A method for extracting features of a spatial complex network

Abstract

The application relates to the technical field of data processing, in particular to a spatial complex network feature extraction method, which comprises the following steps: acquiring building and type information and dynamic information of road nodes in a city traffic complex network; confirming a target building node; obtaining reachable road nodes based on paths reaching the target building node, determining reachable paths, and obtaining travel costs of the reachable road nodes to the target building node; obtaining influence trends of the reachable road nodes on the target building node; clustering influence trends of all the reachable road nodes; and extracting a feasibility evaluation index and a feasibility evaluation result of buildings of various types planned for each reachable road node. The application aims to extract demand features of city road building types, and improve the accuracy and rationality of evaluating road building planning.

Description

Technical Field

[0001] This application relates to the field of data processing technology, specifically to a method for feature extraction of spatially complex networks. Background Technology

[0002] With the acceleration of urbanization, the complex networks of cities and their residents' lives are exhibiting high complexity and dynamic change. Urban transportation networks not only include numerous nodes and connections, but their structure and function are also highly complex. Therefore, it is essential to effectively extract the characteristics of these spatially complex networks to provide crucial references for road and building planning. By analyzing and mining relevant characteristic information, the building layout within the urban road system can be effectively evaluated, thereby optimizing urban planning and improving the overall coordination of traffic and function.

[0003] When evaluating a certain type of building in urban road planning based on complex networks, the data contained in the complex networks often focuses on specific aspects such as the transportation system during the analysis. However, relying solely on this traffic-related data to assess the planning feasibility of buildings on urban roads is one-sided and cannot fully reflect the actual characteristics and needs of buildings; this limitation affects the accuracy and rationality of the assessment of road and building planning. Summary of the Invention

[0004] In view of the above, it is necessary to provide a feature extraction method for spatially complex networks to solve the above problems.

[0005] One embodiment of this application provides a method for feature extraction from spatially complex networks, the method comprising:

[0006] S1: Obtain information on the buildings and their types at each road node in the complex urban traffic network, as well as all dynamic information within a preset time period;

[0007] S2: Take the road nodes where the buildings containing various types of information are located as the target building nodes of various types of information. Based on the path to the target building node, obtain the reachable road nodes, determine the reachable path, analyze the number of road nodes in each reachable path, and combine the distribution characteristics of the dynamic information of each reachable road node to obtain the travel cost from each reachable road node to the target building node.

[0008] S3: Based on the differences in dynamic information between adjacent road nodes in each reachable path, and combined with the travel cost, obtain the influence trend of target building nodes of various types of information on each reachable road node;

[0009] S4: Cluster the influence trends of all reachable road nodes based on the influence trends of target building nodes with the same type of information.

[0010] S5: Based on the influence trends of target building nodes of various types of information on each accessible road node, and combined with the clustering results, extract the feasibility assessment index and feasibility assessment results of buildings of various types of information planned for each accessible road node.

[0011] Specifically, obtaining the reachable road nodes refers to:

[0012] The system counts all paths that reach target building nodes of various types of information, given a specified path length, and records the road nodes traversed by the path as reachable road nodes.

[0013] Specifically, determining the reachable path involves extracting the path from each reachable road node in all paths to the target building node.

[0014] Specifically, the travel cost from each reachable road node to the target building node is obtained as follows:

[0015] Calculate the average number of road nodes in all reachable paths; calculate the shortest path length from each reachable road node to the target building node.

[0016] The average of all dynamic information of each reachable road node within a preset time period is merged to obtain the first dynamic average.

[0017] Based on the average number of road nodes and the shortest path length corresponding to each reachable road node, and combined with the first dynamic average, the travel cost from each reachable road node to the target building node is obtained; wherein, the travel cost is positively correlated with the shortest path length and the first dynamic average, and negatively correlated with the average number of road nodes.

[0018] Specifically, the trend of each reachable road node being affected by target building nodes of various types of information is as follows:

[0019] The preset time period is divided into equal parts to obtain local time periods; on each reachable path, based on the differences in the dynamic information between adjacent road nodes, the attraction of target building nodes of each type of information to each reachable road node in each local time period is obtained.

[0020] By obtaining the average attraction of target building nodes of various types of information to each reachable road node over all time periods, and combining this with the negative correlation mapping of the travel cost of each target building node to each reachable road node, the influence trend of each reachable road node on target building nodes of various types of information is obtained.

[0021] Specifically, the degree to which the target building nodes, from which various types of information are obtained, attract each reachable road node in each local time period is as follows:

[0022] The k-th road node containing the building with the i-th type information is taken as the target building node O. i,k ;

[0023] The dynamic differences between road nodes are obtained by analyzing the distribution differences of dynamic information between road nodes in different local time periods.

[0024] Target building node O i,k The attractiveness of the j-th reachable road node to each local time period is denoted as w. j,(i,k) Its formula is as follows: Where, ΔA (i,k),j,s (r, r-1) represents the distance from the j-th reachable road node to the target building node O. i,k The dynamic differences between the r-th road node and the (r-1)-th road node in the s-th reachable path during each local time period; n (i,k),j,s This represents the distance from the j-th reachable road node to the target building node O. i,k The number of road nodes in the s-th reachable path; m (i,k),j This represents the distance from the j-th reachable road node to the target building node O. i,k The number of reachable paths; ε is a preset value greater than zero.

[0025] The dynamic differences between road nodes are obtained, including:

[0026] The average values ​​of all dynamic information within each local time period of each road node are merged to obtain the second dynamic average value; the difference between the second dynamic average values ​​of road nodes is calculated to obtain the dynamic difference.

[0027] Specifically, the clustering of the influence trends of all reachable road nodes involves:

[0028] Based on the two-dimensional planar distribution, the coordinate system of each road node is obtained; the density clustering method is used to cluster target building nodes of various types of information as seed points to obtain clusters corresponding to various sub-points.

[0029] The specific formula for the feasibility assessment index of the building for extracting various types of information from each reachable road node is as follows:

[0030] Among them, f j,i K represents the feasibility assessment index of the building for planning the i-th type of information at the j-th accessible road node; i This represents the number of target building nodes for the i-th type of information; g i,k P represents the number of road nodes in the cluster corresponding to the k-th seed point where the building of the i-th type of information is located; j,(i,k)The influence trend of the k-th seed point where the building of the i-th type of information is located on the j-th reachable road node is represented; norm() represents the normalization function.

[0031] Specifically, the feasibility assessment results are as follows:

[0032] When the feasibility assessment index of buildings of various types planned for each accessible road node is greater than the preset assessment threshold, the corresponding accessible road node will be used as the planning node for buildings of various types.

[0033] This application has at least the following beneficial effects:

[0034] This application first obtains information on buildings and their types at each road node in a complex urban traffic network, along with all dynamic information within a preset time period. This facilitates subsequent analysis of the types and distribution of buildings at each road node, leading to better road network planning. It then analyzes the number of road nodes in each reachable path and, combined with the distribution characteristics of the dynamic information of each reachable road node, obtains the travel cost from each reachable road node to the target building node. The beneficial effect is that by combining the analysis of reachable paths, the number of nodes, and their travel costs, it can more accurately extract the demand characteristics of building types in certain urban areas, improving the rationality of planning analysis. Furthermore, based on the differences in the dynamic information between adjacent road nodes in each reachable path, and combined with the travel costs, it obtains the influence trend of each reachable road node on the target building node. The beneficial effect is that by analyzing the differences in the dynamic information of adjacent road nodes, it can accurately identify which roads will be affected by the attractiveness of the target building, leading to increased traffic pressure. Finally, based on the influence trend of all reachable road nodes on the same type of target building node, it clusters the influence trends of all reachable road nodes. The beneficial effect is that it avoids the superimposed effect of the same type of building when affecting road nodes, improving the accuracy and rationality of evaluating various types of buildings in road node planning. Attached Figure Description

[0035] Figure 1 A flowchart of a spatial complex network feature extraction method provided in this application;

[0036] Figure 2 A flowchart for obtaining the feasibility assessment index provided for this application. Detailed Implementation

[0037] In the description of the embodiments in this application, the words "exemplary," "or," and "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplary," "or," and "for example" is intended to present the relevant concepts in a specific manner.

[0038] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in this application's specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

[0039] It should also be noted that the terms "first" and "second" in this application and its accompanying drawings are used to distinguish similar objects, rather than to describe a specific order or sequence. The methods disclosed in the embodiments of this application or the methods shown in the flowcharts include one or more steps for implementing the method. Without departing from the scope of protection of this application, the execution order of multiple steps can be interchanged, and some steps can also be deleted.

[0040] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0041] This application proposes a feature extraction method for spatially complex networks, applied in the field of data processing technology. (See attached document.) Figure 1 The method includes the following steps:

[0042] S1: Obtain information on buildings and their types at each road node in the complex urban traffic network, as well as all dynamic information within a preset time period.

[0043] This application extracts features from complex spatial networks to obtain feasibility assessment results for planning various types of buildings on each urban road. A dual topology method is employed when constructing the topology of the complex urban traffic network. This method treats urban roads as nodes in the network, and road intersections as edges connecting nodes, thus abstracting the overall structure of the urban traffic network. Remote sensing data is used to extract relevant information about urban roads and various types of buildings, which is then analyzed using the ArcGIS platform.

[0044] When constructing complex urban traffic networks, relying solely on the distance between road nodes to calculate the average path length may not fully reflect the actual situation of the network. In reality, the attribute characteristics of road nodes typically include both static and dynamic information. Static information includes buildings and their types; this application extracts building and type information for each road node using the ArcGIS platform. Dynamic information includes pedestrian and vehicle traffic flow on the road; this application uses digital twin technology to obtain pedestrian and vehicle traffic data for each road every hour over a historical month. The implementation can adjust the time length and time interval for acquiring dynamic information according to the actual situation; this application does not impose any restrictions on this.

[0045] S2: Take the road nodes where the buildings containing various types of information are located as the target building nodes of various types of information. Based on the path to the target building node, obtain the reachable road nodes, determine the reachable path, analyze the number of road nodes in each reachable path, and combine the distribution characteristics of the dynamic information of each reachable road node to obtain the travel cost from each reachable road node to the target building node.

[0046] When conducting feasibility assessments of planning various buildings along urban roads based on complex urban traffic networks, the data contained within these networks, especially traffic system-related data, often fails to fully reflect the actual spatial situation during demand feature mining. This limitation can affect the reference value and accuracy of traffic data during building planning, thereby reducing the reliability of the assessment results.

[0047] For a building with a certain type of information, it will have a positive promoting effect on the actual residents, pedestrians and vehicles within a certain range. That is, it will drive people and vehicles in the surrounding area to move to the building of this type during a specific time period and drive the development of other industries in the surrounding area. Therefore, the road node containing the i-th type of information can be extracted. Based on the dynamic information of the extracted road node and its surrounding road nodes, the influence range of each road node containing the i-th type of information can be determined, and finally the influence of other road nodes on the current road node can be determined.

[0048] Based on the characteristics of complex urban traffic networks, any two road nodes are connected by an edge, and the average path length between them is the shortest path distance between the two roads. Specifically, the k-th road node containing the building with the i-th type of information is taken as the target building node O. i,kThe number of road nodes traversed by the path is set, and the path containing the building of type i at the k-th road node is counted. It should be noted that adjacent road nodes in the path are connected in the complex urban traffic network, and each road node corresponds to more than one path. For any two different paths to the same road node, at least one of the paths must be different road nodes. In this embodiment, the number of road nodes traversed by the path is set to 10, but the implementer can adjust it according to the actual situation.

[0049] Buildings containing certain types of information typically attract surrounding pedestrians and vehicles, an attraction that often diminishes with increasing distance. This is because the cost of travel increases with distance, making people and vehicles more inclined to choose areas closer to their destination. Therefore, the attractiveness of a central node usually exhibits a distance-attenuation characteristic.

[0050] For a building containing the i-th type of information, it attracts people and vehicles within a certain range, and its attractiveness gradually decreases as the distance from different outer road nodes to the road node where the building is located increases. All road nodes along the path of each road node containing the i-th type of information are denoted as reachable road nodes. The paths from each reachable road node to the target building node are extracted and denoted as reachable paths. The average number of road nodes traversed by the corresponding reachable paths is calculated. The shortest path length from each reachable road node to the target building node is calculated. The average values ​​of all dynamic information for each reachable road node within a preset time period are merged to obtain a first dynamic average. Based on the average number of road nodes corresponding to each reachable road node, the shortest path length, and the first dynamic average, the travel cost from each reachable road node to the target building node is obtained. The travel cost is positively correlated with the shortest path length and the dynamic average, and negatively correlated with the average number of road nodes.

[0051] It should be noted that a positive correlation is a relationship in which one variable increases as the other variable increases; a negative correlation is a relationship in which one variable increases as the other variable decreases.

[0052] Specifically, connect the j-th reachable road node to the target building node O. i,k The travel cost is denoted as μ. j,i,k Its formula is as follows: Where, d j,(i,k) This represents the distance from the j-th reachable road node to the target building node O. i,k The average path length; n j,(i,k) This represents the distance from the j-th reachable road node to the target building node O. i,kThe average number of nodes; This represents the dynamic mean of the j-th reachable road node, which is the sum of the averages of all dynamic information within a preset time period. It is used to measure the result of merging the averages of all dynamic information of reachable road nodes.

[0053] It should be understood that the larger the dynamic mean of reachable road nodes, the greater the pedestrian and vehicle traffic data of that road node within the preset time period, the greater the difficulty of traveling on the corresponding road, and the greater the cost of reaching the target building node.

[0054] S3: Based on the differences in dynamic information between adjacent road nodes in each reachable path, and combined with the travel cost, obtain the influence trend of target building nodes of various types of information on each reachable road node.

[0055] Since attractiveness typically increases towards the target building node, when analyzing the reachable paths from each accessible road node to the target building node, if the traffic or pedestrian flow between adjacent road nodes along the path towards the target building node shows a significant upward trend, this indicates that the target building node is more attractive to each accessible road node.

[0056] The preset time period is divided equally to obtain various local time periods; in this embodiment, the local time period is one day; implementers can adjust it according to actual conditions. On each reachable path from each reachable road node to the target building node, based on the differences in dynamic information between adjacent road nodes, the attractiveness of the target building node of each type of information to each reachable road node in each local time period is obtained: [The text then abruptly shifts to a different topic:] Target building node O... i,k The attractiveness of the j-th reachable road node to each local time period is denoted as w. j,(i,k) Its formula is as follows: Where, ΔA (i,k),j,s (r, r-1) represents the distance from the j-th reachable road node to the target building node O. i,k The dynamic differences between the r-th road node and the (r-1)-th road node in the s-th reachable path during each local time period; n (i,k),j,s This represents the distance from the j-th reachable road node to the target building node O. i,k The number of road nodes in the s-th reachable path; m (i,k),j This represents the distance from the j-th reachable road node to the target building node O. i,k The number of reachable paths; ε is a preset value greater than zero, with a value of 0.01. Specifically, the dynamic difference is: the average of all dynamic information within each local time period of each road node is accumulated to obtain a second dynamic average; the difference between the second dynamic averages of road nodes is calculated to obtain the dynamic difference.

[0057] By summing the differences in dynamic information between adjacent nodes in all reachable paths corresponding to two road nodes and the sum of the absolute values ​​of these differences, the attraction of the target building node to each reachable road node can be obtained. The range of this value is [-1, 1]. The larger the value, the more obvious the increasing trend of dynamic information with the increase of path distance, which indicates that the attraction of the target building node to the road node is stronger.

[0058] Since dynamic information fluctuates at different times, the influence trend of each reachable road node on the target building node is obtained by combining the attraction of the target building node to each reachable road node with the travel cost across all time periods: the average attraction of the target building node of each type of information to each reachable road node across all time periods is obtained, and the negative correlation mapping of the travel cost of each target building node to each reachable road node is combined to obtain the influence trend of each target building node on each reachable road node.

[0059] In this embodiment, the target building node O i,k The influence trend on the j-th reachable road node is denoted as P. j,(i,k) Its formula is as follows: Among them, w j,(i,k),t Represents the target building node O i,k The attractiveness of the j-th reachable road node in the t-th local time interval; T represents the number of all local time intervals; μ j,(i,k) This represents the distance from the j-th reachable road node to the target building node O. i,k The cost of the journey.

[0060] The lower the travel cost of the target building node to each reachable road node, the lower the actual difficulty for residents to reach the target building node from the reachable road nodes. If the target building node is more attractive, the tendency for surrounding residents to move towards the target building node will also increase, and the greater the influence of the target building node on each reachable road node, that is, the greater the tendency for reachable road nodes to be influenced by the target building node over a period of time.

[0061] S4: Cluster the influence trends of all reachable road nodes based on the influence trends of target building nodes with the same type of information.

[0062] In complex urban traffic networks, even if multiple buildings are of the same type, their influence on other road nodes can vary due to differences in reputation, surrounding residents' habits, and other factors. Therefore, when evaluating buildings of various types at any road node, relying solely on the influence of a single neighboring building of the same type may lead to inaccurate judgments.

[0063] Based on the influence trend of all reachable road nodes on target building nodes with the same type of information, the influence trend of all reachable road nodes is clustered: specifically, according to the two-dimensional planar distribution, the coordinate system of each road node is obtained; the mean drift clustering method is used, with the road nodes where various buildings with the same type of information are located as seed points for clustering.

[0064] In practical clustering, each road node is influenced by multiple other road nodes, often falling within the influence range of multiple seed points simultaneously. Furthermore, the irregularity of complex urban traffic networks can lead to some road nodes being incorrectly assigned to clusters corresponding to seed points with less influence. To avoid this, during clustering, the influence of each road node on its own seed point must consistently be greater than its influence on other seed points, ensuring that road nodes are correctly assigned to the most representative clusters. This method yields irregular cluster structures that more accurately reflect the complex networks and spatial relationships in reality. Therefore, for the clusters corresponding to various sub-points of the i-th type of information, the total number of road nodes contained in each cluster can be obtained.

[0065] S5: Based on the influence trends of target building nodes of various types of information on each accessible road node, and combined with the clustering results, extract the feasibility assessment index and feasibility assessment results of buildings of various types of information planned for each accessible road node.

[0066] When conducting a feasibility assessment of buildings of various types planned for each reachable road node, if the influence trend of the reachable road node on the various road nodes where the buildings of the same type are located is smaller, and the number of road nodes contained in the clusters corresponding to its various road nodes is smaller, then the influence range of the various road nodes where the buildings of the same type are located on other surrounding road nodes is smaller, indicating that the influence weight on the reachable road node is lower; and thus the feasibility assessment result of the buildings of that type on the road node is greater.

[0067] Based on this, according to the influence trend of various types of buildings on each reachable road node by different target building nodes, and combined with the clustering results of buildings with the same type of information, the feasibility assessment index of various types of buildings planned for each reachable road node is extracted, expressed by the formula: Among them, f j,i K represents the feasibility assessment index of the building for planning the i-th type of information at the j-th accessible road node; i This represents the number of road nodes containing buildings of type i, i.e., the number of seed points corresponding to buildings of type i; g i,kP represents the number of road nodes in the cluster corresponding to the k-th seed point where the building of the i-th type of information is located; j,(i,k) This represents the influence trend of the k-th seed point, where the building of type i is located, on the j-th reachable road node; norm() represents the normalization function, and this embodiment uses the sigmoid function for normalization. The flowchart for obtaining the feasibility assessment index is shown below. Figure 2 As shown.

[0068] When the feasibility assessment index of buildings of various types planned for each reachable road node is greater than the preset assessment threshold, the corresponding reachable road node will be used as the planning node for buildings of various types. In this embodiment, the assessment threshold is 0.7, and the implementer can adjust it according to the actual situation.

[0069] Finally, the planning nodes corresponding to buildings of various types of information are marked in the form of layers in the complex urban traffic network. In this embodiment, different colors are used to mark them in the network.

[0070] This completes the feature extraction of spatially complex networks.

[0071] This application provides a method for feature extraction from spatially complex networks. The method includes: firstly, acquiring information on buildings and their types at each road node in a complex urban traffic network, along with all dynamic information within a preset time period. This facilitates subsequent analysis of the types and distribution of buildings at each road node, leading to better road network planning. Secondly, analyzing the number of road nodes in each reachable path, and combining this with the distribution characteristics of the dynamic information of each reachable road node, yields the travel cost from each reachable road node to the target building node. The beneficial effect is that by combining the analysis of reachable paths, the number of nodes, and their travel costs, the demand characteristics of building types in certain urban areas can be extracted more accurately, improving the rationality of planning analysis. First, based on the differences in dynamic information between adjacent road nodes in each reachable path and combined with the travel cost, the influence trend of each reachable road node on the target building node is obtained. The beneficial effect is that by analyzing the differences in dynamic information of adjacent road nodes, it is possible to accurately identify which roads will be affected by the attraction of the target building, leading to increased traffic pressure. Based on the influence trend of all reachable road nodes on the target building node with the same type of information, the influence trend of all reachable road nodes is clustered. The beneficial effect is to avoid the superposition effect of the same type of building when affecting road nodes, and to improve the accuracy and rationality of evaluating various types of buildings in road node planning.

[0072] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than that shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the description; sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. Each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0073] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A spatial complex network feature extraction method, characterized in that, The method comprises the following steps: S1: obtaining building and its type information of each road node in the urban traffic complex network and all dynamic information in a preset time period; S2: taking the road node where the building containing various type information is located as a target building node of various type information, obtaining reachable road nodes based on paths reaching the target building node, determining reachable paths, analyzing the number of road nodes in each reachable path, combining the distribution characteristics of dynamic information of each reachable road node, and obtaining the travel cost of each reachable road node to the target building node; S3: obtaining the influence trend of each reachable road node on the target building node of various type information according to the difference between the dynamic information of adjacent road nodes in each reachable path and combining the travel cost; S4: clustering the influence trends of all reachable road nodes according to the influence trends of all reachable road nodes on the target building node of the same type information; S5: extracting the feasibility evaluation index and the feasibility evaluation result of the building of each reachable road node planning various type information according to the influence trends of each reachable road node on the target building node of various type information and combining the clustering results; The travel cost of each reachable road node to the target building node is obtained, specifically as follows: statistically obtaining the average number of road nodes in all reachable paths; and calculating the shortest path length of each reachable road node to the target building node; fusing the average of all dynamic information of each reachable road node in a preset time period to obtain a first dynamic average; obtaining the travel cost of each reachable road node to the target building node based on the average number of road nodes corresponding to each reachable road node, the shortest path length, and the first dynamic average; wherein the travel cost is positively correlated with the shortest path length and the first dynamic average, and is negatively correlated with the average number of road nodes; The influence trend of each reachable road node on the target building node of various type information is obtained, specifically as follows: dividing the preset time period into local time periods; on each reachable path, obtaining the attraction degree of each target building node of various type information to each reachable road node in each local time period according to the difference between the dynamic information of adjacent road nodes; obtaining the average of the attraction degree of each target building node of various type information to each reachable road node in all time periods, and combining the negative correlation mapping of the travel cost of each target building node to each reachable road node to obtain the influence trend of each reachable road node on the target building node of various type information; The influence trends of all reachable road nodes are clustered, specifically as follows: obtaining the coordinate system of each road node according to two-dimensional plane distribution; and adopting a density clustering method to cluster various target building nodes as seed points to obtain the clustering cluster corresponding to each seed point; The specific formula of the feasibility evaluation index of each reachable road node planning various type information buildings is as follows: ; wherein, represents the feasibility evaluation index of the building of the jth reachable road node planning the ith type of information; represents the number of target building nodes of the ith type of information; represents the number of road nodes in the clustering cluster corresponding to the kth seed point where the building of the ith type of information is located; represents the influence trend of the kth seed point where the building of the ith type of information is located to the jth reachable road node; norm() represents a normalization function.

2. The method of claim 1, wherein, The reachable road nodes are obtained, specifically as follows: The paths of all types of information reaching the target building node of the building node are determined, and the road nodes passed by the paths are recorded as reachable road nodes.

3. The method of claim 1, wherein, The reachable paths are determined, specifically, the paths of each reachable road node reaching the target building node in all paths are intercepted.

4. The method of claim 1, wherein, The attraction degrees of each reachable road node to each type of information target building node in each local time period are obtained, specifically: The kth road node where the building containing the ith type of information is located is taken as a target building node ; The dynamic differences between the road nodes are obtained according to the distribution differences of the dynamic information between the road nodes in each local time period. The target building node is determined The attraction degree of each local time period of the jth reachable road node is denoted as The formula is as follows: ; wherein, The dynamic difference between the rth road node and the r-1th road node in the s th reachable path from the jth reachable road node to the target building node in each local time period is denoted as The number of road nodes in the s th reachable path from the jth reachable road node to the target building node is denoted as The number of reachable paths from the jth reachable road node to the target building node is denoted as The number of reachable paths from the jth reachable road node to the target building node is denoted as is a preset value greater than zero.​​ 5. The method of claim 4, wherein, The dynamic differences between the road nodes are obtained, including: The mean values of all dynamic information of each road node in each local time period are fused to obtain a second dynamic mean value; the difference between the second dynamic mean values of the road nodes is calculated to obtain the dynamic differences.

6. The method of claim 1, wherein, The feasibility evaluation result is specifically: When the feasibility evaluation index of each reachable road node planning the buildings of various types of information is greater than a preset evaluation threshold, the corresponding reachable road node is taken as a planning node of the building of various types of information.

Images