Public service facility blind area and low-efficiency area identification and facility adding method and system based on knowledge graph

Abstract

The invention discloses a public service facility blind area and low-efficiency area identification and facility addition method and system based on a knowledge graph, and the method comprises the steps: integrating the current data of a target city, constructing a target city graph which takes spatial form elements and current public service facility elements as entities, and takes a spatial distance as a relation; and screening out a service range sub-graph of each public service facility based on the target city map, and further identifying a service blind area and a low-efficiency area. In addition, for service blind areas and low-efficiency areas, entity nodes in the sub-graphs are intelligently screened according to multi-dimensional elements to serve as newly-added facility site selection points, and results are interactively displayed. According to the method, the multi-dimensional knowledge graph is constructed, so that the relevance characteristics between each element of the crowd and the space and the service facilities can be accurately grasped, and the service blind area and the low-efficiency area can be more scientifically and objectively identified. And meanwhile, the comprehensive site selection credibility based on the multi-dimensional elements is higher, the sub-item site selection optimization is more comprehensive, and the formed three-dimensional interactive display is more stereoscopic and visual.

Description

Technical Field

[0001] The present invention relates to a method and system for identifying blind spots and inefficient areas of public service facilities and adding facilities based on knowledge graphs, and belongs to the field of knowledge graphs and geographic information processing. Background Art

[0002] Public service facilities (cultural facilities, educational and scientific research facilities, medical and health care facilities, etc.) play an important role in improving the quality of life of residents, optimizing resource allocation and promoting sustainable urban development. By comprehensively analyzing the diverse needs and complex structures within the city, we can achieve optimal resource allocation and promote the continuous optimization and improvement of the urban public service system.

[0003] At present, most public service facility site selection studies rely on indicators such as supply and demand, accessibility, etc. for analysis and decision-making. However, due to the complexity and diversity of factors involved in the site selection of public service facilities, commonly used model algorithms, such as K-means clustering and shortest path algorithm, rely on some indicators to layout and site facilities, and it is difficult to fully consider multidimensional factors and complex urban structures. As a result, the scientificity and efficiency of the site selection of public service facilities are limited, and it is difficult to fully solve practical problems. Summary of the invention

[0004] Purpose of the invention: To address the deficiencies mentioned in the above background technology, the first purpose of the present invention is to provide a method and system for identifying blind spots and inefficient areas of public service facilities based on knowledge graphs, which can integrate current urban data through knowledge graphs, identify service blind spots and inefficient areas of newly added public service facilities, and understand the current situation more objectively and accurately. The second purpose of the present invention is to provide a method and system for adding public service facilities based on knowledge graphs, which can intelligently recommend new facility site selection points for identified service blind spots and inefficient areas and interactively display them, thereby improving the scientificity and efficiency of site selection for public service facilities.

[0005] Technical solution: The purpose of the present invention can be achieved through the following technical solution:

[0006] In a first aspect, the present invention provides a method for identifying blind spots and inefficient areas of public service facilities based on a knowledge graph, the method comprising the following steps:

[0007] Obtain the current status data of the target city, including urban spatial form and spatial location data, current public service facilities data, and crowd activity data in blocks; take spatial form elements and current public service facilities elements as entities of the knowledge graph, and the spatial distance between entities as relationships, to construct the target city graph;

[0008] Based on the constructed target city map, the path length from each public service facility entity to all other spatial morphological element entities is calculated, and entities whose path length is less than the service scope of the public service facility are selected as the service scope subgraph of each public service facility;

[0009] Identify all entities not covered by the service scope submap of public service facilities and mark them as service blind spots. The corresponding entities and relationships constitute the current facility service blind spot submap;

[0010] In the service scope submap of each public service facility, the total population corresponding to the block entities contained therein is calculated, and the submaps with a population greater than the corresponding facility service carrying capacity are identified and marked as areas with inefficient current facility services.

[0011] Furthermore, the construction of the target city map includes:

[0012] First, the atlas model layer is constructed, and the entities are defined as spatial morphological elements and current public service facilities. The entity relationship is defined as the spatial distance between entities. The entity attributes of spatial morphological elements are defined as their spatial morphology, spatial location and population. The entity attribute values ​​of spatial morphological elements are area, perimeter, shape index, longitude and latitude of the geometric center and population. The entity attributes of current public service facilities are their service scope and service carrying capacity. The entity attribute values ​​of public service facilities are the radius of their service scope and the maximum number of people they can carry.

[0013] Secondly, we build a graph data layer, clean the data and organize it into a structured data format of "entity-relationship-entity" and "entity-attribute-attribute value" triplets;

[0014] Finally, using the knowledge graph operating system, the structured triples in the data layer are imported into the system, and the target city graph is established according to the rules defined in the pattern layer.

[0015] Furthermore, the path length calculation method from each public service facility entity to all other spatial morphological element entities is as follows: based on the GIS platform, a road network topology structure is established by importing road network data, and the shortest path algorithm is used. With the public service facility entity as the starting point and other spatial morphological element entities as the end point, the path length from the public service facility entity to other spatial morphological element entities is calculated.

[0016] In a second aspect, the present invention provides a method for adding public service facilities based on a knowledge graph. After obtaining the blind spots and inefficient areas of public service facilities based on the knowledge graph, the method comprises the following steps:

[0017] In view of the blind spots of existing facilities, four types of entity nodes in the subgraph of the blind spots of existing facilities are selected as the site selection points of new facilities according to demand, influence, accessibility and comprehensiveness; among them, the block with the highest average number of daily active people is taken as the demand entity node; the node with the largest eigenvector centrality is taken as the influence entity node; the node with the shortest average path to each block is taken as the accessibility entity node; the AHP hierarchical analysis method is used to take the point with the highest comprehensive value as the comprehensive entity node;

[0018] For the inefficient service area of ​​existing facilities, the same method is used to screen four types of entity nodes from the service range subgraph of the corresponding public service facilities to determine the spatial relationship between the entity node and the existing public service facilities. If the entity node is located in the same block as the existing public service facilities or the distance is less than the set value, the entity node is deleted and the second-ranked entity node is selected for re-determination until the spatial position relationship conditions are met. The entity node that meets the conditions is used as the site selection point for the new facility in the inefficient service area of ​​existing facilities.

[0019] The constructed target city map and the geographic coordinates of its nodes are used for three-dimensional spatial mapping, and a three-dimensional sand table is formed in combination with the three-dimensional model of the target city. The four types of facility site selection points and related calculation results obtained are interactively displayed in different colors. Users determine the final location of public service facilities through interactive selection and operation.

[0020] Furthermore, the screening method of the four types of entity nodes includes:

[0021] Combined with the crowd activity data collected by video probes for multiple consecutive days, the average number of people active in each block is calculated, and the block entity node with the highest average number of people active in each block is marked as the demand entity node;

[0022] The eigenvalue decomposition algorithm is used to calculate the eigenvector centrality of each node in the subgraph, and the entity node with the largest eigenvector centrality is taken as the influential entity node. The eigenvector centrality formula is calculated as follows:

[0023]

[0024] Among them, C(i) represents the feature centrality of entity node i, λ is the maximum eigenvalue of the adjacency matrix, N(i) represents the set of neighboring entity nodes of entity node i in the subgraph, and A ij It represents the connection weight between entity node i and entity node j in the adjacency matrix. The connection weight is set as the ratio of the product of the degrees of adjacent nodes to the sum of the degrees of all nodes, which reflects the connection activity of the nodes.

[0025] The Dijkstra algorithm is used to calculate the path length from each node in the subgraph to all blocks, and the average value of the path length is calculated. The entity node with the shortest path average value is selected as the reachability entity node;

[0026] Using the AHP hierarchical analysis method, the weights of influence, accessibility and demand are determined, and the comprehensive calculation formula is as follows:

[0027] S i =ω1v 1i +ω2ν 2i +ω3ν 3i

[0028] Among them, ω1, ω2, and ω3 represent the weights of influence, accessibility, and demand, respectively, and ν 1i , ν 2i , ν 3i are the scores of entity node i under the three criteria of influence, accessibility, and demand, and then the entity node with the highest comprehensive value is selected as the comprehensive entity node.

[0029] In a third aspect, the present invention provides a system for identifying blind spots and inefficient areas of public service facilities based on a knowledge graph, comprising:

[0030] The target city map construction module is used to obtain the current status data of the target city, including urban spatial form and spatial location data, current public service facilities data, and crowd activity data in blocks; the spatial form elements and current public service facilities elements are used as entities of the knowledge map, and the spatial distance between entities is used as a relationship to construct the target city map;

[0031] The service scope subgraph screening module of the public service facilities is used to calculate the path length from each public service facility entity to all other spatial morphological element entities based on the constructed target city map, and screen entities whose path length is less than the service scope of the public service facilities as the service scope subgraph of each public service facility;

[0032] A service blind spot identification module is used to identify all entities not covered by the service scope submap of public service facilities and mark them as service blind spots. The corresponding entities and relationships constitute the current facility service blind spot submap;

[0033] And a service inefficiency area identification module is used to calculate the total population corresponding to the block entities contained in the service range submap of each public service facility, identify the submaps with a population greater than the corresponding facility service carrying capacity and mark them as current facility service inefficiency areas.

[0034] In a fourth aspect, the present invention provides a public service facility addition system based on a knowledge graph, including the modules in the public service facility blind spot and inefficient area identification system based on a knowledge graph, and:

[0035] The service blind spot facility addition module is used to select four types of entity nodes in the service blind spot subgraph of the existing facilities as the site selection points for new facilities according to the demand, influence, accessibility and comprehensiveness for the existing facilities service blind spots; among them, the block with the highest average number of daily active people is taken as the demand entity node; the node with the largest eigenvector centrality is taken as the influence entity node; the node with the shortest average path to each block is taken as the accessibility entity node; and the AHP hierarchical analysis method is used to take the point with the highest comprehensive value as the comprehensive entity node;

[0036] The module for adding facilities in service inefficient areas is used to select four types of entity nodes from the service range subgraph of the corresponding public service facilities in the same way for the service inefficient areas of existing facilities, and judge the spatial relationship between the entity nodes and the existing public service facilities. If the entity nodes are located in the same block as the existing public service facilities or the distance is less than the set value, the entity nodes are deleted, and the entity nodes in the second order are selected for judgment again until the spatial position relationship conditions are met, and the entity nodes that meet the conditions are used as the site selection points for new facilities in the service inefficient areas of existing facilities;

[0037] The interactive display module is used to use the constructed target city map and the geographic coordinates of its nodes to perform three-dimensional spatial mapping, and combine the three-dimensional model of the target city to form a three-dimensional sand table; the four types of facility site selection points and related calculation results obtained by screening are interactively displayed in different colors; users determine the final location of public service facilities through interactive selection and operation.

[0038] In a fifth aspect, the present invention provides a computer system comprising a memory, a processor, and a computer program / instructions stored in the memory and executable on the processor, wherein the computer program / instructions, when executed by the processor, implement the steps of the method for identifying blind spots and inefficient areas of public service facilities based on the knowledge graph, or the steps of the method for adding public service facilities based on the knowledge graph.

[0039] In a sixth aspect, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method for identifying blind spots and inefficient areas of public service facilities based on a knowledge graph, or the steps of the method for adding public service facilities based on a knowledge graph.

[0040] In a seventh aspect, the present invention provides a computer program product, including a computer program / instructions, which, when executed by a processor, implement the steps of the method for identifying blind spots and inefficient areas of public service facilities based on a knowledge graph, or the steps of the method for adding public service facilities based on a knowledge graph.

[0041] Beneficial effects: Compared with the prior art, the present invention has the following advantages:

[0042] 1. The present invention helps to accurately grasp the correlation characteristics between urban population and spatial elements and public service facilities by constructing a multi-dimensional knowledge graph of the target city. It can not only identify the service blind spots of public service facilities, but also identify service inefficient areas by combining the facility carrying capacity with the corresponding population size, making the identification process more comprehensive.

[0043] 2. The present invention can determine possible facility site selection points through crowd activity data collected by video, accessibility data obtained by various algorithms, and other data, solving the problem of large errors in traditional facility site selection based on partial indicators, making the entire process more objective, intelligent, and automated.

[0044] 3. The present invention conducts intelligent site selection for public service facilities based on knowledge graphs, and performs interactive selection and optimization through a three-dimensional sandbox to obtain a relatively optimal solution, which is 300% faster than the traditional manual site selection method.

[0045] 4. The present invention refines the conceptual site selection guidance such as traditional pictures and texts by interactively displaying the final facility site selection and outputting a site selection list. At the same time, it cooperates with the three-dimensional city model to make the subsequent site selection process more intuitive, efficient and controllable, and more instructive for specific projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a flow chart of the method of embodiment 1 of the present invention.

[0047] Figure 2 It is a flow chart of the method of embodiment 2 of the present invention.

[0048] Figure 3 It is a flow chart of the method of embodiment 3 of the present invention.

[0049] Figure 4 This is a schematic diagram of the shortest path algorithm. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] Example 1

[0052] like Figure 1 As shown, a method for identifying blind spots and inefficient areas of public service facilities based on a knowledge graph disclosed in an embodiment of the present invention includes the following steps:

[0053] Step S101, obtain the current status data of the target city, including urban spatial form and spatial location data, current public service facilities data and crowd activity data in blocks; take spatial form elements and current public service facilities elements as entities of the knowledge graph, and the spatial distance between entities as relationships, to construct a target city graph.

[0054] Specifically, the construction of the target city map includes:

[0055] First, the atlas model layer is constructed, and the entities are defined as spatial morphological elements and current public service facilities. The entity relationship is defined as the spatial distance between entities. The entity attributes of spatial morphological elements are defined as their spatial morphology, spatial location and population. The entity attribute values ​​of spatial morphological elements are area, perimeter, shape index, longitude and latitude of the geometric center and population. The entity attributes of current public service facilities are their service scope and service carrying capacity. The entity attribute values ​​of public service facilities are the radius of their service scope and the maximum number of people they can carry.

[0056] Secondly, we build a graph data layer, clean the data and organize it into a structured data format of "entity-relationship-entity" and "entity-attribute-attribute value" triplets;

[0057] Finally, using the knowledge graph operating system, the structured triples in the data layer are imported into the system, and the target city graph is established according to the rules defined in the pattern layer.

[0058] Step S102: Based on the constructed target city map, calculate the path length from each public service facility entity to all other spatial morphological element entities, and filter out entities whose path length is less than the service scope of the public service facility as the service scope subgraph of each public service facility.

[0059] Specifically, the path length from each public service facility entity to all other spatial morphological element entities is calculated as follows: based on the GIS platform, the road network topology structure is established by importing road network data, and the shortest path algorithm is used. The public service facility entity is used as the starting point and other spatial morphological element entities are used as the end point to calculate the path length from the public service facility entity to other spatial morphological element entities.

[0060] Step S103: Identify all entities not covered by the service scope subgraph of the public service facility and mark them as service blind spots. The corresponding entities and relationships constitute the current facility service blind spot subgraph.

[0061] Step S104: In the service range sub-graph of each public service facility, the total population corresponding to the block entities contained therein is calculated, and the sub-graphs with a population greater than the corresponding facility service carrying capacity are identified and marked as areas of inefficient current facility service.

[0062] Example 2

[0063] like Figure 2 As shown, a method for adding public service facilities based on knowledge graph disclosed in an embodiment of the present invention recommends new facility site selection points for service blind spots and service inefficiency areas after the existing facility service blind spots and service inefficiency areas in embodiment 1, and interactively optimizes and outputs the facility site selection results. Specifically, the following steps are included:

[0064] Step S201: For the existing facility service blind spots, four types of entity nodes in the existing facility service blind spot subgraph are selected as the site selection points for new facilities according to demand, influence, accessibility and comprehensiveness; among them, the block with the highest average number of daily active people is taken as the demand entity node; the node with the largest eigenvector centrality is taken as the influence entity node; the node with the shortest average path value to each block is taken as the accessibility entity node; and the AHP hierarchical analysis method is used to take the point with the highest comprehensive value as the comprehensive entity node.

[0065] Specifically, the screening methods of the above four types of entity nodes include:

[0066] Combined with the crowd activity data collected by video probes for multiple consecutive days, the average number of people active in each block is calculated, and the block entity node with the highest average number of people active in each block is marked as the demand entity node;

[0067] The eigenvalue decomposition algorithm is used to calculate the eigenvector centrality of each node in the subgraph, and the entity node with the largest eigenvector centrality is taken as the influential entity node. The eigenvector centrality formula is calculated as follows:

[0068]

[0069] Among them, C(i) represents the feature centrality of entity node i, λ is the maximum eigenvalue of the adjacency matrix, N(i) represents the set of neighboring entity nodes of entity node i in the subgraph, and A ij It represents the connection weight between entity node i and entity node j in the adjacency matrix. The connection weight is set as the ratio of the product of the degrees of adjacent nodes to the sum of the degrees of all nodes, which reflects the connection activity of the nodes.

[0070] The Dijkstra algorithm is used to calculate the path length from each node in the subgraph to all blocks, and the average value of the path length is calculated. The entity node with the shortest path average value is selected as the reachability entity node;

[0071] Using the AHP hierarchical analysis method, the weights of influence, accessibility and demand are determined, and the comprehensive calculation formula is as follows:

[0072] S i =ω1v 1i +ω2v 2i +ω3v 3i

[0073] Among them, ω1, ω2, and ω3 represent the weights of influence, accessibility, and demand, respectively, and v 1i 、v 2i 、v 3i are the scores of entity node i under the three criteria of influence, accessibility, and demand, and then the entity node with the highest comprehensive value is selected as the comprehensive entity node.

[0074] Step S202: For the area with inefficient service of existing facilities, the same method is used to screen four types of entity nodes from the service range subgraph of the corresponding public service facilities, and the spatial relationship between the entity node and the existing public service facility is determined. If the entity node is located in the same block as the existing public service facility or the distance is less than the set value, the entity node is deleted, and the entity node in the second order is selected for re-determination until the spatial position relationship conditions are met. The entity node that meets the conditions is used as the site selection point for new facilities in the area with inefficient service of existing facilities.

[0075] Step S203: Use the constructed target city map and the geographic coordinates of its nodes to perform three-dimensional spatial mapping, and combine the three-dimensional model of the target city to form a three-dimensional sand table; interactively display the four types of facility site selection points and related calculation results obtained in different colors; users determine the final site selection of public service facilities through interactive selection and operation.

[0076] Example 3

[0077] like Figure 3As shown, the embodiment of the present invention takes Nanjing as an example to explain in detail the detailed implementation process of the method for identifying blind spots and inefficient areas of public service facilities and adding facilities based on the knowledge graph. The specific steps are as follows:

[0078] Step S301, Nanjing city data acquisition and graph construction. Obtain the current data of Nanjing, and integrate the spatial form and spatial location data, crowd activity data, and current public service facility data of Nanjing. Take the spatial form elements and current public service facility elements as entities of the knowledge graph, and the spatial distance between entities as the relationship, and construct the Nanjing city graph through the knowledge graph operating system.

[0079] The details are as follows: obtain the current status data from the Nanjing Urban Planning Bureau, and the current status data includes: Nanjing urban spatial form and spatial location data, crowd activity data, and current public service facility data. Among them, Nanjing urban spatial form and spatial location data include: spatial form and spatial location including blocks, plots, buildings, roads, transportation hubs, mountains, and water bodies. Crowd activity data include: block population data, and current public service facility data include: service scope, service carrying capacity and spatial location of public service facilities. Then start to build the Nanjing city map. First, build the map model layer. Define the entity as the spatial form elements and current public service facilities in the planning site data, define the entity relationship as the spatial distance between entities, define the entity attributes of the spatial form elements as their spatial form, spatial location and population, and the entity attribute values ​​of the spatial form elements are area, perimeter, shape index, longitude and latitude of the geometric center and population. The entity attributes of the current public service facilities are their service scope and service carrying capacity. The entity attribute values ​​of public service facilities are the radius size of their service scope and the maximum number of people they can carry. Among them, the spatial form elements include blocks, plots, buildings, roads, transportation hubs, mountains, and water bodies. The spatial distance between the entities is calculated and generated based on the GIS platform through the analysis of road network data and current public service facilities data. The service radius size and the maximum number of people that the public service facilities can carry refer to the "Urban Public Service Facilities Planning Standard" (GB50442-2008), and the specific numerical values ​​are determined according to the category and level of the public service facilities. Secondly, a graph data layer is constructed. The planned site data and the current public service facilities data are cleaned, and the cleaned data are organized into a structured data format of triples. The triple structure is "entity-relationship-entity" and "entity-attribute-attribute value". Finally, the knowledge graph operating system is used to import the structured triples in the data layer into the system, and the target city graph is established according to the rules defined in the model layer.

[0080] Step S302, identification of blind spots and inefficient service areas of existing facilities. For the Nanjing city map constructed in step one, use the DGX computer workstation to calculate the path length from each public service facility entity to all other spatial morphological element entities, and select nodes whose path length is less than the standard service range of the facility as the service range subgraph of each public service facility. Identify all nodes not covered by the subgraph and mark them as service blind spots. The method for calculating the path length from each public service facility entity to all other spatial morphological element entities is based on the GIS platform, and a road network topology is established by importing road network data, and a shortest path algorithm (such as Figure 4 ), taking the public service facility entity as the starting point and other spatial morphological elements as the end point, calculate the path length from the public service facility entity to other spatial morphological element entities. In each public service facility service range subgraph, calculate the sum of the population corresponding to the block nodes it contains, identify the subgraphs with a population greater than the service carrying capacity of the facility and mark them as service inefficiency areas.

[0081] The details are as follows: for the Nanjing city map constructed in step 1, based on the GIS platform, the road network topology is established by importing road network data, and the shortest path algorithm is used. The public service facility entity is taken as the starting point and other spatial morphological elements are taken as the end point to calculate the path length from the public service facility entity to other spatial morphological element entities. Entities whose path length is less than the service range radius of each existing public service facility are screened, and the screened entity set is marked as the service range subgraph of the public service facility. All entity sets not covered by the service range subgraph of the public service facility are marked as the current facility service blind spot. The corresponding entities and relationships constitute the current facility service blind spot subgraph. Then, the service range subgraph of each public service facility is used to screen the block entities within the service range, extract the population quantity attribute of the block entity, calculate the sum of the population quantity corresponding to all block entities, and refer to the "Urban Public Service Facility Planning Standards". If the sum of the population quantity in the subgraph is greater than the service carrying capacity attribute of the public service facility, the subgraph of the public service facility is marked as the current facility service inefficiency area.

[0082] Step S303, site selection for new facilities in service blind spots and service inefficiency areas. For the service blind spots in step 2, four types of entity nodes in the subgraph are selected as site selection points for new facilities based on demand, influence, accessibility, and comprehensiveness. Among them, the block with the highest average number of daily active people is taken as the demand entity node; the node with the largest eigenvector centrality calculated by the eigenvalue decomposition algorithm is taken as the influence entity node; the node with the shortest average path value to each block calculated by the Dijkstra algorithm is taken as the accessibility entity node; and the point with the highest comprehensive value is taken as the comprehensive entity node using the AHP hierarchical analysis method. The above four types of entity nodes are used as site selection points for new facilities in the service blind spots of existing facilities. For the service inefficiency area in step 2, repeat the above steps to select four types of nodes, determine the spatial relationship between the node and the existing public service facilities, and if it is located in the same block as the existing public service facilities or the distance is less than 100 meters, delete the node, select the node in the second place instead, and use the entity node as the site selection point for new facilities in the service inefficiency area of ​​existing facilities.

[0083] The details are as follows: For the blind spots of existing facility services in step 2, four types of entity nodes in the subgraph are selected as the site selection points for new facilities based on demand, influence, accessibility, and comprehensiveness.

[0084] Combined with the block crowd activity data collected by video probes for seven consecutive days, the average number of active people per day in each block is calculated, and the block entity node with the highest average number of active people per day is marked as the demand entity node;

[0085] The eigenvalue decomposition algorithm is used to calculate the eigenvector centrality of each node in the current facility service blind spot map, and the entity node with the largest eigenvector centrality is used as the influential entity node. The eigenvector centrality formula is calculated as follows:

[0086]

[0087] Among them, N(i) represents the set of neighboring entity nodes of entity node i in the current facility service blind spot graph, A ij Represents the connection weight between entity node i and entity node j in the adjacency matrix. The Dijkstra algorithm is used to calculate the path length from each node to all blocks in the current facility service blind spot subgraph, and the average path length is calculated. The entity node with the shortest path average value is selected as the accessibility entity node. The AHP hierarchical analysis method is used to compare the importance of influence, accessibility and demand based on the expert scoring results, and a pairwise comparison matrix of the criterion layer is constructed. For each comparison matrix, the eigenvector is calculated and normalized to obtain the weight vector. The consistency ratio CR is calculated. If CR is less than 0.1, the consistency test is passed; otherwise, the comparison matrix needs to be readjusted. The final comprehensive calculation formula is as follows:

[0088] S i =ω1v 1i +ω2v 2i +ω3v 3i

[0089] Among them, ω1, ω2, and ω3 represent the weights of influence, accessibility, and demand, respectively, and v 1i 、v 2i 、v 3i are the weights of entity node i under the three criteria of influence, accessibility, and demand, and then the entity node with the highest comprehensive value is selected as the comprehensive entity node. The above four types of entity nodes are used as the site selection points for new facilities in the blind spots of existing facility services. Then, for the inefficient service area of ​​existing facilities in step 2, repeat step 3 to screen out four types of entity nodes, and judge the spatial position relationship between the entity node and the existing public service facilities. If the entity node and the existing public service facility are in the same block or the distance between the two is less than 100 meters, delete the entity node, and select the second-ranked entity node for judgment again until the spatial position relationship condition is met, and use the entity node as the site selection point for new facilities in the inefficient service area of ​​existing facilities.

[0090] Step S304, interactive optimization and output display of facility site selection results. Use the geographic coordinates of the Nanjing city map and its nodes constructed in step 1 to perform three-dimensional spatial mapping, and combine it with the three-dimensional model of Nanjing city to form a three-dimensional sand table. The four types of facility site selection points and related calculation results obtained in step 3 are interactively displayed in different colors. The user determines the final site selection of the public service facility through interactive selection and operation, and integrates the above content into a report and outputs it in word / excel format.

[0091] The details are as follows: Map the geographic coordinates of the Nanjing city map and its entity nodes constructed in step one in three-dimensional space, and combine them with the three-dimensional model of Nanjing city to form a three-dimensional sand table for Nanjing city. The site selection points for new facilities in the blind spots of existing facility services and the site selection points for new facilities in the inefficient service areas of existing facilities obtained in step three, as well as the relevant calculation results, are interactively displayed in different colors on the three-dimensional sand table for Nanjing city. The relevant calculation results include their demand, influence, accessibility, and comprehensive values ​​and percentages. Users make interactive selections and operations on the three-dimensional sand table for Nanjing city to determine the final site selection for public service facilities, and integrate the above content into a report to be output and printed in word / excel format.

[0092] Example 4

[0093] The embodiment of the present invention discloses a system for identifying blind spots and inefficient areas of public service facilities based on a knowledge graph, including:

[0094] The target city map construction module is used to obtain the current status data of the target city, including urban spatial form and spatial location data, current public service facilities data, and crowd activity data in blocks; the spatial form elements and current public service facilities elements are used as entities of the knowledge map, and the spatial distance between entities is used as a relationship to construct the target city map;

[0095] The service scope subgraph screening module of the public service facilities is used to calculate the path length from each public service facility entity to all other spatial morphological element entities based on the constructed target city map, and screen entities whose path length is less than the service scope of the public service facilities as the service scope subgraph of each public service facility;

[0096] A service blind spot identification module is used to identify all entities not covered by the service scope submap of public service facilities and mark them as service blind spots. The corresponding entities and relationships constitute the current facility service blind spot submap;

[0097] And a service inefficiency area identification module is used to calculate the total population corresponding to the block entities contained in the service range submap of each public service facility, identify the submaps with a population greater than the corresponding facility service carrying capacity and mark them as current facility service inefficiency areas.

[0098] This embodiment and Embodiment 1 are based on the same inventive concept, and specific details are shown in Embodiment 1, which will not be described in detail.

[0099] Example 5

[0100] The embodiment of the present invention discloses a system for adding public service facilities based on a knowledge graph, including the modules in Embodiment 4, as well as:

[0101] The service blind spot facility addition module is used to select four types of entity nodes in the service blind spot subgraph of the existing facilities as the site selection points for new facilities according to the demand, influence, accessibility and comprehensiveness for the existing facilities service blind spots; among them, the block with the highest average number of daily active people is taken as the demand entity node; the node with the largest eigenvector centrality is taken as the influence entity node; the node with the shortest average path to each block is taken as the accessibility entity node; and the AHP hierarchical analysis method is used to take the point with the highest comprehensive value as the comprehensive entity node;

[0102] The module for adding facilities in service inefficient areas is used to select four types of entity nodes from the service range subgraph of the corresponding public service facilities in the same way for the service inefficient areas of existing facilities, and judge the spatial relationship between the entity nodes and the existing public service facilities. If the entity nodes are located in the same block as the existing public service facilities or the distance is less than the set value, the entity nodes are deleted, and the entity nodes in the second order are selected for judgment again until the spatial position relationship conditions are met, and the entity nodes that meet the conditions are used as the site selection points for new facilities in the service inefficient areas of existing facilities;

[0103] The interactive display module is used to use the constructed target city map and the geographic coordinates of its nodes to perform three-dimensional spatial mapping, and combine the three-dimensional model of the target city to form a three-dimensional sand table; the four types of facility site selection points and related calculation results obtained by screening are interactively displayed in different colors; users determine the final location of public service facilities through interactive selection and operation.

[0104] This embodiment and Embodiment 2 are based on the same inventive concept, and specific details are shown in Embodiment 2, which will not be described in detail.

[0105] Example 6

[0106] A computer system disclosed in an embodiment of the present invention includes a memory, a processor, and a computer program / instruction stored in the memory and executable on the processor. When the computer program / instruction is executed by the processor, the steps of the methods in the aforementioned method embodiments are implemented.

[0107] Example 7

[0108] An embodiment of the present invention discloses a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the methods in the aforementioned method embodiments are implemented.

[0109] Example 8

[0110] A computer program product disclosed in an embodiment of the present invention includes a computer program / instruction, and when the computer program / instruction is executed by a processor, the steps of the method in the aforementioned method embodiments are implemented.

Claims

1. A method for identifying blind spots and inefficient areas of public service facilities based on knowledge graph, characterized in that: The method comprises the following steps: Obtain the current status data of the target city, including urban spatial form and spatial location data, current public service facilities data, and crowd activity data in blocks; take spatial form elements and current public service facilities elements as entities of the knowledge graph, and the spatial distance between entities as relationships, to construct the target city graph; Based on the constructed target city map, the path length from each public service facility entity to all other spatial morphological element entities is calculated, and entities whose path length is less than the service scope of the public service facility are selected as the service scope subgraph of each public service facility; Identify all entities not covered by the service scope submap of public service facilities and mark them as service blind spots. The corresponding entities and relationships constitute the current facility service blind spot submap; In the service scope submap of each public service facility, the total population corresponding to the block entities contained therein is calculated, and the submaps with a population greater than the corresponding facility service carrying capacity are identified and marked as areas with inefficient current facility services.

2. According to the method for identifying blind spots and inefficient areas of public service facilities based on knowledge graph in claim 1, it is characterized in that: The construction of the target city map includes: First, the atlas model layer is constructed, and the entities are defined as spatial morphological elements and current public service facilities. The entity relationship is defined as the spatial distance between entities. The entity attributes of spatial morphological elements are defined as their spatial morphology, spatial location and population. The entity attribute values ​​of spatial morphological elements are area, perimeter, shape index, longitude and latitude of the geometric center and population. The entity attributes of current public service facilities are their service scope and service carrying capacity. The entity attribute values ​​of public service facilities are the radius of their service scope and the maximum number of people they can carry. Secondly, we build a graph data layer, clean the data and organize it into a structured data format of "entity-relationship-entity" and "entity-attribute-attribute value" triples; Finally, using the knowledge graph operating system, the structured triples in the data layer are imported into the system, and the target city graph is established according to the rules defined in the pattern layer.

3. According to the method for identifying blind spots and inefficient areas of public service facilities based on knowledge graph in claim 1, it is characterized in that: The method for calculating the path length from each public service facility entity to all other spatial morphological element entities is as follows: based on the GIS platform, a road network topology structure is established by importing road network data, and the shortest path algorithm is used. The public service facility entity is used as the starting point and other spatial morphological element entities are used as the end point to calculate the path length from the public service facility entity to other spatial morphological element entities.

4. A method for adding public service facilities based on knowledge graph, characterized in that: After obtaining the current facility service blind area and the current facility service inefficient area according to the method for identifying the public service facility blind area and the inefficient area based on the knowledge graph according to any one of claims 1 to 3, the method comprises the following steps: In view of the blind spots of existing facilities, four types of entity nodes in the subgraph of the blind spots of existing facilities are selected as the site selection points of new facilities according to demand, influence, accessibility and comprehensiveness; among them, the block with the highest average number of daily active people is taken as the demand entity node; the node with the largest eigenvector centrality is taken as the influence entity node; the node with the shortest average path to each block is taken as the accessibility entity node; the AHP hierarchical analysis method is used to take the point with the highest comprehensive value as the comprehensive entity node; For the inefficient service area of ​​existing facilities, the same method is used to screen four types of entity nodes from the service range subgraph of the corresponding public service facilities to determine the spatial relationship between the entity node and the existing public service facilities. If the entity node is located in the same block as the existing public service facilities or the distance is less than the set value, the entity node is deleted and the second-ranked entity node is selected for re-determination until the spatial position relationship conditions are met. The entity node that meets the conditions is used as the site selection point for the new facility in the inefficient service area of ​​existing facilities. The constructed target city map and the geographic coordinates of its nodes are used for three-dimensional spatial mapping, and a three-dimensional sand table is formed in combination with the three-dimensional model of the target city. The four types of facility site selection points and related calculation results obtained are interactively displayed in different colors. Users determine the final location of public service facilities through interactive selection and operation.

5. A method for adding public service facilities based on knowledge graph according to claim 4, characterized in that: The screening method of the four types of entity nodes includes: Combined with the crowd activity data collected by video probes for multiple consecutive days, the average number of people active in each block is calculated, and the block entity node with the highest average number of people active in each block is marked as the demand entity node; The eigenvalue decomposition algorithm is used to calculate the eigenvector centrality of each node in the subgraph, and the entity node with the largest eigenvector centrality is taken as the influential entity node. The eigenvector centrality formula is calculated as follows: Among them, C(i) represents the feature centrality of entity node i, λ is the maximum eigenvalue of the adjacency matrix, N(i) represents the set of neighboring entity nodes of entity node i in the subgraph, and A ij It represents the connection weight between entity node i and entity node i in the adjacency matrix. The connection weight is set as the ratio of the product of the degrees of adjacent nodes to the sum of the degrees of all nodes, which reflects the connection activity of the node; The Dijkstra algorithm is used to calculate the path length from each node in the subgraph to all blocks, and the average value of the path length is calculated. The entity node with the shortest path average value is selected as the reachability entity node; Using the AHP hierarchical analysis method, the weights of influence, accessibility and demand are determined, and the comprehensive calculation formula is as follows: S i =ω1v 1i +ω2v 2i +ω3v 3i Among them, ω1, ω2, and ω3 represent the weights of influence, accessibility, and demand, respectively, and v 1i 、v 2i 、v 3i are the scores of entity node i under the three criteria of influence, accessibility, and demand, and then the entity node with the highest comprehensive value is selected as the comprehensive entity node.

6. A public service facility blind spot and inefficient area identification system based on knowledge graph, characterized in that: include: The target city map construction module is used to obtain the current status data of the target city, including urban spatial form and spatial location data, current public service facilities data, and crowd activity data in blocks; The spatial morphological elements and the existing public service facilities elements are taken as entities of the knowledge graph, and the spatial distances between entities are taken as relationships to construct the target city graph; The service scope subgraph screening module of the public service facilities is used to calculate the path length from each public service facility entity to all other spatial morphological element entities based on the constructed target city map, and screen entities whose path length is less than the service scope of the public service facilities as the service scope subgraph of each public service facility; A service blind spot identification module is used to identify all entities not covered by the service scope submap of public service facilities and mark them as service blind spots. The corresponding entities and relationships constitute the current facility service blind spot submap; And a service inefficiency area identification module is used to calculate the total population corresponding to the block entities contained in the service range submap of each public service facility, identify the submaps with a population greater than the corresponding facility service carrying capacity and mark them as current facility service inefficiency areas.

7. A public service facility addition system based on knowledge graph, characterized in that: The method comprises the modules in the public service facility blind spot and inefficient area identification system based on knowledge graph according to claim 6, and: The service blind spot facility addition module is used to select four types of entity nodes in the service blind spot subgraph of the existing facilities as the site selection points for new facilities according to demand, influence, accessibility and comprehensiveness for the existing facilities service blind spots; among them, the block with the highest average number of daily active people is taken as the demand entity node; the node with the largest eigenvector centrality is taken as the influence entity node; the node with the shortest average path to each block is taken as the accessibility entity node; and the AHP hierarchical analysis method is used to take the point with the highest comprehensive value as the comprehensive entity node; The module for adding facilities in service inefficient areas is used to select four types of entity nodes from the service range subgraph of the corresponding public service facilities in the same way for the service inefficient areas of existing facilities, and judge the spatial relationship between the entity nodes and the existing public service facilities. If the entity nodes are located in the same block as the existing public service facilities or the distance is less than the set value, the entity nodes are deleted, and the entity nodes in the second order are selected for judgment again until the spatial position relationship conditions are met, and the entity nodes that meet the conditions are used as the site selection points for new facilities in the service inefficient areas of existing facilities; The interactive display module is used to use the constructed target city map and the geographic coordinates of its nodes to perform three-dimensional spatial mapping, and combine the three-dimensional model of the target city to form a three-dimensional sand table; the four types of facility site selection points and related calculation results obtained by screening are interactively displayed in different colors; users determine the final location of public service facilities through interactive selection and operation.

8. A computer system comprising a memory, a processor, and a computer program / instruction stored in the memory and executable on the processor, characterized in that: When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images