Automatic identification method for urban shadow area based on knowledge graph

Abstract

The invention discloses an urban shadow area automatic identification method based on a knowledge graph. The method comprises five parts of shadow area case library construction, shadow area feature identification model construction, target city graph construction, target city shadow area graph subset search, and target city shadow area identification result output and display. According to the method, the current city data is integrated through the knowledge graph, the city shadow area is accurately identified, and the identification result is finely displayed. The method can cope with the automatic identification of the city shadow area in the field of city planning, the identification accuracy based on the super-large city case library is higher, the identification speed based on the search of the map subset of the shadow area is higher, the formed three-dimensional interactive display is more stereoscopic and visual, and the guidance of the city planning project is stronger.

Description

Technical Field

[0001] The present invention relates to the field of urban planning, and in particular to a method for automatically identifying urban shadow areas based on a knowledge graph. Background Art

[0002] Urban shadow areas are caused by the "unbalanced and insufficient" development of urban internal space, and are mainly characterized by low and disordered construction forms, scattered and insufficient public facilities, old and broken architectural styles, and low-end and scattered business formats. The study of urban shadow areas can be used as an important case to explore issues such as unbalanced urban development, social spatial differentiation, and ineffective urban planning. Through further in-depth research, it can reveal the internal logic and mechanism of urban development and provide theoretical support and empirical basis for future urban planning.

[0003] At present, the identification of most shadow areas still relies on the calculation and summary of indicators such as geographical environment, economic development level, and social and cultural conditions. However, due to the complexity and diversity of the internal causes of shadow areas, it is difficult to accurately judge them by relying on only some indicators, and the selection of specific indicators also has differences in individual subjective cognition. As a result, the identification of shadow areas has problems such as limited summary efficiency and accuracy, making the traditional shadow area identification method not scientific and efficient, and it is difficult to further promote the update and optimization of shadow areas. Summary of the invention

[0004] In order to solve the deficiencies mentioned in the above-mentioned background technology, the purpose of the present invention is to provide a method for automatic identification of urban shadow areas based on knowledge graph. The present invention can integrate current urban data through knowledge graph, accurately identify urban shadow areas and display the identification results in a refined manner.

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

[0006] A method for automatically identifying urban shadow areas based on knowledge graphs includes the following steps:

[0007] Step 1: Construction of the shadow area case library

[0008] The spatial morphological data, business data and human flow data of seven megacities in China were obtained. The megacities were derived from the "Statistical Chart of Economic and Social Development: Basic Population Situation of Megacities and Extra-large Cities in the Seventh National Population Census" published by the National Bureau of Statistics, including Shanghai, Beijing, Shenzhen, Chongqing, Guangzhou, Chengdu and Tianjin. The shadow areas of the central areas of the seven megacities were identified using the quantitative identification method of urban shadow areas, and the boundary vector data of the shadow areas of the central areas of each megacities were obtained. The corresponding spatial morphological data, business data and human flow data were extracted in combination with the boundaries of each shadow area, and a shadow area case library was constructed.

[0009] Step 2: Construction of shadow area feature recognition model

[0010] Combined with the shadow area case library obtained in step S1, spatial morphological elements (including blocks, roads, open spaces), business elements and human flow elements are used as entities of the knowledge graph, and each shadow area graph is constructed through the knowledge graph operating system. A supervised clustering learning algorithm and a deep learning system are used to take the entities and attributes, relationships and attributes of the shadow area graph as machine learning labels to generate a shadow area feature recognition model, and further identify the shadow area feature graph.

[0011] Step 3: Target city map construction

[0012] The current status data of the planning bureau of the target city is retrieved, and the spatial form data, business data and passenger flow data are respectively integrated, and the target city graph is constructed using the knowledge graph operating system described in step S2.

[0013] Step 4: Find the target city shadow area map subset

[0014] Select the graph convolutional network model, use the graph embedding algorithm for the target city map and the shadow area feature map respectively, and train them to learn how to map the graph structure data to the low-dimensional vector space, and then generate the embedding representation of each node in the low-dimensional vector space. Use the similarity calculation method to calculate the feature similarity and relationship similarity of each subgraph of the target city map and the shadow area feature map in the low-dimensional vector space. The closer the similarity is to 1, the more similar the direction of the target city map subgraph and the shadow area feature map in the embedding space is, that is, their graph structure and relationship are more similar to the shadow area feature map. First, calculate the feature similarity of the target city map and the shadow feature map, and screen out the potential shadow area subgraph with similar attribute features to the shadow area feature map; then, calculate the relationship similarity between the potential shadow area subgraph and the shadow feature map, screen out the shadow area subgraph with a similar network structure to the shadow area feature map, and mark it as the target city shadow area map subset.

[0015] Step 5: Output and display of target city shadow area identification results

[0016] The target city shadow area recognition results are output to the three-dimensional interactive display device, and the above contents are integrated into a recognition report and printed in word / excel format.

[0017] Furthermore, the quantitative identification method of the urban shadow area in step 1 refers to using the block as the basic unit for defining the spatial boundary of the urban shadow area, and calculating the indicators of the spatial location, construction intensity, business layout, and crowd vitality of each block unit according to the table (Table 1). The above-mentioned factor analysis results are spatially aligned and superimposed using the geographic information system to obtain the comprehensive index distribution, and the area composed of relatively low-value blocks in the bottom 10% of the comprehensive index is used as the preliminary boundary definition result. Identify the adjacent blocks outside each area, and if the block is in the bottom 20% of the identification result, include it in the shadow area. Further conduct on-site surveys of each area, and eliminate the natural elements and blocks where public buildings are located based on the survey results.

[0018] Table 1. Recognition of spatial boundaries of shadow areas

[0019]

[0020] Furthermore, the construction of each shaded area map through the knowledge graph operating system in step 2 is an innovative step of this patent, which means first constructing the graph pattern layer. Define the entity elements and their attributes, entity relationships and their attributes of the graph (Table 2), and define the structure and hierarchical relationship between entities, attributes and relationships (Table 3); secondly, construct the graph data layer. Clean the spatial morphological data, business data and population data in the database, and organize the cleaned data into a structured data format of triples; finally, import the structured data of the data layer into the graph database management system, and establish the relationship between entities according to the definition of the pattern layer, thereby completing the graph construction.

[0021] Table 2 Graph entities and their attributes

[0022]

[0023]

[0024] Table 3 Graph relationships and their attributes

[0025]

[0026] Furthermore, the shadow area feature recognition model in step 2 is an innovative step of this patent, which refers to using the entities and attributes, relationships and properties of the shadow area map as machine learning labels, and dividing the shadow area map into training set, validation set and test set in a ratio of 6:2:2. The operator selects entities and relationships related to the characteristics of each shadow area on the knowledge map visualization platform, and obtains the operator's selection tendency with the assistance of an eye tracker with 0.4° line of sight tracking accuracy. A supervised clustering learning algorithm is used to perform shadow area map feature extraction learning and training through a 512GB video memory deep learning system, and a machine learning model with strong generalization performance is selected as the shadow area feature recognition model, and the identified entity elements and attributes, entity relationships and attributes are output to obtain the shadow area feature map.

[0027] Furthermore, the feature similarity calculation in step 4 is an innovative step of this patent, which refers to extracting the attributes of the target city map sub-map and the shadow feature map, wherein the attributes are the pattern layer attributes of the shadow feature map and the target city map sub-map defined in steps 1 and 4. The cosine similarity measurement method is used to calculate and compare the feature similarity between the two maps. The formula is as follows:

[0028]

[0029] Where A is the embedded representation of the target city map sub-map in the low-dimensional vector space, and B is the embedded representation of the shadow feature map in the low-dimensional vector space.

[0030] Calculate the feature similarity between all n sub-graphs of the target city graph and the shadow feature graph, that is, calculate Similarity(A1,B), Similarity(A2,B)…Similarity(A n ,B). In the interval [-1,1], sort the feature similarities from large to small, select the top 10% feature similarities, if the top 10% feature similarities are all greater than 0, then mark the corresponding sub-graph as a potential shadow sub-graph with similar attribute features to the shadow feature map; otherwise, remove the feature similarities less than or equal to 0, and mark the remaining corresponding sub-graphs as potential shadow sub-graphs with similar attribute features to the shadow feature map.

[0031] Furthermore, the relationship similarity calculation in step 4 is an innovative step of this patent, which refers to converting the potential shadow area subgraph and the shadow feature map into the form of an adjacency matrix, and using the subgraph isomorphism algorithm to calculate and compare the relationship similarity between the two maps. The formula is as follows:

[0032]

[0033] Among them G iis the potential shadow subgraph, G is the shadow feature map, V1 is the node set of the potential shadow subgraph, Similarity(v,G(v)) is the similarity between node v and the corresponding node G(v) in the shadow feature map. The higher the score, the more similar the potential shadow subgraph is to the shadow feature map.

[0034] Calculate the similarity between all m sub-images of the potential shadow area and the shadow feature map, that is, calculate score(G1,G), score(G2,G)…score(G m ,G), sort all relationship similarities from large to small, select the top 10% of similarities, and mark their corresponding subgraphs as the shaded area map subset of the target city.

[0035] Furthermore, the display of the target city shadow area identification results in the step five refers to the display of the graph structure of three graphs, namely, the shadow area feature graph, the target city graph, and the target city shadow area graph subset in the form of a graph network, wherein the graph structure includes the network structure of each entity, attribute and relationship, and displays the feature similarity and relationship similarity between the shadow area graph subset of each target city and the shadow area feature graph.

[0036] Beneficial effects of the present invention:

[0037] 1. Acquire the spatial morphological data, business data and passenger flow data of megacities, use the quantitative identification method of urban shadow areas to identify the boundary vector data of shadow areas in each central area, and build a shadow area case library by combining the four types of data, laying the foundation for the construction of the subsequent shadow area feature recognition model.

[0038] 2. Through the knowledge graph operating system, the graphs of each shadow area are constructed, and the supervised clustering learning algorithm and deep learning system are used to train the shadow area features, so as to establish a shadow area feature recognition model. This model provides a standard and reliable reference for shadow area feature recognition.

[0039] 3. Combining the feature similarity and relationship similarity algorithms, the function of searching for subsets of the target city’s shadow area map is realized, and subgraphs in the target city map whose spatial form and relationship network are similar to the shadow area feature map are screened and identified, thereby realizing automatic identification of the target city’s shadow area. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a flow chart of the method of the present invention.

[0041] Figure 2 It is the flow chart of shadow area feature recognition. DETAILED DESCRIPTION

[0042] 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.

[0043] A method for automatically identifying urban shadow areas based on knowledge graph, such as Figure 1 and Figure 2 As shown, the following steps are included:

[0044] 1. Construction of shadow area case library. The spatial morphological data, business data and human flow data of seven megacities in China were obtained. The megacities were derived from the "Statistical Chart of Economic and Social Development: Basic Population Situation of Megacities and Extra-large Cities in the Seventh National Population Census" published by the National Bureau of Statistics, including Shanghai, Beijing, Shenzhen, Chongqing, Guangzhou, Chengdu and Tianjin. The shadow areas of the central areas of the seven megacities were identified using the quantitative identification method of urban shadow areas, and the boundary vector data of the shadow areas of the central areas of each megacities were obtained. The corresponding spatial morphological data, business data and human flow data were extracted in combination with the boundaries of each shadow area to construct a shadow area case library.

[0045] The quantitative identification method of the urban shadow area is as follows: the block is used as the basic unit for defining the spatial boundary of the urban shadow area, and the indicators of the spatial location, construction intensity, business layout, and crowd vitality of each block unit are calculated according to the table (Table 1). The above-mentioned factor analysis results are spatially aligned and superimposed using the geographic information system to obtain the comprehensive index distribution, and the area composed of relatively low-value blocks in the bottom 10% of the comprehensive index is used as the preliminary boundary definition result. The adjacent blocks outside each area are identified. If the block is in the bottom 20% of the identification result, it is included in the shadow area. Further field surveys are conducted in each area, and the natural elements and blocks where public buildings are located are eliminated based on the survey results.

[0046] Table 1. Recognition of spatial boundaries of shadow areas

[0047]

[0048]

[0049] 2. Construction of shadow area feature recognition model. Combined with the shadow area case library obtained in the construction of the shadow area case library, the spatial morphological elements, business elements and human flow elements are used as entities of the knowledge graph, and each shadow area map is constructed through the knowledge graph operating system. Using the supervised clustering learning algorithm and deep learning system, the entities and attributes, relationships and attributes of the shadow area map are used as machine learning labels to generate a shadow area feature recognition model, and further identify the shadow area feature map.

[0050] The specific construction of each shaded area map through the knowledge graph operating system is as follows: First, construct the graph pattern layer. Define the entity elements and their attributes, entity relationships and their attributes of the graph (Table 2), and define the structure and hierarchical relationship between entities, attributes and relationships (Table 3); secondly, construct the graph data layer. Clean the spatial morphological data, business data and crowd data in the database, and organize the cleaned data into a structured data format of triples; finally, import the structured data of the data layer into the graph database management system, and establish the relationship between entities according to the definition of the pattern layer, so as to complete the graph construction.

[0051] Table 2 Graph entities and their attributes

[0052]

[0053]

[0054] Table 3 Graph relationships and their attributes

[0055]

[0056] The shadow area feature recognition model is as follows: the entities and attributes, relationships and properties of the shadow area map are used as machine learning labels, and the shadow area map is divided into a training set, a validation set, and a test set in a ratio of 6:2:2. The operator selects entities and relationships related to the characteristics of each shadow area on the knowledge map visualization platform, and the operator's selection tendency is obtained with the assistance of an eye tracker with a 0.4° line of sight tracking accuracy. A supervised clustering learning algorithm is used to perform learning and training for shadow area map feature extraction through a 512GB video memory deep learning system. A machine learning model with strong generalization performance is selected as the shadow area feature recognition model, and the identified entity elements and attributes, entity relationships and attributes are output to obtain the shadow area feature map.

[0057] 3. Construction of target city map. Retrieve the current status data of the target city planning bureau, integrate the spatial form data, business data and passenger flow data respectively, and use the knowledge graph operating system described in the construction of the shadow area feature recognition model to construct the target city map.

[0058] 4. Finding subsets of target city shadow area graphs. Select a graph convolutional network model, use graph embedding algorithms on the target city graph and shadow area feature graph respectively, and train them to learn how to map graph structure data to low-dimensional vector space, and then generate an embedded representation of each node in the low-dimensional vector space. Use the similarity calculation method to calculate the feature similarity and relationship similarity of each subgraph of the target city graph and the shadow area feature graph in the low-dimensional vector space. The closer the similarity is to 1, the more similar the direction of the target city graph subgraph and the shadow area feature graph in the embedding space is, that is, their graph structure and relationship are more similar to the shadow area feature graph. First, calculate the feature similarity of the target city graph and the shadow feature graph, and screen out potential shadow area subgraphs with similar attribute features to the shadow area feature graph; then, calculate the relationship similarity of the potential shadow area subgraph and the shadow feature graph, screen out shadow area subgraphs with similar network structures to the shadow area feature graph, and mark them as subsets of the target city shadow area graph.

[0059] The method for calculating feature similarity screening is as follows: extract the attributes of the target city map sub-map and the shadow feature map, wherein the attributes are the pattern layer attributes of the shadow feature map and the target city map sub-map defined in step S2 and step S41. Use the cosine similarity measurement method to calculate and compare the feature similarity between the two maps. The formula is as follows:

[0060]

[0061] A is the embedding representation of the target city map sub-map in the low-dimensional vector space, and B is the embedding representation of the shadow feature map in the low-dimensional vector space. Calculate the feature similarity between all n sub-maps of the target city map and the shadow feature map, that is, calculate Similarity(A1,B), Smilarity(A2,B)…Smilarity(A n ,B). In the interval [-1,1], sort the feature similarities from large to small, select the top 10% feature similarities, if the top 10% feature similarities are all greater than 0, then mark the corresponding sub-graph as a potential shadow sub-graph with similar attribute features to the shadow feature map; otherwise, remove the feature similarities less than or equal to 0, and mark the remaining corresponding sub-graphs as potential shadow sub-graphs with similar attribute features to the shadow feature map.

[0062] The method for calculating the relationship similarity screening is as follows: convert the potential shadow area subgraph and the shadow feature map into the form of an adjacency matrix, and use the subgraph isomorphism algorithm to calculate and compare the relationship similarity between the two maps. The formula is as follows:

[0063]

[0064] Among them Gi is the potential shadow subgraph, G is the shadow feature map, V1 is the node set of the potential shadow subgraph, Similarity(v,G(v)) is the similarity between node v and the corresponding node G(v) in the shadow feature map, the higher the score, the more similar the potential shadow subgraph is to the shadow feature map. Calculate the similarity between all m subgraphs of the potential shadow subgraph and the shadow feature map, that is, calculate score(G1,G), score(G2,G)…score(G m ,G), sort all relationship similarities from large to small, select the top 10% of similarities, and mark their corresponding subgraphs as the shaded area map subset of the target city.

[0065] 5. Output and display of target city shadow area recognition results. Output the target city shadow area recognition results to the three-dimensional interactive display device, and integrate the above content into a recognition report and print it in word / excel format.

[0066] The target city shadow area recognition result is displayed specifically as follows: the graph structure of three graphs, namely the shadow area feature graph, the target city graph, and the target city shadow area graph subset, is displayed in the form of a graph network, wherein the graph structure includes the network structure of each entity, attribute and relationship, and displays the feature similarity and relationship similarity between the shadow area graph subset of each target city and the shadow area feature graph.

Claims

1. A method for automatically identifying urban shadow areas based on knowledge graph, characterized in that: The method comprises the following steps: Step S1: Construction of shadow area case library The spatial morphological data, business data and human flow data of seven megacities in China were obtained. The megacities were derived from the "Statistical Charts on Economic and Social Development: Basic Population Situation of Megacities and Extra-large Cities in the Seventh National Population Census" published by the National Bureau of Statistics, including Shanghai, Beijing, Shenzhen, Chongqing, Guangzhou, Chengdu and Tianjin. The shadow areas of the central areas of the seven megacities were identified using the quantitative identification method of urban shadow areas, and the boundary vector data of the shadow areas of the central areas of each megacity was obtained. The corresponding spatial morphological data, business data and human flow data were extracted in combination with the boundaries of each shadow area, and a shadow area case library was constructed. Step S2: Construction of shadow area feature recognition model Combined with the shadow area case library obtained in step S1, spatial morphological elements (including blocks, roads, open spaces), business elements and human flow elements are used as entities of the knowledge graph, and each shadow area graph is constructed through the knowledge graph operating system; supervised clustering learning algorithm and deep learning system are used to take the entities and attributes, relationships and attributes of the shadow area graph as machine learning labels, generate a shadow area feature recognition model, and further identify and obtain the shadow area feature graph; Step S3: Target city map construction Retrieve the current status data of the planning bureau of the target city, and integrate the spatial form data, business data and passenger flow data respectively, and use the knowledge graph operating system described in step S2 to construct the target city graph; Step S4: Searching for a subset of the target city shadow area atlas Select a graph convolutional network model, use a graph embedding algorithm for the target city map and the shadow area feature map respectively, and map the graph network structure to a computable low-dimensional vector space; use a feature similarity algorithm to perform a similarity test on the target city map obtained in step S3 and the shadow area feature map obtained in step S2, and screen out potential shadow area subgraphs with similar attribute features to the shadow area feature map; then, use a relational similarity algorithm to screen out shadow area subgraphs with similar network structures to the shadow area feature map obtained in step S2 from the potential shadow area subgraphs, and mark them as the shadow area map subset of the target city; Step S5: Output and display of target city shadow area identification results The target city shadow area recognition results are output to the three-dimensional interactive display device, and the above contents are integrated into a recognition report and printed in word / excel format.

2. According to the method of automatic identification of urban shadow areas based on knowledge graph in claim 1, it is characterized in that: The specific method for quantitatively identifying urban shadow areas in step S1 is as follows: Taking the block as the basic unit for defining the spatial boundary of the urban shadow area, the indicators of spatial location, construction intensity, business layout, and crowd vitality of each block unit are calculated according to the table, see Table 1; the above-mentioned factor analysis results are spatially aligned and superimposed using the geographic information system to obtain the comprehensive index distribution, and the area composed of relatively low-value blocks in the bottom 10% of the comprehensive index is used as the preliminary boundary definition result; the adjacent blocks outside each area are identified, and if the block is in the bottom 20% of the identification result, it is included in the shadow area; further field surveys are conducted on each area, and the natural elements and blocks where public buildings are located are eliminated based on the survey results; Table 1. Recognition of spatial boundaries of shadow areas 3. The method for automatically identifying urban shadow areas based on knowledge graph according to claim 2 is characterized in that: The specific construction of each shadow area graph through the knowledge graph operating system in step S2 is as follows: First, construct the graph model layer. Define the graph entity elements and their attributes, entity relationships and their attributes, see Table 2; define the structure and hierarchical relationship between entities, attributes and relationships, see Table 3; Table 2 Graph entities and their attributes Table 3 Graph relationships and their attributes Secondly, construct the graph data layer. Clean the spatial form data, business data and crowd data in the database, and organize the cleaned data into a triple structured data format; Finally, the structured data of the data layer is imported into the graph database management system, and the relationship between entities is established according to the definition of the model layer to complete the graph construction.

4. The method for automatically identifying urban shadow areas based on knowledge graph according to claim 3 is characterized in that: The shadow area feature recognition model described in step S2 is specifically as follows: The entities and attributes, relationships and properties of the shadow area map are used as labels for machine learning, and the shadow area map is divided into training set, validation set, and test set in a ratio of 6:2:

2. The operator selects entities and relationships related to the characteristics of each shadow area on the knowledge graph visualization platform, and uses an eye tracker with 0.4° line of sight tracking accuracy to assist in obtaining the operator's selection tendency. A supervised clustering learning algorithm is used to perform shadow area map feature extraction learning and training through a 512GB video memory deep learning system. A machine learning model with strong generalization performance is selected as the shadow area feature recognition model, and the identified entity elements and attributes, entity relationships and attributes are output to obtain the shadow area feature map.

5. The method for automatically identifying urban shadow areas based on knowledge graph according to claim 4 is characterized in that: Step S4 includes the following steps: S41 Target city map and shadow area map embedding Select the graph convolutional network model, use the graph embedding algorithm on the target city map and the shadow area feature map, and train them to learn how to map the graph structure data to the low-dimensional vector space, thereby generating the embedded representation of each node in the low-dimensional vector space; S42 Find the shadow area atlas subset of the target city Using the similarity calculation method, the feature similarity and relationship similarity between each subgraph of the target city graph and the feature graph of the shadow area are calculated in the low-dimensional vector space. The closer the similarity is to 1, the more similar the directions of the subgraph of the target city graph and the feature graph of the shadow area in the embedding space are, that is, the higher the similarity between their graph structures and relationships and the feature graph of the shadow area; First, the feature similarity between the target city map and the shadow feature map is calculated, and the potential shadow area submap with similar attribute features to the shadow area feature map is screened out; then, the relationship similarity between the potential shadow area submap and the shadow feature map is calculated, and the shadow area submap with a similar network structure to the shadow area feature map is screened out and marked as the shadow area map subset of the target city.

6. The method for automatically identifying urban shadow areas based on knowledge graph according to claim 1 is characterized in that: The method for calculating feature similarity screening in step S42 is as follows: For the target city map sub-map and the shadow feature map, their attributes are extracted, wherein the attributes are the mode layer attributes of the shadow feature map and the target city map sub-map defined in step S2 and step S41; the cosine similarity measurement method is used to calculate and compare the feature similarity between the two maps; the formula is as follows: Where A is the embedded representation of the target city map sub-map in the low-dimensional vector space, and B is the embedded representation of the shadow feature map in the low-dimensional vector space; Calculate the feature similarity between all n sub-graphs of the target city graph and the shadow feature graph, that is, calculate Similarity(A1,B), Similarity(A2,B)…Similarity(A n ,B); In the interval of [-1,1], sort the feature similarities from large to small, select the top 10% feature similarities, if the top 10% feature similarities are all greater than 0, then mark the corresponding sub-graph as a potential shadow area sub-graph with similar attribute features to the shadow area feature map; otherwise, remove the feature similarities less than or equal to 0, and mark the remaining corresponding sub-graphs as potential shadow area sub-graphs with similar attribute features to the shadow area feature map.

7. The method for automatically identifying urban shadow areas based on knowledge graph according to claim 6 is characterized in that: The method for calculating the relationship similarity screening in step S42 is as follows: The potential shadow area subgraph and the shadow feature map are converted into the form of an adjacency matrix, and the subgraph isomorphism algorithm is used to calculate and compare the similarity of the relationship between the two maps; the formula is as follows: Among them G i is the potential shadow subgraph, G is the shadow feature map, V1 is the node set of the potential shadow subgraph, Similarity(v,G(v)) is the similarity between node v and the corresponding node G(v) in the shadow feature map, and the higher the score, the more similar the potential shadow subgraph is to the shadow feature map; Calculate the similarity between all m sub-images of the potential shadow area and the shadow feature map, that is, calculate score(G1,G), score(G2,G)…score(G m ,G), sort all relationship similarities from large to small, select the top 10% of similarities, and mark their corresponding subgraphs as the shaded area map subset of the target city.

8. The method for automatically identifying urban shadow areas based on knowledge graph according to claim 7 is characterized in that: The target city shadow area recognition result in step S5 is shown as follows: The graph structures of the shadow area feature graph, the target city graph, and the shadow area graph subset of the target city are displayed in the form of a graph network, wherein the graph structure includes the network structure of each entity, attribute, and relationship, and displays the feature similarity and relationship similarity between the shadow area graph subset of each target city and the shadow area feature graph.

Images