Spatial complex network feature extraction method

Abstract

The invention relates to the technical field of data processing, in particular to a spatial complex network feature extraction method, which comprises the following steps of: acquiring buildings of road nodes in an urban traffic complex network and type information and dynamic information of the buildings; determining a target building node, obtaining reachable road nodes based on a path reaching the target building node, determining a reachable path, and obtaining an advancing cost from each reachable road node to the target building node; obtaining the influence trend of each reachable road node on the target building node; clustering the influence trends of all reachable road nodes; and extracting feasibility evaluation indexes and feasibility evaluation results of the buildings of various types of information planned by each reachable road node. The invention aims to extract demand features of urban road building types and improve the accuracy and rationality of evaluating road building planning.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method for extracting features of a spatial complex network. Background Art

[0002] With the acceleration of urbanization, the complex network of cities and their residents' lives presents a high degree of complexity and dynamic changes. The urban traffic complex network not only includes a large number of nodes and connections, but also its structure and function are full of complexity. Therefore, it is necessary to effectively extract the characteristics of these spatial complex networks in order to better provide important references for road and building planning. By analyzing and mining relevant feature information, the building layout in the urban road system can be effectively evaluated, thereby optimizing urban planning and improving the coordination of overall traffic and functions.

[0003] When evaluating a certain type of building in urban road planning based on complex networks, the data contained in the complex network often focuses on specific aspects such as the traffic system during the analysis process. However, relying solely on these traffic-related data is rather one-sided in the planning feasibility of buildings on urban roads, and cannot fully reflect the actual feature requirements of buildings; this limitation affects the accuracy and rationality of the evaluation of road building planning. Summary of the invention

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

[0005] An embodiment of the present application provides a method for extracting features of a spatial complex network, the method comprising:

[0006] S1: Obtain the building and its type information of each road node in the urban traffic complex network, and all dynamic information within a preset time period;

[0007] S2: The road nodes where the buildings containing various types of information are located are taken as the target building nodes of various types of information, and based on the paths to the target building nodes, the reachable road nodes are obtained, the reachable paths are determined, the number of road nodes in each reachable path is analyzed, and the travel cost from each reachable road node to the target building node is obtained in combination with the distribution characteristics of the dynamic information of each reachable road node;

[0008] S3: according to the difference between the dynamic information of adjacent road nodes in each reachable path, combined with the travel cost, the influence trend of each reachable road node on the target building node of various types of information is obtained;

[0009] S4: clustering the influence trends of all reachable road nodes according to the influence trends of all reachable road nodes being influenced by the target building nodes of the same type of information;

[0010] S5: According to the influence trend of each reachable road node by the target building node of various types of information, combined with the clustering results, the feasibility evaluation index and feasibility evaluation results of the buildings of various types of information planned for each reachable road node are extracted.

[0011] The obtaining of the reachable road nodes is specifically as follows:

[0012] All paths with specified path lengths to target building nodes of various types of information are counted, and the road nodes passed by the paths are recorded as reachable road nodes.

[0013] The determining of the reachable path specifically involves intercepting the path from each reachable road node in all paths to the target building node.

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

[0015] Count 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 means of all dynamic information of each reachable road node within a preset time period are integrated to obtain a first dynamic mean;

[0017] Based on the average number of road nodes and the shortest path length corresponding to each reachable road node, combined with the first dynamic mean, 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 mean, and negatively correlated with the average number of road nodes.

[0018] The influence trend of each reachable road node on the target building node of various types of information is obtained as follows:

[0019] The preset time period is evenly divided to obtain a local time period; on each reachable path, according to the difference between the dynamic information of adjacent road nodes, the attraction degree of the target building node of each type of information to each reachable road node in each local time period is obtained;

[0020] The average value of the attraction degree of the target building nodes of each type of information to each reachable road node in 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 reachable road node by the target building nodes of various types of information.

[0021] The attraction degree of the target building node that obtains each type of information to each reachable road node in each local time period is specifically:

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

[0023] According to the distribution difference of dynamic information in each local time period between road nodes, the dynamic difference between road nodes is obtained;

[0024] Set the target building node O i,k The attraction degree of each local time period of the jth accessible road node is recorded as w j,(i,k) , its formula form is: Where ΔA (i,k),j,s (r, r-1) represents the distance from the jth reachable road node to the target building node O i,k The dynamic difference between the rth road node and the r-1th road node in the sth reachable path in each local time period; n (i,k),j,s Represents the jth reachable road node to the target building node O i,k The number of road nodes in the sth reachable path; m (i,k),j Represents the jth 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] Wherein, obtaining the dynamic difference between road nodes includes:

[0026] The means of all dynamic information in each local time period of each road node are fused to obtain a second dynamic mean; the difference between the second dynamic means between road nodes is calculated to obtain a dynamic difference.

[0027] The clustering of the influence trends of all reachable road nodes is specifically as follows:

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

[0029] The specific formula for extracting the feasibility evaluation index of the building of various types of information planned for each reachable road node is:

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

[0031] The feasibility assessment results are as follows:

[0032] When the feasibility evaluation index of each type of building information planned at each reachable road node is greater than a preset evaluation threshold, the corresponding reachable road node is used as a planning node for the building information of each type.

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

[0034] The present application first obtains the building and its type information of each road node in the complex network of urban traffic, and all dynamic information within a preset time period, which is helpful for the subsequent analysis of the type and distribution of the buildings at each road node, and can better plan the road network; the number of road nodes in each reachable path is analyzed, and the travel cost from each reachable road node to the target building node is obtained in combination with the distribution characteristics of the dynamic information of each reachable road node. The beneficial effect is that by combining the analysis of the reachable path, the number of nodes and their travel cost, the demand characteristics of the building type in certain areas of the city are more accurately extracted, and the rationality of the planning analysis is improved; further, according to the difference between the dynamic information of adjacent road nodes in each reachable path, combined with the travel cost, the influence trend of each reachable road node by the target building node is obtained, and the beneficial effect is that by analyzing the difference in dynamic information of adjacent road nodes, which roads will be accurately identified that will be affected by the attraction of the target building, resulting in increased traffic pressure; according to the influence trend of all reachable road nodes by the target building node of the same type of information, the influence trend of all reachable road nodes is clustered, and the beneficial effect is to avoid the superposition effect of the same type of buildings when affecting the road nodes, and improve the accuracy and rationality of evaluating buildings of various types of information planned for road nodes. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0036] Figure 2 Flowchart for obtaining the feasibility assessment index provided for this application. DETAILED DESCRIPTION

[0037] In the description of the embodiments of the present application, words such as "exemplary", "or", "for example" and the like are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of 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" and the like is intended to present related concepts in a concrete manner.

[0038] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art in the present application. The terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application.

[0039] It should also be noted that the terms "first" and "second" in this application and its drawings are used to distinguish similar objects, rather than to describe a specific order or sequence. The method disclosed in the embodiments of the present application or the method shown in the flow chart includes 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 with each other, and some steps can also be deleted.

[0040] Unless defined otherwise, 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.

[0041] This application proposes a spatial complex network feature extraction method, which is applied to the field of data processing technology. Figure 1 , the method comprises the following steps:

[0042] S1: Obtain the building and its type information of each road node in the complex urban traffic network, and all dynamic information within a preset time period.

[0043] This application extracts the characteristics of spatial complex networks and obtains the feasibility assessment results of planning buildings of various types of information on each urban road. When constructing the topological structure of the urban traffic complex network, the dual topology method is adopted. This method regards urban roads as nodes in the network, and road intersections as edges connecting nodes, thereby abstracting the overall structure of the urban traffic network. Through remote sensing data, relevant information about urban roads and various types of buildings can be extracted, and then the ArcGIS platform can be used for data analysis.

[0044] When constructing a complex urban traffic network, simply relying on the distance between road nodes to calculate the average path length may not fully reflect the actual situation of the network. In actual situations, the attribute characteristics of road nodes usually include some static information and dynamic information. Static information includes buildings and their types. This application uses the ArcGIS platform to extract the building and type information of each road node; dynamic information includes pedestrian and vehicle traffic on the road. This application uses digital twin technology to obtain pedestrian and vehicle traffic data for each road every hour in a month. The time length and time interval for obtaining dynamic information can be adjusted by the implementer according to the actual situation, and this application does not limit 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, obtain the reachable road nodes based on the path to the target building nodes, determine the reachable paths, 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 on the planning of various buildings on urban roads based on the urban traffic complex network, the data contained in the urban traffic complex network, especially the traffic system-related data, often cannot fully reflect the actual situation of the spatial location when mining demand characteristics. This limitation may affect the reference value and accuracy of traffic data in the planning process of buildings, thereby reducing the reliability of the evaluation results.

[0047] For buildings with a certain type of information, they will have a positive promoting effect on the actual residents, pedestrians, and vehicles within a certain range around them, that is, they will drive the people and vehicles around them to move to this type of building in a specific time period and drive the development of other surrounding industries; therefore, the road node where the building containing the i-th type of information is located can be extracted, and the influence range of each road node where the building containing the i-th type of information is located can be judged based on the dynamic information performance of the extracted road node and its surrounding road nodes, and finally the influence of the current road node on other road nodes can be judged.

[0048] According to the characteristics of the complex urban traffic network, any two road nodes are connected by an edge, and the corresponding average path length is the shortest path distance between the two roads; specifically, the kth road node where the building containing the i-th type information is located is taken as the target building node O i,k, set the number of road nodes that the path passes through, and count the path of the kth road node where the building containing the i-th type information is located. It should be noted that adjacent road nodes in the path have a connection relationship in the complex network of urban traffic, and each road node corresponds to more than one path. For any two different paths of the same road node, there is at least one different road node. In this embodiment, the number of road nodes that the path passes through is set to 10, and the implementer can adjust it according to the actual situation.

[0049] Buildings containing certain types of information usually have an attractive effect on the surrounding people and vehicles, and this attraction tends to gradually weaken with increasing distance. This is because as the distance increases, the cost of travel increases, making people and vehicles more inclined to choose areas closer to the destination. Therefore, the attraction of the central node usually exhibits the characteristics of distance attenuation.

[0050] For a building containing the i-th type information, since it has an attractive effect on people and traffic within a certain range around it, and as the distance from different outer road nodes to the road node where the building is located increases, its attraction ability gradually decreases; all road nodes in the path of each road node where the building containing the i-th type information is located are recorded as reachable road nodes, the path from each reachable road node in all paths to the target building node is intercepted and recorded as a reachable path, and the average number of road nodes passed by the corresponding reachable path is counted; the shortest path length from each reachable road node to the target building node is calculated; the mean of all dynamic information within a preset time period of each reachable road node is fused to obtain a first dynamic mean; based on the average number of road nodes corresponding to each reachable road node and the shortest path length, combined with the first dynamic mean, 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 dynamic mean, and negatively correlated with the average number of road nodes.

[0051] It should be noted that a positive correlation refers to a relationship in which as one variable increases, another variable also increases; a negative correlation refers to a relationship in which as one variable increases, another variable decreases.

[0052] Specifically, the jth reachable road node is connected to the target building node O i,k The travel cost is denoted as μ j,i,k , its formula form is: Among them, d j,(i,k) Represents the jth reachable road node to the target building node O i,k The average path length of n j,(i,k) Represents the jth reachable road node to the target building node O i,kThe mean number of nodes; It represents the dynamic mean of the jth reachable road node, that is, the cumulative sum of the means of all dynamic information within the preset time period, which is used to measure the result of the fusion of the means of all dynamic information of the reachable road nodes.

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

[0054] S3: According to the difference between the dynamic information of adjacent road nodes in each reachable path and in combination with the travel cost, the influence trend of each reachable road node on the target building node of various types of information is obtained.

[0055] Since the attraction usually tends to increase gradually toward the target building node, when analyzing the accessible paths from each accessible road node to the target building node, if the vehicle flow or pedestrian flow between adjacent road nodes along the path toward the target building node shows a significant upward trend, this indicates that the target building node has a higher degree of attraction to each accessible road node.

[0056] The preset time period is evenly divided to obtain each local time period; in this embodiment, the local time period is set to one day; the implementer can adjust it according to the actual situation. On each reachable path from each reachable road node to the target building node, according to the difference between the dynamic information of adjacent road nodes, the attraction degree of the target building node of each type of information to each reachable road node in each local time period is obtained: the target building node O i,k The attraction degree of each local time period of the jth accessible road node is recorded as w j,(i,k) , its formula form is: Among them, ΔA (i,k),j,s (r, r-1) represents the distance from the jth reachable road node to the target building node O i,k The dynamic difference between the rth road node and the r-1th road node in the sth reachable path in each local time period; n (i,k),j,s Represents the jth reachable road node to the target building node O i,k The number of road nodes in the sth reachable path; m (i,k),j Represents the jth reachable road node to the target building node O i,k The number of reachable paths; ε is a preset value greater than zero, and the value is 0.01. The dynamic difference is specifically: accumulating the means of all dynamic information in each local time period of each road node to obtain a second dynamic mean; calculating the difference of the second dynamic means between road nodes to obtain the dynamic difference.

[0057] By accumulating the sum of the dynamic information differences between adjacent nodes in all reachable paths corresponding to two road nodes and the sum of the absolute values ​​of their differences, the degree of attraction of the target building node to each reachable road node is obtained. The value range is [-1,1]. The larger the value, the more obvious the increasing trend of the dynamic information as the path distance increases, which further indicates that the target building node has a stronger attraction to the road node.

[0058] Since dynamic information fluctuates to a certain extent in different time periods, the degree of attraction of the target building nodes to each reachable road node in all time periods is combined with the travel cost to obtain the influence trend of each reachable road node under the target building nodes: the average value of the degree of attraction of the target building nodes of each type of information to each reachable road node in 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 jth accessible road node is recorded as P j,(i,k) , its formula form is: Among them, w j,(i,k),t Represents the target building node O i,k The attraction degree of the jth reachable road node in the tth local time period; T represents the number of all local time periods; μ j,(i,k) Represents the jth reachable road node to the target building node O i,k The cost of moving forward.

[0060] The smaller the travel cost of the target building node to each accessible road node, the lower the actual difficulty for residents to get from the accessible road node to the target building node. If the attraction of the target building node is strong, the tendency of the surrounding residents to move to the target building node will also increase. The greater the influence of the target building node on each accessible road node, the greater the tendency of the accessible road node to be affected by the target building node during the duration.

[0061] S4: Cluster the influence trends of all reachable road nodes according to the influence trends of all reachable road nodes being influenced by the target building nodes of the same type of information.

[0062] In a complex urban traffic network, even if multiple buildings are of the same type, the influence trend of the road node where the building is located on other road nodes may vary due to different factors such as reputation and habits of surrounding residents. Therefore, when evaluating buildings of various types of information at any road node, if the evaluation only relies on the influence of a single surrounding building of the same type, it may lead to inaccurate judgment.

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

[0064] In the actual clustering process, since each road node is affected by multiple road nodes, a road node often falls into the influence range of multiple seed points at the same time. At the same time, the irregularity of the complex urban traffic network may also cause some road nodes to be mistakenly divided into clusters corresponding to seed points that have less influence on them. In order to avoid this situation, it is necessary that during the clustering process, the influence of the seed point corresponding to the cluster of each road node is always greater than its influence on other seed points, so as to ensure that the road node is correctly classified into the most representative cluster. This method can obtain an irregular cluster structure, which can more accurately reflect the complex network 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: According to the influence trend of each reachable road node by the target building node of various types of information, combined with the clustering results, the feasibility evaluation index and feasibility evaluation results of the buildings of various types of information planned for each reachable road node are extracted.

[0066] When conducting feasibility assessments on buildings of various types of information planned for each reachable road node, if the reachable road node is less affected by the road nodes where buildings of the same type of information are located, the fewer road nodes are included in the clusters corresponding to each road node, and the smaller the influence range of each road node where buildings of the same type of information are located on other surrounding road nodes, the lower the influence weight on the reachable road node; and thus the greater the feasibility assessment result of the building of this type of information on the road node.

[0067] Based on this, according to the influence trend of each reachable road node on buildings of various types of information of different target building nodes, combined with the clustering results corresponding to buildings with the same type of information, the feasibility evaluation index of buildings of various types of information planned for each reachable road node is extracted, which is expressed as follows: Among them, f j,i K represents the feasibility evaluation index of the building with the i-th type of information planned at the j-th accessible road node; i represents the number of road nodes where the i-th type of information building is located, that is, the number of seed points corresponding to the i-th type of information building; g i,kThe number of road nodes in the cluster corresponding to the kth seed point where the building of the i-th type of information is located; P j,(i,k) represents the influence trend of the kth seed point where the building of type i is located on the jth accessible road node; norm() represents the normalization function, and this embodiment uses the sigmoid function for normalization. Among them, the feasibility evaluation index acquisition flow chart is as follows: Figure 2 shown.

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

[0069] Finally, the planning nodes corresponding to the 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] At this point, the feature extraction of spatial complex networks is completed.

[0071] The present application provides a spatial complex network feature extraction method, the method comprising: firstly obtaining the building and its type information of each road node in the urban traffic complex network, and all dynamic information within a preset time period, which is helpful for subsequent analysis of the type and distribution of the buildings at each road node, and can better plan the road network; analyzing the number of road nodes in each reachable path, combining the distribution characteristics of the dynamic information of each reachable road node, and obtaining the travel cost from each reachable road node to the target building node, the beneficial effect of which is that combining the analysis of the reachable path, the number of nodes and their travel cost, more accurately extracts the demand characteristics of the building type in certain areas of the city, and improves the rationality of the planning analysis; and further In the first step, according to the difference between the dynamic information of adjacent road nodes in each reachable path, combined with the travel cost, the influence trend of each reachable road node by the target building node is obtained, and its beneficial effect is that by analyzing the difference in dynamic information of adjacent road nodes, it is possible to accurately identify which roads will be affected by the attractiveness of the target building, resulting in increased traffic pressure; according to the influence trend of all reachable road nodes by the target building nodes of the same type of information, the influence trend of all reachable road nodes is clustered, and its beneficial effect is to avoid the superposition effect of the same type of buildings when affecting the road nodes, and improve the accuracy and rationality of evaluating buildings of various types of information in road node planning.

[0072] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two continuous operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

[0073] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A spatial complex network feature extraction method, characterized in that: The method comprises the following steps: S1: Obtain the building and its type information of each road node in the urban traffic complex network, and all dynamic information within a preset time period; S2: The road nodes where the buildings containing various types of information are located are taken as the target building nodes of various types of information, and based on the paths to the target building nodes, the reachable road nodes are obtained, the reachable paths are determined, the number of road nodes in each reachable path is analyzed, and the travel cost from each reachable road node to the target building node is obtained in combination with the distribution characteristics of the dynamic information of each reachable road node; S3: according to the difference between the dynamic information of adjacent road nodes in each reachable path, combined with the travel cost, the influence trend of each reachable road node on the target building node of various types of information is obtained; S4: clustering the influence trends of all reachable road nodes according to the influence trends of all reachable road nodes being influenced by the target building nodes of the same type of information; S5: According to the influence trend of each reachable road node by the target building node of various types of information, combined with the clustering results, the feasibility evaluation index and feasibility evaluation results of the buildings of various types of information planned for each reachable road node are extracted.

2. A spatial complex network feature extraction method as claimed in claim 1, characterized in that: The obtainment of the reachable road node is specifically as follows: All paths with specified path lengths to target building nodes of various types of information are counted, and the road nodes passed by the paths are recorded as reachable road nodes.

3. A spatial complex network feature extraction method as claimed in claim 1, characterized in that: The determining of the reachable path specifically involves intercepting the path from each reachable road node in all paths to the target building node.

4. A spatial complex network feature extraction method according to claim 1, characterized in that: The travel cost from each reachable road node to the target building node is obtained as follows: Count 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; The means of all dynamic information of each reachable road node within a preset time period are integrated to obtain a first dynamic mean; Based on the average number of road nodes and the shortest path length corresponding to each reachable road node, combined with the first dynamic mean, 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 mean, and negatively correlated with the average number of road nodes.

5. A spatial complex network feature extraction method according to claim 1, characterized in that: The influence trend of each reachable road node on the target building node of various types of information is obtained as follows: The preset time period is evenly divided to obtain a local time period; on each reachable path, according to the difference between the dynamic information of adjacent road nodes, the attraction degree of the target building node of each type of information to each reachable road node in each local time period is obtained; The average value of the attraction degree of the target building nodes of each type of information to each reachable road node in 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 reachable road node by the target building nodes of various types of information.

6. A spatial complex network feature extraction method as claimed in claim 5, characterized in that: The attraction degree of the target building node that obtains each type of information to each reachable road node in each local time period is specifically: The kth road node where the building containing the i-th type information is located is taken as the target building node O i,k ; According to the distribution difference of dynamic information in each local time period between road nodes, the dynamic difference between road nodes is obtained; Set the target building node O i,k The attraction degree of each local time period of the jth accessible road node is recorded as w j,(i,k) , its formula form is: Where ΔA (i,k),j,s (r, r-1) represents the distance from the jth reachable road node to the target building node O i,k The dynamic difference between the rth road node and the r-1th road node in the sth reachable path in each local time period; n (i,k),j,s Represents the jth reachable road node to the target building node O i,k The number of road nodes in the sth reachable path; m (i,k),j Represents the jth reachable road node to the target building node O i,k The number of reachable paths; ε is a preset value greater than zero.

7. A spatial complex network feature extraction method as claimed in claim 6, characterized in that: The obtaining of dynamic differences between road nodes includes: The means of all dynamic information in each local time period of each road node are fused to obtain a second dynamic mean; the difference between the second dynamic means between road nodes is calculated to obtain a dynamic difference.

8. A spatial complex network feature extraction method according to claim 1, characterized in that: The clustering of the influence trends of all reachable road nodes is specifically as follows: According to the two-dimensional plane distribution, the coordinate system of each road node is obtained; the density clustering method is used to cluster the target building nodes of various types of information as seed points to obtain the clusters corresponding to various sub-points.

9. A spatial complex network feature extraction method as claimed in claim 7, characterized in that: The specific formula for the feasibility evaluation index of the building for extracting various types of information planned for each reachable road node is: Among them, f j,i K represents the feasibility evaluation index of the building with the i-th type of information planned at the j-th accessible road node; i represents the number of target building nodes of the i-th type of information; g i,k The number of road nodes in the cluster corresponding to the kth seed point where the building of the i-th type of information is located; P j,(i,k) It represents the influence trend of the kth seed point where the building of the i-th type of information is located on the j-th reachable road node; norm() represents the normalization function.

10. A spatial complex network feature extraction method according to claim 1, characterized in that: The feasibility assessment results are specifically as follows: When the feasibility evaluation index of each type of building information planned at each reachable road node is greater than a preset evaluation threshold, the corresponding reachable road node is used as a planning node for the building information of each type.

Images