Urban road congestion critical path identification method and device

Abstract

The invention relates to an urban road congestion critical path identification method and device, and belongs to the technical field of road traffic management, and the method comprises the steps: obtaining a target model and a graph neural network interpretation algorithm; the target model is an urban road congestion fitting model constructed based on a graph neural network; an urban road congestion instance map is obtained through prediction of the target model; performing important sub-graph recognition on the urban road congestion instance graph through a graph neural network interpretation algorithm to obtain a target sub-graph; the target sub-graph comprises nodes, connecting edges between the nodes and weights of the connecting edges; and determining a congestion critical path in the urban road congestion instance graph according to the weight of the connecting edge in the target sub-graph. According to the method, the key paths causing urban road congestion can be reasonably identified, and a basis is provided for prevention and alleviation of urban road congestion.

Description

Technical Field

[0001] The present invention relates to the technical field of road traffic management, and in particular to a method and device for identifying a critical path for urban road congestion. Background Art

[0002] Traffic congestion has always been the main problem that hinders the "good travel" of urban residents in various cities in my country. How to prevent or alleviate traffic congestion is also a difficulty and pain point in the current field of urban road traffic management. Therefore, if the key paths that cause traffic congestion can be identified and effective control measures can be taken in a timely manner, it will be of great significance to improving the travel experience of urban residents.

[0003] Since the urban road traffic system is a complex and fluctuating system with nonlinear changes, the generation of traffic congestion is extremely random, which makes it difficult to identify the key paths that cause traffic congestion, and there is currently no recognized and reliable means to achieve this goal. Graph Neural Networks (GNNs), as a machine learning method, is currently the most accurate method in the field of traffic prediction. However, GNNs have the common problem of previous machine learning methods: the prediction process is like a black box, and no explanation for the prediction can be given; therefore, GNNs themselves cannot help traffic managers identify the key paths that cause traffic congestion. Summary of the invention

[0004] In view of this, it is necessary to provide a method and device for identifying critical paths of urban road congestion to solve the problem in the prior art that traffic status prediction through graph neural networks cannot help traffic managers identify critical paths that cause traffic congestion.

[0005] In order to solve the above problems, in a first aspect, the present invention provides a method for identifying a critical path of urban road congestion, comprising: Obtaining a target model and a graph neural network interpretation algorithm; the target model is an urban road congestion fitting model constructed based on a graph neural network; Obtaining an example map of urban road congestion through prediction of the target model; Using the graph neural network interpretation algorithm, important subgraphs are identified on the urban road congestion example graph to obtain a target subgraph; the target subgraph includes nodes, connecting edges between nodes, and weights of connecting edges; According to the weights of the connecting edges in the target subgraph, a congestion critical path in the urban road congestion example graph is determined.

[0006] Optionally, the graph neural network interpretation algorithm is a GNNExplainer algorithm.

[0007] Optionally, the target subgraph includes congested nodes; and determining the congested critical path in the urban road congestion example graph according to the weights of the connecting edges in the target subgraph includes: Taking the connection edge in the target subgraph whose weight is greater than a preset weight threshold as the target connection edge; A target critical path causing congestion of the congested node is determined according to the target connection edge and the congested node.

[0008] Optionally, determining, according to the target connection edge and the congested node, a target critical path causing congestion of the congested node includes: Determine at least one sub-target critical path that causes congestion of the congested node according to the target connection edge and the congested node; Determine the average weight of the connecting edges in each of the sub-goal critical paths; The sub-target critical path with the largest average weight is used as the target critical path.

[0009] Optionally, the example map of urban road congestion obtained by predicting the target model includes: Coupling the target model with the graph neural network interpretation algorithm to obtain a coupled model; Obtaining an example diagram of urban road congestion through prediction of the target model in the coupling model; The important subgraphs of the urban road congestion example graph are identified by the graph neural network interpretation algorithm to obtain the target subgraph, including: The graph neural network interpretation algorithm in the coupling model is used to identify important subgraphs of the urban road congestion example graph to obtain a target subgraph.

[0010] Optionally, the acquiring the target model includes: Obtain node identification, node connection information, node traffic parameter information and node traffic congestion status of urban road network nodes; A target model is constructed according to the node identification, node connection information, node traffic parameter information and node traffic congestion status.

[0011] Optionally, obtaining the node traffic congestion status includes: Obtaining the mapping relationship between traffic parameter information and traffic congestion status; The node traffic congestion state is determined according to the node traffic parameter information and the mapping relationship.

[0012] Optionally, the target model is trained in the following manner: Construct a node adjacency matrix based on the node identifier and the node connection information A {w ij}, where w ij It is expressed as follows: ; The target model is used to make predictions based on the adjacency matrix and the node traffic parameter information; wherein the prediction process of the target model is expressed by the following formula: ,in, Represents all nodes respectively t- n , t-n+1 , t The characteristic vector of the node traffic parameter information detected at all times, A represents the adjacency matrix, represents the parameters of the target model, represents the prediction process, Represents all nodes t +1 Predicted node traffic congestion status at time; According to the preset loss function of the target model, the predicted node traffic congestion status and the node traffic congestion status, the parameters of the target model are adjusted until the parameters meet the preset requirements.

[0013] Optionally, the target model is a three-layer network model, wherein the first and second layers are graph attention networks in the graph neural network, and the third layer is a fully connected linear output layer; the activation function of the graph attention network is the Mish function, and the loss function of the target model is the multi-classification cross entropy loss function lose .

[0014] In a second aspect, the present invention further provides a device for identifying a critical path of urban road congestion, comprising: A model and model interpretation algorithm acquisition module, used to acquire a target model and a graph neural network interpretation algorithm; the target model is an urban road congestion fitting model built based on a graph neural network; A congestion instance prediction module, used to predict and obtain a city road congestion instance map through the target model; An important subgraph identification module is used to identify important subgraphs of the urban road congestion example graph through the graph neural network interpretation algorithm to obtain a target subgraph; the target subgraph includes nodes, connecting edges between nodes, and weights of connecting edges; The congestion critical path determination module is used to determine the congestion critical path in the urban road congestion example graph according to the weights of the connecting edges in the target subgraph.

[0015] The beneficial effects of the present invention are: The target model is obtained and an example diagram of urban road congestion is obtained through prediction by the target model; wherein the target model is a fitting model of urban road congestion constructed based on a graph neural network; the present invention continues to use the graph neural network model to predict traffic congestion conditions to ensure the accuracy of the prediction.

[0016] Further, a graph neural network interpretation algorithm is obtained, and the important subgraphs of the urban road congestion example graph are identified through the graph neural network interpretation algorithm to obtain the target subgraph; the target subgraph includes nodes, connecting edges between nodes, and the weights of the connecting edges; then, according to the weights of the connecting edges in the target subgraph, the congestion critical path in the urban road congestion example graph is determined. The graph neural network interpretation algorithm can compare the various subgraphs in the input urban road congestion example graph, and determine the target subgraph that plays a key role in the target model prediction process from each subgraph. The larger the weight of the connecting edge in the target subgraph, the more likely it is that the connecting edge is the congestion critical path. Therefore, by determining the congestion critical path according to the weight of the connecting edge in the target subgraph, the critical path that causes urban road congestion can be reasonably identified, thereby providing a basis for the prevention and relief of urban road congestion. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic diagram of a flow chart of an embodiment of a method for identifying a critical path for urban road congestion provided by the present invention; Figure 2 A flowchart of another embodiment of the critical path identification method provided by the present invention; Figure 3 A schematic diagram of a neural network model provided by the present invention; Figure 4 A schematic diagram of a target subgraph provided by the present invention; Figure 5 A schematic structural diagram of an embodiment of a device for identifying critical paths for urban road congestion provided by the present invention. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0019] In the description of the embodiments of the present invention, unless otherwise specified, "multiple" means two or more than two. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" may mean: A exists alone, A and B exist at the same time, and B exists alone.

[0020] The descriptions of "first", "second", etc. involved in the embodiments of the present invention are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the technical features defined as "first" and "second" may explicitly or implicitly include at least one of the features.

[0021] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0022] Reference Figure 1 , shows a flow chart of an embodiment of a method for identifying a critical path of urban road congestion provided by the present invention, the method comprising: Step S101, obtain the target model and the graph neural network interpretation algorithm; the target model is a city road congestion fitting model constructed based on the graph neural network.

[0023] Step S102, obtaining a city road congestion example map through target model prediction.

[0024] Step S103, using a graph neural network interpretation algorithm to identify important subgraphs of the urban road congestion example graph, and obtain a target subgraph; the target subgraph includes nodes, connecting edges between nodes, and weights of connecting edges.

[0025] Step S104, determining the critical congestion path in the urban road congestion example graph according to the weights of the connecting edges in the target subgraph.

[0026] The target model is a neural network model used to predict urban road congestion. The graph neural network interpretation algorithm is an algorithm used to analyze and explain the prediction results of the graph neural network.

[0027] The target model can first predict an urban road congestion instance graph, which is used to characterize the urban road congestion situation. The urban road congestion instance graph may include nodes, node identifiers, connecting edges between nodes, predicted node congestion status, etc. Nodes refer to but are not limited to any object that can be abstracted as a node, such as road endpoints, road sections, or road intersections. Node identifiers are used to identify nodes and to distinguish different nodes in the urban road network. The connecting edges between nodes represent the connection relationship between different nodes. If there is an upstream and downstream relationship between the traffic flows between nodes, there are edges between the nodes, otherwise, there are no edges. The predicted node congestion status can be represented by the node congestion degree, for example, no congestion, slight congestion, moderate congestion, etc.

[0028] The graph neural network explanation algorithm can be the GNNExplainer algorithm, which was proposed in 2019 to provide explainability of the GNN model decision process. GNNExplainer helps users understand how the model makes predictions by identifying the subgraph structure and node features that are most important for the GNN prediction results.

[0029] By using the graph neural network interpretation algorithm to identify important subgraphs of the urban road congestion example graph, we can obtain the target subgraph that plays a key role in the target model prediction process; the target subgraph includes nodes, the connecting edges between nodes, and the weights of the connecting edges. The larger the weight of the connecting edge, the more likely it is that the connecting edge is the key path causing congestion. Therefore, based on the target subgraph and the weights of the connecting edges in the target subgraph, the congestion key path in the urban road congestion example graph can be determined.

[0030] In the present invention, a target model is acquired and an example diagram of urban road congestion is obtained through prediction by the target model; wherein the target model is a fitting model of urban road congestion constructed based on a graph neural network; and the graph neural network model is used to predict traffic congestion to ensure the accuracy of the prediction.

[0031] Further, a graph neural network interpretation algorithm is obtained, and the important subgraphs of the urban road congestion example graph are identified through the graph neural network interpretation algorithm to obtain the target subgraph; the target subgraph includes nodes, connecting edges between nodes, and the weights of the connecting edges; then, according to the weights of the connecting edges in the target subgraph, the congestion critical path in the urban road congestion example graph is determined. The graph neural network interpretation algorithm can compare the various subgraphs in the input urban road congestion example graph, and determine the target subgraph that plays a key role in the target model prediction process from each subgraph. The larger the weight of the connecting edge in the target subgraph, the more likely it is that the connecting edge is the congestion critical path. Therefore, by determining the congestion critical path according to the weight of the connecting edge in the target subgraph, the critical path that causes urban road congestion can be reasonably identified, thereby providing a basis for the prevention and relief of urban road congestion.

[0032] In one embodiment, the target subgraph includes a congested node; step S104 may specifically include: taking a connection edge in the target subgraph whose weight is greater than a preset weight threshold as a target connection edge; and determining a target critical path that causes congestion of the congested node based on the target connection edge and the congested node.

[0033] In this embodiment, the connection edges in the target subgraph may be screened first to select target connection edges whose weights are greater than a preset weight threshold, and then the target critical path causing the congestion of the congested node may be determined based on the target connection edges and the congested node.

[0034] In one embodiment, the step of determining the target critical path that causes congestion of the congested node based on the target connecting edges and the congested nodes may specifically include: determining at least one sub-target critical path that causes congestion of the congested node based on the target connecting edges and the congested nodes; determining the average weight of the connecting edges in each sub-target critical path; and taking the sub-target critical path with the largest average weight as the target critical path.

[0035] In this embodiment, after the target connection edges are screened out, one or more sub-target critical paths that cause congestion of the congested nodes can be determined based on the target connection edges and the congested nodes, and then the average weights of the connection edges of each sub-target critical path are calculated respectively, and the sub-target critical path with the largest average weight is used as the target critical path.

[0036] In one embodiment, step S102 includes: coupling the target model with the graph neural network interpretation algorithm to obtain a coupled model; obtaining an urban road congestion instance graph by predicting the target model in the coupled model; step S103 includes: identifying important subgraphs of the urban road congestion instance graph by the graph neural network interpretation algorithm in the coupled model to obtain a target subgraph.

[0037] Coupling the target model with the graph neural network interpretation algorithm means combining the two so that they can work together to solve a problem.

[0038] In one embodiment, step S101 includes: obtaining node identification, node connection information, node traffic parameter information and node traffic congestion status of urban road network nodes; and constructing a target model based on the node identification, node connection information, node traffic parameter information and node traffic congestion status.

[0039] In this embodiment, the node traffic parameter information may include the average speed of traffic flow, the average flow rate of traffic flow, the average road occupancy rate of traffic flow, etc. The node traffic congestion state may be information indicating the node congestion situation, for example, it may be a traffic congestion level. The node traffic congestion state may be determined based on the node traffic parameter information.

[0040] In one embodiment, the step of obtaining the node traffic congestion status may specifically include: obtaining a mapping relationship between traffic parameter information and the traffic congestion status; and determining the node traffic congestion status according to the node traffic parameter information and the mapping relationship.

[0041] In this embodiment, the node traffic congestion state corresponding to the node traffic parameter information may be determined according to the mapping relationship.

[0042] In one embodiment, the target model is trained in the following manner: constructing an adjacency matrix of nodes according to the node identifiers and the node connection information A { w ij}, where w ij It is expressed as follows: ; The target model is used to make predictions based on the adjacency matrix and the node traffic parameter information; wherein the prediction process of the target model is expressed by the following formula: ,in, Represents all nodes respectively t- n , t-n+1 , t The characteristic vector of the node traffic parameter information detected at all times, A represents the adjacency matrix, represents the parameters of the target model, represents the prediction process, Represents all nodes t +1 Predicted node traffic congestion status at time; According to the preset loss function of the target model, the predicted node traffic congestion status and the node traffic congestion status, the parameters of the target model are adjusted until the parameters meet the preset requirements.

[0043] In one embodiment, the target model is a three-layer network model, wherein the first and second layers are graph attention networks in a graph neural network, and the third layer is a fully connected linear output layer; the activation function of the graph attention network is Mish(), and the loss function of the target model is multi-classification cross entropy CrossEntropyLoss().

[0044] Reference Figure 2 , showing a flow chart of another embodiment of the critical path identification method provided by the present invention.

[0045] ① Obtain the urban road network node topology information.

[0046] Node topology information includes: node identification and node connection information. Node connection information refers to the connection relationship between different nodes in the network, that is, whether there is a connection edge between nodes. In specific practice, for example, the node identification and node connection information of 228 nodes in a city road network can be obtained.

[0047] ② Obtain traffic information of urban road network nodes.

[0048] The node traffic information includes: node traffic parameter information and node traffic congestion status. The node traffic congestion status can be determined based on the node traffic parameter information.

[0049] Continuing with the above example, the node traffic parameter information may be the average speed of vehicles at the node. The average speed of vehicles detected by sensors at the above 228 nodes at fixed intervals of five minutes may be obtained, and the collection time is from May 1, 2012 to June 30, 2012. Then, based on the average speed of vehicles at the node, the traffic congestion state of the node is converted. The conversion may be based on the congestion quantification standard issued by the state, as shown in Table 1 below: Table 1, Congestion Quantification Standard Table

[0050] ③Construct the urban road network node adjacency matrix.

[0051] Constructing the urban road network node adjacency matrix based on the urban road network node topology information A { w ij}.

[0052] Continuing the above example, we can get a 228 The adjacency matrix with 228 rows and columns is simplified as follows: .

[0053] ④Construct an urban road congestion fitting model based on GNNs.

[0054] First, we build a three-layer initial network model, where the first and second layers are the Graph Attention Networks (GAT) in the Graph Neural Networks (GNNs), and the third layer is a fully connected linear output layer. The specific structure of the initial network model is as follows: Figure 3 shown.

[0055] Then, the activation function of the GAT layer is defined as the Mish function, and the loss function of the initial network model is defined as the multi-classification cross entropy loss function CrossEntropyLoss().

[0056] After that, the node traffic parameter information, node traffic congestion status and adjacency matrix are input into the initial network model. The initial network model predicts the traffic congestion status of the next time step with the average speed of 12 time steps, and adjusts and trains the initial network model according to the loss function of the initial network model, the predicted node traffic congestion status and the actual node traffic congestion status until the parameters of the initial network model are optimal, thus obtaining the final target model. The fitting accuracy of the target model is 92%, which can effectively fit the congestion instance.

[0057] ⑤Couple the GNNExplainer algorithm with the target model.

[0058] The explainer coupling explanation model can be constructed through the explainer organization module of Python. The model to be explained in the coupling model is the target model, and the explanation algorithm is the GNNExplainer algorithm.

[0059] ⑥Identify important subgraphs through coupling models.

[0060] The urban road congestion instance graph is obtained by predicting the target model in the coupling model. The important subgraphs of the urban road congestion instance graph are identified by the GNNExplainer algorithm to obtain the target subgraph.

[0061] The GNNExplainer algorithm can compare the importance of different subgraphs in the congestion instance to the model fitting to find the most important subgraph, that is, the target subgraph. The importance is quantified by the mutual information MI:

[0062] in, Y is the prediction result of the target model, that is, , Gsis the subgraph constructed by the GNNExplainer algorithm, Xs is the feature vector on the subgraph node, H(Y) is the exact probability of the congestion fitting model.

[0063] Reference Figure 4 , showing a schematic diagram of a target subgraph provided by the present invention. Taking congested node 2 as an example, the target subgraph that has the greatest impact on the congestion of node 2 identified by the GNNExplainer algorithm is as follows Figure 4 As shown in the figure, when the target subgraph is identified by the GNNExplainer algorithm, the weights of the connecting edges between the nodes of the target subgraph can be obtained. The more important the connecting edge is, the closer the weight is to 1, and vice versa.

[0064] ⑦ Determine the critical path where congestion occurs.

[0065] Continue with Figure 4 As shown in the example, the weight threshold is first preset to 0.6, then Figure 4 The target connection edges greater than the preset weight threshold include: the connection edge from node 15 to node 4, the connection edge from node 4 to node 2, the connection edge from node 4 to node 12, and the connection edge from node 12 to node 2.

[0066] Then, according to the target connection edge and the congested node 2, the sub-target critical path that causes the congestion of the congested node 2 is determined, and the sub-target critical path includes: node 15 to node 4 to node 2, and node 15 to node 4 to node 12 to node 2.

[0067] Finally, the average weight of the connecting edges in each sub-target critical path is calculated. The average weight of the connecting edges from node 15 to node 4 to node 2 is: (0.77+0.83) / 2=0.8; the average weight of the connecting edges from node 15 to node 4 to node 12 to node 2 is: (0.77+0.65+0.67) / 3=0.7. Therefore, it can be determined that node 15 to node 4 to node 2 is the most important target critical path that causes congestion at congested node 2. Traffic managers should focus on this path when preventing or alleviating traffic congestion at node 2.

[0068] The present invention provides a method for identifying critical paths caused by urban road congestion. Based on a graph neural network model with high fitting accuracy, the method combines the GNNExplainer algorithm to identify the critical paths caused by congestion and provides a quantitative basis. It provides quantitative analysis and decision support for traffic managers, effectively helps to alleviate traffic congestion, improve travel efficiency, reduce resource waste and environmental pollution, and thus significantly improve the quality of life of urban residents and the sustainable development of cities.

[0069] Reference Figure 5 , showing a schematic diagram of the structure of an embodiment of a device for identifying a critical path of urban road congestion provided by the present invention, the device 200 comprises: Model and model interpretation algorithm acquisition module 201, used to acquire a target model and a graph neural network interpretation algorithm; the target model is a city road congestion fitting model built based on a graph neural network; A congestion instance prediction module 202, used for obtaining a city road congestion instance map through prediction of the target model; The important subgraph identification module 203 is used to identify important subgraphs of the urban road congestion example graph by using the graph neural network interpretation algorithm to obtain a target subgraph; the target subgraph includes nodes, connecting edges between nodes, and weights of connecting edges; The congestion critical path determination module 204 is used to determine the congestion critical path in the urban road congestion example graph according to the weights of the connecting edges in the target subgraph.

[0070] It should be noted that the implementation principles or implementation processes of the above modules can refer to the above-mentioned embodiment of building facade structure extraction, and will not be described one by one here.

[0071] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0072] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.

Claims

1. A method for identifying critical paths of urban road congestion, characterized in that: include: Obtain the target model and graph neural network interpretation algorithm; The target model is an urban road congestion fitting model built based on a graph neural network; Obtaining an example map of urban road congestion through prediction of the target model; Using the graph neural network interpretation algorithm, important subgraphs are identified on the urban road congestion example graph to obtain a target subgraph; the target subgraph includes nodes, connecting edges between nodes, and weights of connecting edges; According to the weights of the connecting edges in the target subgraph, a congestion critical path in the urban road congestion example graph is determined.

2. The urban road congestion critical path identification method according to claim 1 is characterized in that: The graph neural network interpretation algorithm is the GNNExplainer algorithm.

3. The method for identifying critical paths of urban road congestion according to claim 1, characterized in that: The target subgraph includes congested nodes; and determining the congested critical path in the urban road congestion example graph according to the weights of the connecting edges in the target subgraph includes: Taking the connection edge in the target subgraph whose weight is greater than a preset weight threshold as the target connection edge; A target critical path causing congestion of the congested node is determined according to the target connection edge and the congested node.

4. The method for identifying critical paths of urban road congestion according to claim 3, characterized in that: The determining, according to the target connection edge and the congested node, a target critical path causing congestion of the congested node includes: Determine at least one sub-target critical path that causes congestion of the congested node according to the target connection edge and the congested node; Determine the average weight of the connecting edges in each of the sub-goal critical paths; The sub-target critical path with the largest average weight is used as the target critical path.

5. The method for identifying critical paths of urban road congestion according to claim 1, characterized in that: The example map of urban road congestion obtained by predicting the target model includes: Coupling the target model with the graph neural network interpretation algorithm to obtain a coupled model; Obtaining an example diagram of urban road congestion through prediction of the target model in the coupling model; The important subgraphs of the urban road congestion example graph are identified by the graph neural network interpretation algorithm to obtain the target subgraph, including: The graph neural network interpretation algorithm in the coupling model is used to identify important subgraphs of the urban road congestion example graph to obtain a target subgraph.

6. The urban road congestion critical path identification method according to claim 1 is characterized in that: The obtaining of the target model comprises: Obtain node identification, node connection information, node traffic parameter information and node traffic congestion status of urban road network nodes; A target model is constructed according to the node identification, node connection information, node traffic parameter information and node traffic congestion status.

7. The method for identifying key paths of urban road congestion according to claim 6, characterized in that: The obtaining of the node traffic congestion status includes: Obtaining the mapping relationship between traffic parameter information and traffic congestion status; The node traffic congestion state is determined according to the node traffic parameter information and the mapping relationship.

8. The method for identifying critical paths of urban road congestion according to claim 6, characterized in that: The target model is trained as follows: Construct a node adjacency matrix based on the node identifier and the node connection information A { w ij }, where w ij It is expressed as follows: ； The target model is used to make predictions based on the adjacency matrix and the node traffic parameter information; wherein the prediction process of the target model is expressed by the following formula: ,in, Represents all nodes respectively tn , tn +1 , t The characteristic vector of the node traffic parameter information detected at all times, A represents the adjacency matrix, represents the parameters of the target model, represents the prediction process, Represents all nodes t +1 Predicted node traffic congestion status at time; According to the preset loss function of the target model, the predicted node traffic congestion status and the node traffic congestion status, the parameters of the target model are adjusted until the parameters meet the preset requirements.

9. The method for identifying critical paths of urban road congestion according to claim 8, characterized in that: The target model is a three-layer network model, wherein the first and second layers are graph attention networks in the graph neural network, and the third layer is a fully connected linear output layer; the activation function of the graph attention network is the Mish function, and the loss function of the target model is a multi-classification cross entropy loss function.

10. A device for identifying critical paths of urban road congestion, characterized in that: include: Model and model interpretation algorithm acquisition module, used to obtain the target model and graph neural network interpretation algorithm; The target model is an urban road congestion fitting model built based on a graph neural network; A congestion instance prediction module, used to predict and obtain a city road congestion instance map through the target model; An important subgraph identification module is used to identify important subgraphs of the urban road congestion example graph through the graph neural network interpretation algorithm to obtain a target subgraph; the target subgraph includes nodes, connecting edges between nodes, and weights of connecting edges; The congestion critical path determination module is used to determine the congestion critical path in the urban road congestion example graph according to the weights of the connecting edges in the target subgraph.

Images