying transient traffic network supply capacity according to claim 6, characterized in that: In step S3, the average value of the normalized spectral distance is The calculation formula is as follows: Among them, C h represents the hth type of road network; k h It indicates the number of road networks contained in the h-th type of road network; H indicates the number of reasonable classifications.

8. A device for identifying transient traffic network supply capacity, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the method for identifying the supply capacity of a transient traffic network as claimed in any one of claims 1 to 7 when executing the computer program.

9. A computer medium, characterized in that The computer medium stores a computer program, and when the computer program is executed by a processor, the method for identifying the supply capacity of a transient traffic network as claimed in any one of claims 1 to 7 is implemented.

Images