Road network key node identification method and device, equipment and storage medium

Abstract

The invention provides a road network key node identification method and device, equipment and a storage medium, which can be applied to the technical field of regional road network traffic. According to the method, traffic information of a plurality of nodes in a target area is obtained, an initial weight of each node is determined, a traffic network model is constructed, then each node is subjected to scoring processing based on the traffic network model, a comprehensive score of each node is obtained, and thus key nodes in the target area are determined. According to the method, road network key nodes are identified, and optimization of traffic resource configuration and management is facilitated, so that congestion is effectively relieved, the smoothness and safety of traffic are improved, and the operation efficiency and the service level of an urban traffic system are improved.

Description

Technical Field

[0001] The present application relates to the field of regional road network traffic technology, and in particular to a method, device, equipment and storage medium for identifying key nodes in a road network. Background Art

[0002] In recent years, the development of autonomous driving technology has promoted the construction of smart mines and smart ports. At the same time, the high-density logistics road network and high-intensity transportation demand in closed areas have also brought huge challenges to the reliability of the road network.

[0003] Intersection nodes are key components of the road network, but unexpected accidents and other events can easily lead to congestion at these intersections, which in turn may cause large-scale paralysis of the entire regional road network. Therefore, timely identification of key nodes is crucial to solving road network congestion and vehicle control.

[0004] However, most of the existing key node identification methods are based on traditional complex networks and have certain limitations. These methods often only evaluate the importance of nodes from the perspective of the network's topological structure, while ignoring the unique traffic flow characteristics of the road network, which reduces their general applicability to a certain extent. Therefore, a method for identifying key nodes in a closed area road network is needed to timely control vehicles running in the closed area road network according to road conditions. Summary of the invention

[0005] The present application provides a method, device, equipment and storage medium for identifying key nodes in a road network, so as to solve the problems of lack of universality and accuracy in existing methods for identifying key nodes in a road network.

[0006] In a first aspect, the present application provides a method for identifying key nodes in a road network, the method comprising:

[0007] Acquire traffic information of multiple nodes in the target area, and determine an initial weight of each node based on the traffic information;

[0008] Constructing a traffic network model according to the traffic information and initial weights of the plurality of nodes;

[0009] Determining comprehensive scores of multiple nodes based on the transportation network model;

[0010] According to the comprehensive scores of the multiple nodes, key nodes in the target area are determined from the multiple nodes.

[0011] Optionally, the traffic information includes: inflow traffic volume of multiple nodes, and determining the initial weight of each node based on the traffic information includes:

[0012] For any one of the plurality of nodes, determining at least one incoming traffic volume corresponding to the node;

[0013] An initial weight of the node is determined according to the at least one incoming traffic volume.

[0014] Optionally, the traffic information further includes: associations between multiple nodes and outflow traffic volumes of multiple nodes, the associations including: inflow relationships and outflow relationships, and constructing a traffic network model based on the traffic information and initial weights of the multiple nodes includes:

[0015] Determine, according to the association relationship between the multiple nodes, the edge information corresponding to the multiple nodes;

[0016] The traffic network model is constructed based on the edge information, the location of each node, the outflow traffic volume and the initial weight.

[0017] Optionally, determining the comprehensive scores of the multiple nodes based on the traffic network model includes:

[0018] Determining a first authority value and a first center value of each node based on the outflow traffic and the initial weights of the plurality of nodes;

[0019] The first authority value and the first center value are optimized and updated to obtain a comprehensive score of each node.

[0020] Optionally, determining the first authority value and the first center value of each node based on the outflow traffic volume and the initial weights of the multiple nodes includes:

[0021] For any one of the plurality of nodes, determining at least one associated edge corresponding to the node and an outflow traffic volume of each associated edge relative to the node;

[0022] determining a first central value of the node based on the outflow traffic volume of the at least one associated edge relative to the node;

[0023] A first authority value of the node is determined according to the initial weight of the node.

[0024] Optionally, the optimizing and updating the first authority value and the first center value to obtain a comprehensive score of each node includes:

[0025] Normalizing the first authority value and the first center value to obtain a second authority value and a second center value of each node;

[0026] Iteratively updating the second authoritative value and the second central value until the second authoritative value and the second central value converge;

[0027] According to the converged second authority value and the second center value, the comprehensive score of the corresponding node is determined.

[0028] Optionally, determining the key nodes in the target area from the multiple nodes according to the comprehensive scores of the multiple nodes includes:

[0029] Sorting the comprehensive scores of the multiple nodes in descending order;

[0030] The first N nodes after sorting are determined as key nodes in the target area.

[0031] In a second aspect, the present application provides a road network key node identification device, the device comprising:

[0032] An acquisition module, used to acquire traffic information of multiple nodes in a target area;

[0033] A determination module, used to determine the initial weight of each node based on the traffic information;

[0034] A processing module, used for constructing a traffic network model according to the traffic information and initial weights of the plurality of nodes;

[0035] The determination module is further used to determine the comprehensive scores of multiple nodes based on the traffic network model; and determine the key nodes in the target area from the multiple nodes according to the comprehensive scores of the multiple nodes.

[0036] Optionally, the determination module is further used to determine, for any one of the multiple nodes, at least one incoming traffic volume corresponding to the node; and determine an initial weight of the node based on the at least one incoming traffic volume.

[0037] Optionally, the determining module is further configured to determine the edge information corresponding to the multiple nodes according to the association relationship between the multiple nodes;

[0038] The processing module is also used to construct the traffic network model based on the edge information, the location of each node, the outflow traffic volume and the initial weight.

[0039] Optionally, the determination module is further used to determine the first authority value and the first center value of each node based on the outflow traffic volume and the initial weights of the multiple nodes;

[0040] The processing module is further used to optimize and update the first authority value and the first center value to obtain a comprehensive score for each node.

[0041] Optionally, the determination module is further configured to determine, for any one of the multiple nodes, at least one associated edge corresponding to the node and the outflow traffic volume of each associated edge relative to the node; and determine the first center value of the node according to the outflow traffic volume of the at least one associated edge relative to the node;

[0042] The processing module is further used to determine the first authority value of the node according to the initial weight of the node.

[0043] Optionally, the processing module is further used to normalize the first authority value and the first center value to obtain a second authority value and a second center value of each node; and iteratively update the second authority value and the second center value until the second authority value and the second center value converge;

[0044] The determination module is further used to determine the comprehensive score of the corresponding node according to the converged second authority value and the second center value.

[0045] Optionally, the processing module is further used to sort the comprehensive scores of the multiple nodes in descending order;

[0046] The determination module is further configured to determine the first N nodes after sorting as key nodes in the target area.

[0047] In a third aspect, the present application provides a road network key node identification device, including:

[0048] Memory;

[0049] processor;

[0050] Wherein, the memory stores computer-executable instructions;

[0051] The processor executes the computer-executable instructions stored in the memory to implement the road network key node identification method as described in the above-mentioned first aspect and various possible implementation methods of the first aspect.

[0052] In a fourth aspect, the present application provides a computer storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the method for identifying key nodes in a road network as described in the first aspect and various possible implementations of the first aspect.

[0053] This application provides a method for identifying key nodes in a road network. By obtaining traffic information of multiple nodes in a target area, determining the initial weight of each node and building a traffic network model, each node is scored based on the traffic network model to obtain a comprehensive score for each node, thereby determining the key nodes in the target area. This method determines the key nodes based on the comprehensive scoring of the nodes, which can help traffic management departments accurately identify bottlenecks and hubs in the road network. By optimizing the operation and infrastructure of these nodes, traffic congestion can be effectively alleviated and road capacity can be improved, thereby enhancing the efficiency and reliability of the entire transportation system and providing people with a smoother and safer travel environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0055] Figure 1 A road network key node identification method provided in this application Figure 1 ;

[0056] Figure 2 A schematic diagram of a traffic network model for a method for identifying key nodes in a road network provided in this application;

[0057] Figure 3 A road network key node identification method provided in this application Figure 2 ;

[0058] Figure 4 A schematic diagram of the structure of a road network key node identification device provided in this application;

[0059] Figure 5 A schematic diagram of the structure of a road network key node identification device provided for this application.

[0060] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0062] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in sequences other than those illustrated or described herein.

[0063] In the embodiments of the present application, the words "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0064] First, the terms involved in this application are explained:

[0065] Road network: refers to a road system composed of various roads that are interconnected and interwoven into a network within a certain area.

[0066] Hyperlink-Induced Topic Search (HITS) algorithm: is a method for ranking web pages. The algorithm is mainly used to find authoritative pages and central pages in a group of related web pages. Although it was originally designed to solve the problem of organizing and retrieving information on the World Wide Web, its basic principles can also be applied to other types of networks.

[0067] According to the HITS algorithm, after the user enters a keyword, the algorithm calculates two values ​​for the returned matching pages: one is the hub score and the other is the authority score. These two values ​​are interdependent and influence each other. The so-called hub score refers to the sum of the authority scores of all the outbound links on the page. The authority score refers to the sum of the hubs in the page where all the inbound links are located.

[0068] In recent years, the development of autonomous driving technology has promoted the construction of smart mines and smart ports. At the same time, the high-density logistics road network and high-intensity transportation demand in closed areas have also brought huge challenges to the reliability of the road network.

[0069] Intersection nodes are key components of the road network, but unexpected accidents and other events can easily lead to congestion at these intersections, which in turn may cause large-scale paralysis of the entire regional road network. Therefore, timely identification of key nodes is crucial to solving road network congestion and vehicle control.

[0070] However, most of the existing key node identification methods are studied on traditional complex networks and have certain limitations. These methods often only evaluate the importance of nodes from the perspective of the network's topological structure, while ignoring the unique traffic flow characteristics of the road network, which to some extent reduces their universal applicability.

[0071] In response to the above problems, this application proposes a method for identifying key nodes in a road network.

[0072] This method obtains traffic information of multiple nodes in the target area, determines the initial weight of each node and constructs a traffic network model, and then scores each node based on the traffic network model to obtain a comprehensive score for each node, thereby determining the key nodes in the target area. Based on the comprehensive score of the nodes, this method determines the key nodes, which can help traffic management departments accurately identify bottlenecks and hubs in the road network. By optimizing the operation and infrastructure of these nodes, traffic congestion can be effectively alleviated and road capacity can be improved, thereby enhancing the efficiency and reliability of the entire transportation system and providing people with a smoother and safer travel environment.

[0073] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0074] Figure 1 This is a process of a method for identifying key nodes in a road network provided in an embodiment of the present application. Figure 1 .

[0075] like Figure 1 As shown, the road network key node identification method provided by this embodiment includes:

[0076] S101: Obtain traffic information of multiple nodes in a target area, and determine an initial weight of each node based on the traffic information.

[0077] Among them, the target area can be, for example, a closed traffic area where key nodes need to be identified, and the traffic information of multiple nodes can include, for example: the incoming traffic volume of multiple traffic nodes in the target area, the outgoing traffic volume of multiple nodes, and the association relationship between multiple nodes. The multiple nodes can be intersection nodes in the target area, and the initial weight of each node can include, for example, the initial weighted flow of each node edge.

[0078] Since traffic conditions are changing dynamically, especially during peak hours or when emergencies occur, it is necessary to obtain traffic information in the target area in real time, so as to determine the initial weight of each node based on the traffic information, that is, to determine the initial weighted flow of each node edge. The purpose is to make the subsequently constructed traffic network model closer to the actual situation, so that the final identification results of the authoritative nodes and central nodes are more accurate.

[0079] In one possible manner, based on traffic information, determining the initial weight of each node may be implemented in the following manner:

[0080] Based on traffic information, for example, the traffic volume q of each intersection node A in the road network can be obtained, and the formula is as follows:

[0081]

[0082] Among them, q i It refers to the number of vehicles entering an entrance lane of intersection A per unit time.

[0083] From the traffic information, we can also extract features that help describe the importance of the node, such as traffic during peak hours, average waiting time, etc. Then we define a function to represent how these features affect the weight of the node. For example, we can define a linear combination formula:

[0084] ω=a×q+b×g+c×h

[0085] Among them, ω is the initial weight of node A, a, b, c are the corresponding weight coefficients, g is the characteristic function related to the vehicle speed, and h is the characteristic function related to the congestion situation of node A.

[0086] Similarly, the initial weighted flow of the node edge can be obtained according to the calculation method of the initial weight of the node.

[0087] It can be understood that the traffic information of multiple nodes in the target area is obtained within a specified time period, that is, in order to determine the key nodes in the target area, a time period can be preset and the traffic information within the time period can be obtained.

[0088] S102: Constructing a traffic network model according to the traffic information and initial weights of the plurality of nodes.

[0089] in, Figure 2A schematic diagram of the construction of a traffic network model is shown. In this figure, the points numbered 1 to 28 represent multiple traffic nodes in the target area, which can be important intersections or other key locations. The lines between the nodes clearly indicate the road connections between these intersections, and intuitively show the structure and layout of the traffic network. Through such a model, it is easier to analyze the interaction and importance of each node in the overall traffic network.

[0090] Traffic network models can better reflect the role of different nodes in the traffic network. Some nodes may be major traffic intersections, while others may be minor connection points. By collecting actual traffic information to build a traffic network model, we can more accurately reflect the actual usage of these nodes, thereby better evaluating their importance.

[0091] G = (V, E) is used to represent the traffic network, where V = (v1, v2, v3, …, v N ) is the set of traffic network nodes, E=(e1,e2,e3,…,e M ) is the edge set of the network, N = |V| is the total number of network nodes, and M = |E| is the total number of network edges. Based on the traffic information and initial weights of multiple nodes, a traffic network model similar to the actual traffic situation is constructed.

[0092] S103: Determine comprehensive scores of multiple nodes based on the traffic network model.

[0093] Among them, the comprehensive score can be used to evaluate the criticality of multiple nodes.

[0094] This step determines the comprehensive scores of multiple nodes in the target area so that we can subsequently identify which nodes are key nodes in the transportation network. By scoring each node, we can more accurately assess their importance and influence in the entire transportation network, thereby providing a scientific basis for optimizing traffic flow management, alleviating congestion, improving road capacity, and enhancing emergency response efficiency. After identifying these key nodes, the transportation management department can take more targeted measures to improve the operating efficiency and service level of the entire transportation system.

[0095] Based on the constructed traffic network model, analytical calculations can be performed to obtain the authority value and center value of each node. Through these calculation results, further comprehensive analysis based on the authority value and center value of each node can determine the comprehensive score of each node. This process not only helps us quantify the importance and connectivity of each node in the traffic network, but also provides a scientific basis for identifying key nodes, thereby providing strong support for optimizing traffic management and planning.

[0096] S104: Determine key nodes in the target area from the multiple nodes according to the comprehensive scores of the multiple nodes.

[0097] Among them, the key node can be a node with a larger comprehensive score in the target area.

[0098] The comprehensive score can be used to evaluate which nodes are most critical, such as which nodes are most prone to congestion, so as to take targeted measures, such as adjusting the timing of traffic lights, adding lanes or guiding traffic flow. For example, in the event of a traffic accident or natural disaster, the comprehensive score of the node can be used to quickly locate the key node, so as to quickly deploy emergency resources and reduce the impact of traffic disruption.

[0099] After obtaining the comprehensive scores of multiple nodes, the nodes can be sorted in order from large to small. According to the actual situation, the first N nodes can be used as key nodes in the target area.

[0100] Understandably, key nodes may be places with the heaviest traffic flow or hubs connecting multiple important road sections. Identifying these key nodes can help optimize resource allocation, such as giving priority to improving the infrastructure of these nodes.

[0101] The method for identifying key nodes in a road network provided in an embodiment of the present application obtains traffic information of multiple nodes in a target area, determines the initial weight of each node and constructs a traffic network model, and then scores each node based on the traffic network model to obtain a comprehensive score for each node, thereby determining the key nodes in the target area. The method realizes the identification of key nodes in the road network, helps to optimize the allocation and management of traffic resources, thereby effectively alleviating congestion, improving the smoothness and safety of traffic, and improving the operating efficiency and service level of the urban transportation system.

[0102] Figure 3 The process of the road network key node identification method provided in the embodiment of the present application Figure 2 This embodiment is in Figure 1 Based on the embodiment, a method for identifying key nodes in a road network is described in detail.

[0103] like Figure 1 As shown, the road network key node identification method provided by this embodiment includes:

[0104] S301: Obtain traffic information of multiple nodes in the target area, and for any one of the multiple nodes, determine at least one incoming traffic volume corresponding to the node, wherein the traffic information includes: the incoming traffic volume of the multiple nodes, the association relationship between the multiple nodes, and the outgoing traffic volume of the multiple nodes, and the association relationship includes: an inflow relationship and an outflow relationship.

[0105] Among them, the inflow traffic volume is the number of vehicles flowing into each node in the target area within the preset time, the outflow traffic volume is the number of vehicles flowing out of each node in the target area within the preset time, and the association relationship between multiple nodes can be the inflow relationship and outflow relationship of vehicles between each node.

[0106] The traffic information of multiple nodes in the target area is obtained, and at least one corresponding incoming traffic volume is determined for any of these nodes. The purpose is to fully understand the traffic load of each node, and determine the initial weight of each node based on the incoming traffic volume, outgoing traffic volume and the correlation between the incoming traffic volume and outgoing traffic volume between each node. The initial weight also includes the initial weighted flow of each node edge.

[0107] Real-time data can be collected through sensors, cameras and other equipment installed on the road to obtain traffic information at multiple intersections in the target monitoring area. Combined with historical traffic records and traffic flow information provided by third-party platforms, the traffic inflow of each node can be accurately measured and analyzed to evaluate the traffic load and importance of the node.

[0108] S302: Determine an initial weight of the node according to the at least one incoming traffic volume.

[0109] Among them, according to the inflow traffic volume of the node, the initial weight of the node can be determined in the following way:

[0110] The inflow traffic volume q of each intersection node A in the road network is obtained by the following formula:

[0111]

[0112] Among them, q i It refers to the number of vehicles entering an entrance lane of intersection A per unit time. In other words, the total inflow traffic volume of node A can be obtained by adding up the outflow traffic volume of all other nodes that have an inflow relationship with node A.

[0113] From the traffic information, we can also extract features that help describe the importance of nodes, such as peak-hour traffic and average waiting time, and define a function to reflect the impact of these features on node weights. For example, we can use a linear combination formula to calculate the weight of a node, assigning different feature values ​​to corresponding weight coefficients according to their importance, and thus comprehensively evaluate the importance of each node. Among them, we can define a linear combination formula:

[0114] ω=a×q+b×g+c×h

[0115] Among them, ω is the initial weight of node A, a, b, c are the corresponding weight coefficients, g is the characteristic function related to the vehicle speed, and h is the characteristic function related to the congestion situation of node A. The initial weight of node A can be calculated by this formula, and by analogy, the initial weight of each node in the target area can be further calculated.

[0116] S303: Determine the side information corresponding to the multiple nodes according to the association relationship between the multiple nodes.

[0117] The edge information corresponding to each node includes: the initial weighted flow of the edge corresponding to each node. The initial weighted flow of the node edge can be, for example, the traffic flow corresponding to each road at each intersection in real-time traffic.

[0118] The purpose of determining the edge information corresponding to multiple nodes based on the association relationship between these nodes is to accurately describe the connection mode and interaction intensity between nodes, so as to better understand the structure and traffic distribution of the entire transportation network and to facilitate the subsequent construction of a transportation network model.

[0119] The edge information corresponding to a node is determined based on the association relationship between multiple nodes. This can be done by analyzing the direct connections between nodes, recording whether there is a road connection between each pair of nodes and the type of connection, such as main roads, secondary roads, etc., and quantifying the properties of these connections, such as road length, initial weighted flow, average vehicle speed, etc., thereby forming detailed edge information to describe the relationship and interaction intensity between nodes.

[0120] The process of calculating the initial weighted flow of the edges corresponding to each node is similar to the process of calculating the initial weight of each node. For example, the traffic volume q of the node edge corresponding to each node can be obtained. The specific formula is as follows:

[0121]

[0122] Among them, q i It refers to the number of vehicles traveling around each node per unit time.

[0123] Then we can define a function to express how these features affect the weights of each node edge. For example, we can define a linear combination formula:

[0124] ω=a×q+b×g+c×h

[0125] Among them, ω is the initial weighted flow of the node edge, a, b, c are the corresponding weight coefficients, g is the characteristic function related to the vehicle speed, and h is the characteristic function of the road length corresponding to the node edge. The formula can be used to calculate the initial weighted flow of each node edge, and the initial weighted flow of each node edge is analyzed and processed to merge into the edge information corresponding to each node.

[0126] S304: Constructing the traffic network model based on the edge information, the location of each node, the outflow traffic volume and the initial weight.

[0127] The schematic diagram of traffic network model construction can be shown as follows: Figure 2 As shown in the figure, the points numbered 1 to 28 represent multiple nodes in the target area and the position of each node. Each node contains the outflow traffic volume and initial weight of each node; the lines between the nodes represent the road connections between these nodes, that is, the edges corresponding to each node. Each line contains edge information, that is, the initial weighted flow of each node edge.

[0128] This step constructs a traffic network model in order to more conveniently analyze the mutual influence and importance of each node in the entire traffic network, thereby providing clear guidance for optimizing traffic management and planning.

[0129] S305: Determine a first authority value and a first center value of each node based on the outflow traffic volume and the initial weights of the multiple nodes.

[0130] The first authority value may represent the authority of each node in the traffic network model of the entire target area, and the first center value may represent the center of each node in the traffic network model of the entire target area.

[0131] Determining the first authority value and the first center value of each node is the basic concept of the HITS algorithm. By determining the authority value and center value of each node, the HITS algorithm can identify the key nodes and paths in the road network, which plays an important role in optimizing traffic flow management and planning.

[0132] In one possible manner, the first authority value and the first center value of each node are determined based on the outflow traffic volume and initial weights of multiple nodes, and specifically, the following manner may be adopted:

[0133] For any node among the multiple nodes in the target area, the authority value a(i) and the center value h(i) of each node in the road network can be obtained based on the HITS algorithm, and then the authority value and the center value of all nodes can be initialized, that is, a0=1, h0=1.

[0134] Then determine the associated edge corresponding to the node according to the traffic network model. It should be noted that there is more than one associated edge, and analyze the associated edges to obtain the outflow traffic volume of each associated edge for the node, that is, the traffic volume flowing out of the node to other nodes through the corresponding associated edge. For example, the traffic volume flowing out of node I to node Q can be expressed as w iqTherefore, the outflow traffic volume of each associated edge for the node can be combined to calculate the first central value h(i) of each node. Specifically, the following formula can be used:

[0135] h(i)=∑w iq a(i)

[0136] Among them, w iq is the outflow traffic from node I to other nodes, h(i) is the first center value of node I, a(i) is the first authoritative value of node I, and at this time it is the initialized authoritative value, that is, a(i)=a0=1.

[0137] The first authority value a(i) of each node can also be calculated by combining the initial weight of the node, that is, the initial weighted flow of each association to the node. Specifically, the following formula can be used:

[0138] a(i)=∑w qi h(i)

[0139] Among them, w qi is the initial weight of node I, h(i) is the first center value of node I, which is the initialized center value at this time, that is, h(i)=h0=1, and a(i) is the first authority value of node I.

[0140] It is understandable that after calculating the first authority value and the first center value of each node, the authority value and the center value of each node need to be calculated repeatedly until convergence. Convergence means that the change of the authority value and the center value between two consecutive iterations is less than a preset threshold.

[0141] S306: Normalize the first authority value and the first center value to obtain a second authority value and a second center value of each node.

[0142] Among them, normalization processing is a commonly used technology in data analysis and processing, and its purpose is to convert the numerical values ​​of the first authoritative value and the first central value into the same range.

[0143] In each iteration process, the first authority value and the first central value need to be normalized to eliminate the adverse effects of data differences so that different features or variables can be compared and calculated at the same scale to avoid numerical expansion.

[0144] In a possible manner, the first authority value and the first central value may be normalized using the following calculation formula:

[0145]

[0146]

[0147] The normalized first authority value and the first center value are used as the second authority value and the second center value.

[0148] S307: Iteratively update the second authoritative value and the second central value until the second authoritative value and the second central value converge.

[0149] Among them, the authority value and the center value are continuously iteratively updated according to the above-mentioned authority value, center value and normalized calculation method until convergence.

[0150] S308: Determine a comprehensive score of the corresponding node according to the converged second authority value and the second center value.

[0151] Among them, the comprehensive score can be used to evaluate the criticality of multiple nodes.

[0152] In a possible manner, the following calculation method may be used to determine the comprehensive score of the node according to the converged second authority value and the second center value:

[0153] R(i)=α×a ′ (i)+(1-α)×h ′ (i)

[0154] Among them, R(i) is the comprehensive score of the node, α=0.5.

[0155] S309: Sorting the comprehensive scores of the multiple nodes in descending order.

[0156] Among them, multiple nodes are sorted in descending order according to the comprehensive score. The higher the comprehensive score of each node, the greater the importance of the node.

[0157] S310: Determine the first N nodes after sorting as key nodes in the target area.

[0158] Wherein, N can be 1 or other numbers.

[0159] If only the most critical nodes in the target area are to be determined, then N=1, and the nodes with the highest comprehensive scores in the road network are the key nodes. If the more critical nodes in the target area need to be determined, then N=5 can be set, and the nodes ranked in the first five are the key nodes in the road network.

[0160] The method for identifying key nodes in a road network provided by the embodiment of the present application obtains traffic information of multiple nodes in a target area, determines the initial weight of each node and the side information corresponding to each node, and constructs a traffic network model, and then analyzes based on the model to determine the authority value and center value of each node, and performs a comprehensive score calculation based on the authority value and center value of each node to obtain a comprehensive score for each node, which can be used to judge the key nodes in the target area. The larger the score, the more critical the node. This method realizes the identification of key nodes in the road network, thereby effectively alleviating congestion, improving the smoothness and safety of traffic, and improving the operating efficiency and service level of the urban transportation system.

[0161] Figure 4 This is a schematic diagram of the structure of the road network key node identification device provided by this application. Figure 4 As shown, the road network key node identification device 400 provided in this embodiment includes:

[0162] An acquisition module 401 is used to acquire traffic information of multiple nodes in a target area;

[0163] A determination module 402, configured to determine an initial weight of each node based on the traffic information;

[0164] The processing module 403 is used to construct a traffic network model according to the traffic information and initial weights of the plurality of nodes;

[0165] The determination module 402 is further configured to determine comprehensive scores of a plurality of nodes based on the traffic network model; and determine key nodes in the target area from the plurality of nodes according to the comprehensive scores of the plurality of nodes.

[0166] Optionally, the determination module 402 is further used to determine, for any one of the multiple nodes, at least one incoming traffic volume corresponding to the node; and determine an initial weight of the node based on the at least one incoming traffic volume.

[0167] Optionally, the determining module 402 is further configured to determine the edge information corresponding to the multiple nodes according to the association relationship between the multiple nodes;

[0168] The processing module 403 is further used to construct the traffic network model based on the edge information, the location of each node, the outflow traffic volume and the initial weight.

[0169] Optionally, the determination module 402 is further configured to determine a first authority value and a first center value of each node based on the outflow traffic volume and initial weights of the multiple nodes;

[0170] The processing module 403 is further used to optimize and update the first authority value and the first center value to obtain a comprehensive score of each node.

[0171] Optionally, the determination module 402 is further configured to determine, for any one of the multiple nodes, at least one associated edge corresponding to the node and an outflow traffic volume of each associated edge relative to the node; and determine a first central value of the node according to the outflow traffic volume of the at least one associated edge relative to the node;

[0172] The processing module 403 is further configured to determine a first authority value of the node according to the initial weight of the node.

[0173] Optionally, the processing module 403 is further used to normalize the first authority value and the first center value to obtain a second authority value and a second center value of each node; iteratively update the second authority value and the second center value until the second authority value and the second center value converge;

[0174] The determination module 402 is further configured to determine a comprehensive score of the corresponding node according to the converged second authority value and the second center value.

[0175] Optionally, the processing module 403 is further configured to sort the comprehensive scores of the multiple nodes in descending order;

[0176] The determination module 402 is further configured to determine the first N nodes after sorting as key nodes in the target area.

[0177] The present embodiment provides a device for identifying key nodes in a road network, which can execute the method for identifying key nodes in a road network provided by the above method embodiment. The implementation principle and technical effect thereof are similar, and will not be described in detail in the present embodiment.

[0178] Figure 5 This is a schematic diagram of the structure of the road network key node identification device provided in this application. Figure 5 As shown, the present application provides a road network key node identification device, and the road network key node identification device 500 includes: a receiver 501, a transmitter 502, a processor 503 and a memory 504.

[0179] Receiver 501, used for receiving instructions and data;

[0180] A transmitter 502, used for sending instructions and data;

[0181] Memory 504, used to store computer-executable instructions;

[0182] The processor 503 is used to execute the computer-executable instructions stored in the memory 504 to implement the various steps performed by the road network key node identification method in the above embodiment. For details, please refer to the relevant description in the above embodiment of the road network key node identification method.

[0183] Optionally, the memory 504 may be independent or integrated with the processor 503 .

[0184] When the memory 504 is independently provided, the electronic device further includes a bus for connecting the memory 504 and the processor 503 .

[0185] The present application also provides a computer storage medium, in which computer execution instructions are stored. When a processor executes the computer execution instructions, a road network key node identification method as performed by the above-mentioned road network key node identification device is implemented.

[0186] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In hardware implementations, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical nodes; for example, a physical node may have multiple functions, or a function or step may be performed by several physical nodes in cooperation. Some physical nodes or all physical nodes may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those of ordinary skill in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0187] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0188] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for identifying key nodes in a road network, characterized in that: include: Acquire traffic information of multiple nodes in the target area, and determine an initial weight of each node based on the traffic information; Constructing a traffic network model according to the traffic information and initial weights of the plurality of nodes; Determining comprehensive scores of multiple nodes based on the transportation network model; According to the comprehensive scores of the multiple nodes, key nodes in the target area are determined from the multiple nodes.

2. The method according to claim 1, characterized in that The traffic information includes: the inflow traffic volume of multiple nodes, and the initial weight of each node is determined based on the traffic information, including: For any one of the plurality of nodes, determining at least one incoming traffic volume corresponding to the node; An initial weight of the node is determined according to the at least one incoming traffic volume.

3. The method according to claim 2, characterized in that The traffic information also includes: associations between multiple nodes and outflow traffic volumes of multiple nodes, wherein the associations include inflow relationships and outflow relationships. The traffic network model is constructed based on the traffic information and initial weights of the multiple nodes, including: Determine, according to the association relationship between the multiple nodes, the edge information corresponding to the multiple nodes; The traffic network model is constructed based on the edge information, the location of each node, the outflow traffic volume and the initial weight.

4. The method according to claim 3, characterized in that Determining the comprehensive scores of the plurality of nodes based on the traffic network model includes: Determining a first authority value and a first center value of each node based on the outflow traffic and the initial weights of the plurality of nodes; The first authority value and the first center value are optimized and updated to obtain a comprehensive score of each node.

5. The method according to claim 4, characterized in that The determining of the first authority value and the first center value of each node based on the outflow traffic volume and the initial weights of the plurality of nodes comprises: For any one of the plurality of nodes, determining at least one associated edge corresponding to the node and an outflow traffic volume of each associated edge relative to the node; determining a first central value of the node based on the outflow traffic volume of the at least one associated edge relative to the node; A first authority value of the node is determined according to the initial weight of the node.

6. The method according to claim 4, characterized in that The optimizing and updating the first authority value and the first center value to obtain a comprehensive score of each node includes: Normalizing the first authority value and the first center value to obtain a second authority value and a second center value of each node; Iteratively updating the second authoritative value and the second central value until the second authoritative value and the second central value converge; According to the converged second authority value and the second center value, the comprehensive score of the corresponding node is determined.

7. The method according to claim 1, characterized in that Determining the key nodes in the target area from the multiple nodes according to the comprehensive scores of the multiple nodes includes: Sorting the comprehensive scores of the multiple nodes in descending order; The first N nodes after sorting are determined as key nodes in the target area.

8. A road network key node identification device, characterized in that: The device comprises: An acquisition module, used to acquire traffic information of multiple nodes in a target area; A determination module, used to determine the initial weight of each node based on the traffic information; A processing module, used for constructing a traffic network model according to the traffic information and initial weights of the plurality of nodes; The determination module is further used to determine the comprehensive scores of multiple nodes based on the traffic network model; and determine the key nodes in the target area from the multiple nodes according to the comprehensive scores of the multiple nodes.

9. A road network key node identification device, characterized in that: include: Memory; processor; Wherein, the memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the road network key node identification method according to any one of claims 1-7.

10. A computer storage medium, characterized in that: The computer storage medium stores computer execution instructions, which, when executed by a processor, are used to implement the road network key node identification method according to any one of claims 1 to 7.

Images