Urban road network important sub-region identification method and system based on improved WVoteRank algorithm

Abstract

The invention relates to an urban road network important sub-region identification method and system based on an improved WVoteRank algorithm. The identification method comprises the following steps: dividing an urban road network into a plurality of nodes by using a macroscopic fundamental diagram, and calculating an initial voting score and voting ability of each node; calculating voting scores of all nodes, and taking the node with the highest voting score as a key node; setting the voting capability of the key node as 0, and inhibiting the voting capabilities of a first-order neighbor node and a second-order neighbor node of the key node; and iteratively calculating voting scores of nodes except the key nodes until the number of the key nodes reaches a predetermined value, determining the sub-regions corresponding to the key nodes as important traffic control regions, and optimizing traffic flow distribution by adjusting the boundary signal lamp timing of the important traffic control regions. And cooperative regulation and control of regional traffic congestion are realized. The urban road network important sub-region recognition method based on the improved WVoteRank algorithm is suitable for key node recognition in a traffic network, and important sub-regions with control potential in the traffic network are recognized through the improved algorithm.

Description

Technical Field

[0001] The present invention relates to the technical field of urban traffic network control, and in particular to a method and system for identifying important sub-regions of an urban road network based on an improved WVoteRank algorithm. Background Art

[0002] When traffic congestion occurs, the uneven distribution of congestion can cause the Macroscopic Fundamental Diagram (MFD) curve to exhibit high dispersion, leading to inaccurate traffic state estimates. Therefore, before implementing traffic signal control on large-scale urban road networks, it is an effective strategy to divide the complex traffic network into several homogeneous sub-regions. Subsequently, controlling these sub-regions can achieve better control results.

[0003] The divided sub-areas become the focus of traffic control. In theory, it is feasible to implement signal control for each sub-area independently. However, as the number of sub-areas increases, the complexity of control calculations will increase exponentially. Summary of the Invention

[0004] To address some or all of the problems in the prior art, the present invention provides a method for identifying important sub-regions of an urban road network based on an improved WVoteRank algorithm. The method comprises the following steps:

[0005] Use the macro basic graph to divide the urban road network into multiple nodes and calculate the initial voting score and voting capacity of each node;

[0006] Calculate the voting scores of all nodes and select the node with the highest voting score as the key node;

[0007] Setting the voting power of the key node to 0, suppressing the voting power of the first-order neighbor nodes and the second-order neighbor nodes of the key node; and

[0008] The voting scores of nodes other than the key nodes are iteratively calculated until the number of the key nodes reaches a predetermined value, and the sub-areas corresponding to the key nodes are determined as important traffic control areas. The traffic flow distribution is optimized by adjusting the boundary signal light timing of the important traffic control area to achieve coordinated regulation of regional traffic congestion.

[0009] Furthermore, the method for identifying important sub-regions of an urban road network based on the improved WVoteRank algorithm further includes:

[0010] Calculate the clustering coefficient and centrality index of each node to obtain the evaluation results of each node.

[0011] Furthermore, the calculation of each node's initial voting score and voting power includes:

[0012] Node v's initial voting score S v0 for,

[0013]

[0014] Among them, D max D v The maximum value, D v It is expressed by the following formula:

[0015]

[0016] Among them, R v is the set of road segments in the sub-area corresponding to node v, L r is the length of road section r, A v is the area of the sub-region corresponding to node v;

[0017] Node v's voting capacity Va v for,

[0018]

[0019] Among them, k v is the degree of node v, k max is the maximum degree of all nodes, S v0 is the initial voting score of node v.

[0020] Further,

[0021] The voting score obtained by node v is,

[0022]

[0023] Among them, node i represents the neighbor of node v, w vi is the edge weight between node v and node i, |Γ v | is the number of neighbors of node v, S v0 is the initial voting score of node v, Va i is the voting ability of node i;

[0024] Among them, w vi It is expressed by the following formula:

[0025]

[0026] Among them, E vi is the number of road sections between two sub-areas, E max For E vi The maximum value.

[0027] Furthermore, the voting capacity of the first-order neighbor nodes and the second-order neighbor nodes of the key node is suppressed as follows:

[0028]

[0029] Among them, λ is the suppression factor, λ∈[0,1].

[0030] Furthermore, the clustering coefficient of node v is,

[0031]

[0032] Where E(v) is the number of edges between the neighbors of node v, and k(v) is the degree of node v;

[0033] The centrality indicators include degree centrality, closeness centrality and betweenness centrality;

[0034] The degree centrality D(v) of node v is,

[0035]

[0036] Where k(v) is the degree of node v and n is the total number of nodes;

[0037] The closeness centrality of node v is,

[0038]

[0039] Where d(u,v) represents the shortest path distance from node v to node u, and n is the total number of nodes;

[0040] The betweenness centrality of node v is,

[0041]

[0042] Among them, σ st represents the total number of shortest paths from node s to node t, σ st (v) represents the total number of shortest paths from s to t that pass through node v.

[0043] The present invention also provides a system for the method for identifying important sub-areas of urban road networks based on the improved WVoteRank algorithm, the system comprising the following modules:

[0044] The initialization module is configured to use the macro basic graph to divide the urban road network into multiple nodes and calculate the initial voting score and voting capacity of each node;

[0045] The key node selection module is configured to calculate the voting scores of all nodes and select the node with the highest voting score as the key node;

[0046] a voting suppression module configured to set the voting capability of the key node to 0, thereby suppressing the voting capabilities of the first-order neighbor nodes and the second-order neighbor nodes of the key node; and

[0047] The important traffic control area determination module is configured to iteratively calculate the voting scores of nodes other than the key nodes until the number of the key nodes reaches a predetermined value, and determine the sub-area corresponding to the key node as the important traffic control area. By adjusting the boundary signal light timing of the important traffic control area, the traffic flow distribution is optimized to achieve coordinated regulation of regional traffic congestion.

[0048] The present invention also provides a computer system, comprising:

[0049] a processor configured to execute machine-readable instructions;

[0050] A graphics card with an artificial intelligence chip, configured to train the method for identifying important sub-areas of urban road networks based on the improved WVoteRank algorithm; and

[0051] The memory is configured to store machine-readable instructions, which, when executed by the processor and / or graphics card, perform the steps of the method for identifying important sub-areas of urban road networks based on the improved WVoteRank algorithm.

[0052] The present invention also provides a computer-readable storage medium having machine-readable instructions stored thereon. When the machine-readable instructions are executed by a processor, the steps of the method for identifying important sub-areas of an urban road network based on the improved WVoteRank algorithm are performed.

[0053] The technical solution provided by the present invention has the following advantages:

[0054] 1. The method for identifying important sub-areas in urban road networks based on the improved WVoteRank algorithm proposed in this paper optimizes the WVoteRank algorithm and the VoteRank++ algorithm to make them suitable for identifying key nodes in transportation networks. The improved algorithm identifies important sub-areas in transportation networks with control potential.

[0055] 2. The method for identifying important sub-areas of urban road networks based on the improved WVoteRank algorithm proposed in this invention can select the number of key nodes according to their capabilities and accurately invest limited resources in the blocks with the best benefits and greatest impact.

[0056] 3. The method for identifying important sub-regions in urban road networks based on the improved WVoteRank algorithm proposed in the present invention can also introduce traffic information design to identify important sub-regions in dynamic road networks, and on this basis, it can also control the sub-regions in the graph. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] To further illustrate the above and other advantages and features of various embodiments of the present invention, a more detailed description of various embodiments of the present invention will be presented with reference to the accompanying drawings. It will be understood that these drawings depict only typical embodiments of the present invention and are not to be considered as limiting the scope thereof. In the drawings, for clarity, identical or corresponding components will be represented by the same or similar reference numerals.

[0058] Figure 1 A schematic diagram illustrating a flow chart of a method for identifying important sub-regions of an urban road network based on an improved WVoteRank algorithm according to an embodiment of the present invention is shown;

[0059] Figure 2 A schematic diagram illustrating a framework of a method for identifying important sub-regions of an urban road network based on an improved WVoteRank algorithm according to an embodiment of the present invention is shown;

[0060] Figure 3 A schematic diagram of a road network at a certain location in Shenzhen is shown;

[0061] Figure 4 Shows a schematic diagram of the Shenzhen road network divided into 14 sub-areas;

[0062] Figure 5 Shows an abstract network diagram of Shenzhen's road network;

[0063] Figure 6 shows a schematic diagram of key nodes in Shenzhen's road network; and

[0064] Figure 7 A schematic diagram of a system for identifying important sub-regions of an urban road network based on an improved WVoteRank algorithm according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0065] In the following description, the present invention is described with reference to various embodiments. However, those skilled in the art will recognize that the embodiments may be implemented without one or more of the specific details or with other alternative and / or additional methods or components. In other cases, well-known structures or operations are not shown or described in detail to avoid obscuring the inventive aspects of the present invention. Similarly, specific numbers and configurations are set forth for illustrative purposes in order to provide a comprehensive understanding of the embodiments of the present invention. However, the present invention is not limited to these specific details.

[0066] In this specification, reference to "one embodiment" or "the embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. The appearances of the phrase "in one embodiment" in various places in this specification are not necessarily all referring to the same embodiment.

[0067] It should be noted that the embodiments of the present invention describe the method steps in a specific order, but this is only for the purpose of illustrating the specific embodiment and does not limit the order of the steps. On the contrary, in different embodiments of the present invention, the order of the steps can be adjusted according to actual needs.

[0068] In the present invention, each module of the system according to the present invention can be implemented using software, hardware, firmware or a combination thereof. When the module is implemented using software, the function of the module can be implemented by a computer program flow, for example, the module can be implemented by a code segment (such as a code segment in a language such as C, C++) stored in a storage device (such as a hard disk, memory, etc.), wherein when the code segment is executed by a processor, the corresponding function of the module can be implemented. When the module is implemented using hardware, the function of the module can be implemented by setting a corresponding hardware structure, for example, by hardware programming a programmable device such as a field programmable gate array (FPGA) to implement the function of the module, or by designing an application-specific integrated circuit (ASIC) including electronic devices such as a plurality of transistors, resistors and capacitors to implement the function of the module. When the module is implemented using firmware, the function of the module can be written into a read-only memory such as an EPROM or EEPROM of the device in the form of program code, and when the program code is executed by the processor, the corresponding function of the module can be implemented. In addition, certain functions of the module may need to be implemented by separate hardware or through collaboration with the hardware, for example, the detection function is implemented by corresponding sensors (such as proximity sensors, accelerometers, gyroscopes, etc.), the signal transmission function is implemented by corresponding communication devices (such as Bluetooth devices, infrared communication devices, baseband communication devices, Wi-Fi communication devices, etc.), the output function is implemented by corresponding output devices (such as displays, speakers, etc.), and so on.

[0069] In order to solve the problem that the complexity of control calculation will increase exponentially with the increase in the number of sub-areas, the present invention introduces the containment control theory in complex network theory. The theory proposes to achieve effective management of the entire network by selectively controlling a part of key nodes. This strategy aims to alleviate traffic congestion in the entire road network by controlling key sub-areas.

[0070] This paper uses an improved WVoteRank algorithm, combined with the inherent characteristics of the traffic network and the characteristics of the road segments connecting different subregions, to identify key control nodes in the traffic network. This improvement takes into account the characteristics of the subregional road network and the characteristics of the road segments connecting different subregions, resulting in a method suitable for identifying key control nodes in the traffic network. Simulation experiments based on a real traffic network identified a group of highly important subregions, providing a solid foundation for subsequent traffic signal control.

[0071] The method for identifying important sub-regions of urban road networks proposed in this paper is an improved WVoteRank method, which refers to the traffic network to identify influential nodes in the weighted network. This method is an extension of the WVoteRank method and the VoteRank++ method. v Set to (1, 0), S v is the voting score that node v gets from its neighbor nodes, while the VoteRank++ method sets node v to an expression related to degree, which is the most direct network metric. In an undirected graph, the degree k of node i is i represents the number of edges directly connected to node i. In a directed network, this is divided into indegree and outdegree. Indegree is the number of edges pointing from other nodes to node i, while outdegree is the number of edges starting from node i and pointing to other nodes. However, the initial voting score for each sub-area in a transportation network should be different, which may be related to the number and density of intersections and road sections within them. Therefore, the present invention forms an improved method based on this.

[0072] The present invention provides a method for identifying important sub-areas of an urban road network, so as to solve the problem of traffic flow congestion caused by traffic sub-area planning and the like. Figure 1 A flow chart of a method for identifying important sub-areas in an urban road network based on an improved WVoteRank algorithm according to an embodiment of the present invention is shown. Figure 2 The following is a schematic diagram showing a framework of a method for identifying important sub-areas of urban road networks based on an improved WVoteRank algorithm according to an embodiment of the present invention. Figure 1 and Figure 2 , the method for identifying important sub-regions of urban road networks based on the improved WVoteRank algorithm proposed by the present invention is described. In one embodiment of the present invention, the method for identifying important sub-regions of urban road networks based on the improved WVoteRank algorithm can be executed by a computer. Figure 1 As shown in FIG, the method for identifying important sub-areas of urban road networks based on the improved WVoteRank algorithm includes the following steps:

[0073] First, the urban road network is divided into multiple nodes using a macro basic graph, and the initial voting score and voting ability of each node are calculated.

[0074] Figure 3 Figure 1 shows a schematic diagram of the road network in Shenzhen. Figure 3 The road network shown in FIG is taken as an example to illustrate the identification method of the present invention. Figure 3 The urban road network shown in Figure 1 is divided into 14 sub-areas, namely nodes, such as Figure 4As shown in the figure, the urban road network is divided into 14 sub-areas based on MFD, and each sub-area has a good MFD curve. Based on this research, a traffic network simulation is performed, and the traffic network in the figure is abstracted as G(V, E, W). G represents the graph, V represents the point, E represents the edge, and W represents the weight between nodes.

[0075] Number each sub-area, and one node corresponds to one sub-area. In order to obtain the initial conditions, the traffic sub-area is modularized. Figure 4 Transformed into Figure 5 The abstract network shown. Each sub-region of the road network is abstracted as a set of points. The values between points are edge weights. The edge weights between nodes are considered to be related to the number of road sections between the two sub-regions. vi is the edge weight between node v and node i, w vi It is expressed by the following formula:

[0076]

[0077] Among them, E vi is the number of road sections between two sub-areas, E max For E vi The maximum value.

[0078] The state of each node is represented by the tuple (S v ,Va v ) is related, where S v is the voting score that node v gets from its neighbor nodes, Va v represents the voting power of node v to its neighbor nodes. However, given the traffic road network, the importance of a sub-region is not only related to the voting power of its neighbors, but also to its own structure. It should not be just the weighted sum of the voting power of its neighbors.

[0079] Define the initial voting score S of node v v0 for,

[0080]

[0081] Among them, D max D v The maximum value, D v It is expressed by the following formula:

[0082]

[0083] Among them, R v is the set of road segments in the sub-area corresponding to node v, L r is the length of road section r, A v is the area of the subregion corresponding to node v.

[0084] The VoteRank algorithm does not distinguish between differences in node voting power. Each sub-region in the traffic network has different locations, different internal road structures, different impacts on adjacent sub-regions, and different voting power. Therefore, assuming that voting power is related to importance, the voting power of node v is defined as Va in the implementation process. v for,

[0085]

[0086] Among them, k v is the degree of node v, k max is the maximum degree of all nodes, S v0 is the initial voting score of node v.

[0087] The voting score of each node is calculated by the above formula. Table 1 lists the initial voting score S of each node in Shenzhen road network. v0 ,Take node 2 as an example, the area of the irregular sub-region is calculated directly from the digital map by GIS software. ,The total road length L2 of sub-region 2 is 26.35km, the total road length L3 of sub-region 3 is 26.21km, the area A2 of sub-region 2 is 3.21 hectares, and the area A3 of sub-region 3 is 3.12 hectares. ,D2 is 8.21, and D3 is 8.40, where D3 is D max ,pass Calculated to be 0.98.

[0088] Table 1 Initial voting scores of each node in Shenzhen road network

[0089]

[0090]

[0091] Next, the voting scores of all nodes are calculated, and the node with the highest voting score is selected as the key node.

[0092] Node v's initial voting score S v0 Combined with the WVoteRank voting phase, the voting score obtained by each node v is equal to the product of the sum of its neighbors’ voting power and the initial voting score.

[0093] The calculation formula for the voting score obtained by node v is:

[0094]

[0095] Among them, node i represents the neighbor of node v, w vi is the edge weight between node v and node i, |Γ v | is the number of neighbors of node v, S v0is the initial voting score of node v, Va i is the voting ability of node i.

[0096] Among them, wv i It is expressed by the following formula:

[0097]

[0098] Among them, E vi is the number of road sections between two sub-areas, E max For E vi The maximum value.

[0099] As can be seen from the formula, the voting score of node v depends on four factors: the number of nodes v's neighbors, the node's initial score, the voting power of each neighbor i, and the edge weight between nodes v and i. The voting scores of all nodes are calculated, and the node with the highest voting score is selected as the key node.

[0100] Next, the voting capability of the key node is set to 0, and the voting capabilities of the first-order neighbor nodes and the second-order neighbor nodes of the key node are suppressed.

[0101] The key node no longer participates in voting, and its voting power is set to 0. To ensure a relatively even distribution of key nodes across the network, the voting power of the key node's neighbors is suppressed. In subsequent iterations, the voting power of the selected node's neighbors is suppressed. First-order neighbors are subject to more restrictions than second-order neighbors to prevent excessive node aggregation. The closer to the selected node, the stronger the suppression.

[0102] The calculation formula for suppressing the voting power of the first-order neighbor nodes and the second-order neighbor nodes of the key node is:

[0103]

[0104] Where λ is a suppression factor, λ∈[0,1]. When a node is selected as a key node, the voting power of its neighboring second-order nodes is reduced. This reduction in voting power ensures that after a node is selected, the probability of its lower-order neighbors being selected in the next voting round is reduced. This protects key nodes in different locations, reduces the possibility of selected nodes clustering, and enhances the controllability of the entire network.

[0105] Finally, the voting scores of nodes other than the key nodes are iteratively calculated until the number of key nodes reaches a predetermined value. The sub-area corresponding to the key node is determined as an important traffic control area. By adjusting the timing of the boundary traffic lights in the important traffic control area, the traffic flow distribution is optimized to achieve coordinated regulation of regional traffic congestion.

[0106] like Figure 2 As shown, node voting scores are iteratively calculated until the number of selected key nodes reaches a predetermined value, l. In this experiment, l is chosen to be 5, meaning that five key nodes are selected. In a new iteration, as the voting power of some nodes decreases, the node voting scores need to be updated to select new nodes. This update can be performed only on nodes adjacent to the suppressed or selected node, while the voting scores of other nodes remain unchanged. This helps reduce the cost of calculating the voting scores of all nodes.

[0107] A set of sorted nodes, node numbers and voting scores are obtained as shown in Table 2. The selected nodes, i.e. key nodes, are marked in the figure. Figure 6 The schematic diagram of key nodes in Shenzhen's road network is shown. The sub-areas corresponding to the key nodes are identified as important traffic control areas. By adjusting the timing of the boundary lights in the important traffic control areas, the traffic flow distribution is optimized to achieve coordinated control of regional traffic congestion.

[0108] Table 2 Score ranking of key nodes in Shenzhen road network

[0109] Importance Ranking Node number Node score 1 1 1.26 2 12 0.67 3 8 0.57 4 13 0.48 5 9 0.29

[0110] In one embodiment of the present invention, the method for identifying important subregions in an urban road network based on the improved WVoteRank algorithm further includes calculating the clustering coefficient and centrality index of each node to obtain an evaluation result for each node. The node simulation results for Shenzhen City are analyzed at a macro level, and important parameters of some nodes in graph theory are calculated.

[0111] The clustering coefficient is used to measure the degree of connection between the neighbors of a node and is defined as the ratio of the actual number of edges of a node to the possible number of edges. The clustering coefficient of node v is,

[0112]

[0113] Where E(v) is the number of edges between node v's neighbors, and k(v) is the degree of node v, that is, the number of edges connected to it. If C(v) = 1, the node's neighbors are completely connected to each other, forming a complete graph. If C(v) = 0, there is no connection between the node's neighbors.

[0114] The centrality indicators include degree centrality, closeness centrality and betweenness centrality.

[0115] Degree centrality refers to the degree of a node, that is, the number of edges connected to the node, which is used to evaluate the direct influence of the node. The degree centrality D(v) of node v is,

[0116]

[0117] Where k(v) is the degree of node v and n is the total number of nodes. The higher the degree centrality, the more connections a node has and the greater its influence in the network.

[0118] Closeness centrality measures the inverse of the sum of the distances between a node and all other nodes in the network, reflecting the "closeness" of the node to other nodes. The closeness centrality of node v is,

[0119]

[0120] Where d(u,v) represents the shortest path distance from node v to node u, and n is the total number of nodes. Nodes with high proximity centrality have a shorter average distance to other nodes in the network, allowing information to propagate more quickly through them.

[0121] Betweenness centrality reflects the importance of a node in the shortest path between other nodes. It measures the intermediary role of a node in the information transmission process. The betweenness centrality of node v is,

[0122]

[0123] Among them, σ st represents the total number of shortest paths from node s to node t, σ st (v) represents the total number of shortest paths from s to t that pass through node v. Nodes with higher betweenness centrality are on the shortest paths between more nodes and have the effect of "controlling" the flow of information in the network.

[0124] After analyzing the actual traffic network and node evaluation metrics, subregions 1 and 13 were found to have the highest degree centrality, indicating that these two subregions are adjacent to multiple other subregions, allowing them to effectively influence more adjacent subregions. These two subregions also have high proximity centrality, meaning they can more quickly access all nodes in the network, resulting in a more significant influence on other nodes. Furthermore, due to the higher road network density of subregion 1, its initial voting score is also high, indicating its reasonable placement in the importance ranking. Subregion 12 connects four subregions and has a relatively dense internal road network. Subregions 8 and 9 all have high clustering coefficients, degree centrality, and proximity centrality, as well as good betweenness centrality. They maintain a certain distance from the selected subregions and are adjacent to other uncontrolled subregions, which helps avoid node concentration and enhances the control effect on the entire subregion. The parameters in Table 3 confirm the accuracy of the central node selection results in Table 2. Overall, the selected subregions have high degree centrality, ensuring a broad range of influence.

[0125] Table 3 Evaluation results of node indicators in Shenzhen

[0126]

[0127]

[0128] The method for identifying important sub-areas in urban road networks based on the improved WVoteRank algorithm proposed in the present invention optimizes the WVoteRank algorithm and the VoteRank++ algorithm to make them suitable for identifying key nodes in traffic networks. The improved algorithm can identify important sub-areas with control potential in the traffic network; the number of key nodes can be selected according to their capabilities, and limited resources can be accurately invested in blocks with the best benefits and the greatest impact; traffic information design can also be introduced to identify important sub-areas in dynamic road networks, and on this basis, the sub-areas in the graph can be controlled.

[0129] In one embodiment of the present invention, the present invention also provides a system for identifying important sub-regions of an urban road network based on an improved WVoteRank algorithm. Figure 7 FIG1 shows a schematic diagram of an important sub-area identification system for an urban road network based on an improved WVoteRank algorithm according to an embodiment of the present invention. Figure 7 As shown, the system includes the following modules:

[0130] The initialization module is configured to use the macro basic graph to divide the urban road network into multiple nodes and calculate the initial voting score and voting capacity of each node;

[0131] The key node selection module is configured to calculate the voting scores of all nodes and select the node with the highest voting score as the key node;

[0132] a voting suppression module configured to set the voting capability of the key node to 0, thereby suppressing the voting capabilities of the first-order neighbor nodes and the second-order neighbor nodes of the key node; and

[0133] The important traffic control area determination module is configured to iteratively calculate the voting scores of nodes other than the key nodes until the number of the key nodes reaches a predetermined value, and determine the sub-area corresponding to the key node as the important traffic control area. By adjusting the boundary signal light timing of the important traffic control area, the traffic flow distribution is optimized to achieve coordinated regulation of regional traffic congestion.

[0134] In one embodiment of the present invention, a computer system is provided, comprising a processor, a graphics card having an artificial intelligence chip, and a memory, wherein the memory is configured to store machine-readable instructions, the graphics card is configured to train the method for identifying important sub-regions of an urban road network based on the improved WVoteRank algorithm, and the processor is configured to execute the machine-readable instructions. When the processor and / or the graphics card execute the machine-readable instructions, the following processing steps are implemented: using a macro basic graph to divide the urban road network into multiple nodes, calculating the initial voting score and voting power of each node; calculating the voting scores of all nodes, and determining the node with the highest voting score as a key node; setting the voting power of the key node to 0, and suppressing the voting power of the first-order and second-order neighbor nodes of the key node; iteratively calculating the voting scores of nodes other than the key node until the number of key nodes reaches a predetermined value, determining the sub-region corresponding to the key node as an important traffic control area, and optimizing traffic flow distribution by adjusting the boundary signal timing of the important traffic control area to achieve coordinated regulation of regional traffic congestion.

[0135] The graphics card can preferably have a GPU computing power higher than 5.0. Since the amount of data required for training is large, providing a graphics card configuration can significantly improve the training speed.

[0136] The memory includes various media that can store machine-readable instructions, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0137] It can be understood that in addition to the memory and processor mentioned above, the above-mentioned computer system also includes other software and hardware components not listed in this specification. The specific components can be determined according to the model of the specific data processing equipment in different application scenarios. This specification will not list them one by one in detail.

[0138] In one embodiment of the present invention, the present invention also provides a computer-readable storage medium having machine-readable instructions stored thereon, which implement the following processing steps when executed by a processor: using a macro basic graph to divide the urban road network into multiple nodes, and calculating the initial voting score and voting capacity of each node; calculating the voting scores of all nodes, and taking the node with the highest voting score as the key node; setting the voting capacity of the key node to 0, and suppressing the voting capacity of the first-order neighbor nodes and second-order neighbor nodes of the key node; iteratively calculating the voting scores of nodes other than the key node until the number of the key nodes reaches a predetermined value, and determining the sub-area corresponding to the key node as an important traffic control area, and optimizing the traffic flow distribution by adjusting the boundary signal light timing of the important traffic control area, thereby realizing coordinated regulation of regional traffic congestion.

[0139] Although various embodiments of the present invention have been described above, it should be understood that they are presented as examples only and not as limitations. It will be apparent to those skilled in the relevant art that various combinations, modifications, and variations may be made thereto without departing from the spirit and scope of the present invention. Therefore, the breadth and scope of the present invention disclosed herein should not be limited by the exemplary embodiments disclosed above, but should be defined based on the technical solutions of the present invention and their equivalents.

Claims

1. A method for identifying important sub-regions of urban road networks based on an improved WVoteRank algorithm, characterized in that: The steps include: Use the macro basic graph to divide the urban road network into multiple nodes and calculate the initial voting score and voting capacity of each node; Calculate the voting scores of all nodes and select the node with the highest voting score as the key node; Setting the voting power of the key node to 0, and suppressing the voting power of the first-order neighbor nodes and the second-order neighbor nodes of the key node; as well as The voting scores of nodes other than the key nodes are iteratively calculated until the number of the key nodes reaches a predetermined value, and the sub-areas corresponding to the key nodes are determined as important traffic control areas. The traffic flow distribution is optimized by adjusting the boundary signal light timing of the important traffic control area to achieve coordinated regulation of regional traffic congestion.

2. The method for identifying important sub-regions of an urban road network based on the improved WVoteRank algorithm according to claim 1 is characterized in that: Also includes: Calculate the clustering coefficient and centrality index of each node to obtain the evaluation results of each node.

3. The method for identifying important sub-regions of an urban road network based on the improved WVoteRank algorithm according to claim 1, characterized in that: Calculating each node's initial voting score and voting power includes: Node v's initial voting score S v0 for, Among them, D max D v The maximum value, D v It is expressed by the following formula: Among them, R v is the set of road segments in the sub-area corresponding to node v, L r is the length of road section r, A v is the area of the sub-region corresponding to node v; Node v's voting capacity Va v for, Among them, k v is the degree of node v, k max is the maximum degree of all nodes, S v0 is the initial voting score of node v.

4. The method for identifying important sub-regions of an urban road network based on the improved WVoteRank algorithm according to claim 1, characterized in that: The voting score obtained by node v is, Among them, node i represents the neighbor of node v, w vi is the edge weight between node v and node i, |Γ v | is the number of neighbors of node v, S v0 is the initial voting score of node v, Va i is the voting ability of node i; Among them, w vi It is expressed by the following formula: Among them, E vi is the number of road sections between two sub-areas, E max For E vi The maximum value.

5. The method for identifying important sub-regions of an urban road network based on the improved WVoteRank algorithm according to claim 1, characterized in that: The voting power of the first-order neighbor nodes and second-order neighbor nodes that suppress the key node is, Among them, λ is the suppression factor, λ∈[0,1].

6. The method for identifying important sub-regions of an urban road network based on the improved WVoteRank algorithm according to claim 2, characterized in that: The clustering coefficient of node v is, Where E(v) is the number of edges between the neighbors of node v, and k(v) is the degree of node v; The centrality indicators include degree centrality, closeness centrality and betweenness centrality; The degree centrality D(v) of node v is, Where k(v) is the degree of node v and n is the total number of nodes; The closeness centrality of node v is, Where d(u,v) represents the shortest path distance from node v to node u, and n is the total number of nodes; The betweenness centrality of node v is, Among them, σ st represents the total number of shortest paths from node s to node t, σ st (v) represents the total number of shortest paths from s to t that pass through node v.

7. A system for the method for identifying important sub-areas of urban road networks based on the improved WVoteRank algorithm according to any one of claims 1 to 6, characterized in that: Includes the following modules: The initialization module is configured to use the macro basic graph to divide the urban road network into multiple nodes and calculate the initial voting score and voting capacity of each node; The key node selection module is configured to calculate the voting scores of all nodes and select the node with the highest voting score as the key node; a voting suppression module configured to set the voting capability of the key node to 0, thereby suppressing the voting capabilities of the first-order neighbor nodes and the second-order neighbor nodes of the key node; as well as The important traffic control area determination module is configured to iteratively calculate the voting scores of nodes other than the key nodes until the number of the key nodes reaches a predetermined value, and determine the sub-area corresponding to the key node as the important traffic control area. By adjusting the boundary signal light timing of the important traffic control area, the traffic flow distribution is optimized to achieve coordinated regulation of regional traffic congestion.

8. A computer system, characterized in that: include: a processor configured to execute machine-readable instructions; A graphics card with an artificial intelligence chip configured to train a method for identifying important sub-regions of an urban road network based on an improved WVoteRank algorithm; as well as A memory configured to store machine-readable instructions, wherein the machine-readable instructions, when executed by a processor and / or a graphics card, perform the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that Machine-readable instructions are stored thereon, which, when executed by a processor, perform the steps of the method according to any one of claims 1 to 6.

Images