Geographic spatial data knowledge graph construction method and system based on geographic element classification

Abstract

The invention relates to the technical field of geographic knowledge, in particular to a geographic spatial data knowledge graph construction method and system based on geographic element classification. Performing fine-grained hierarchical division on the first-level classifications of the geographic elements according to geographic positions and spatial distribution in the first-level classifications of the geographic elements to obtain sub-classifications of the geographic elements in the first-level classifications of the geographic elements; constructing a geographic element knowledge ontology library according to each geographic element subclass; extracting thematic geographic entities, thematic geographic entity relationships and thematic geographic entity attributes based on the geographic element knowledge ontology library, constructing a thematic geographic space knowledge triple, and storing the thematic geographic space knowledge triple into a Neo4j graph database to form a thematic geographic element data knowledge graph, the geographic space data can be retrieved and queried by utilizing the knowledge graph. According to the method, geographic space knowledge can be fully utilized to realize conversion from geographic space data to knowledge data, and dynamic retrieval and query of geographic space objects are realized.

Description

Technical Field

[0001] The present invention relates to the field of geographic knowledge technology, and in particular to a method and system for constructing a geographic spatial data knowledge graph based on geographic element classification. Background Art

[0002] Knowledge graphs are widely used in the field of artificial intelligence and provide important underlying support for many intelligent applications. However, existing general knowledge graphs are mostly constructed based on non-spatial data such as Wikipedia, with low spatial knowledge coverage and missing Chinese attributes and coordinate information. Space is the basic dimension of objective things and the essential attribute of geographic feature data. How to display the interaction of objective things and use spatial relationships to achieve the conversion of "data-information-knowledge" is the focus of research. At present, existing studies have mostly formalized shared concepts through ontologies, constructed geographic spatial knowledge databases, and integrated multi-source data. Although ontologies can realize data sharing and spatial relationship reasoning, they must be constructed by domain experts and can only reflect relatively constant knowledge and logical relationships. Summary of the invention

[0003] To this end, the present invention provides a method and system for constructing a geospatial data knowledge graph based on geographic element classification, which solves the deficiency that the existing use of ontology to construct geospatial knowledge can only relatively constantly describe knowledge and logical relationships. Based on the fine-grained classification of geographic elements to describe the attributes of each ontology and the relationship between ontologies, the geospatial knowledge can be fully utilized to realize the transformation of geospatial data into knowledge data, so as to realize dynamic retrieval and query of geospatial objects by using the geospatial knowledge graph.

[0004] According to the design scheme provided by the present invention, on the one hand, a method for constructing a geographic spatial data knowledge graph based on geographic element classification is provided, comprising:

[0005] Classify the geographical elements into primary categories according to their geographical location and spatial distribution, and divide the primary categories of the geographical elements into fine-grained hierarchical categories according to their geographical location and spatial distribution, so as to obtain subcategories of the geographical elements in the primary categories of the geographical elements, wherein the geographical elements are geographical factors used to describe differences between geographical types and / or geographical areas;

[0006] Constructing a geographic element knowledge ontology library according to each geographic element subclass, the knowledge ontology library includes an ontology object, an ontology attribute set and an ontology relationship set, the ontology object is a model for describing a geographic space object, the ontology attribute set is used to describe the characteristic attributes of the ontology object, and the ontology relationship set is used for the association relationship between each ontology object;

[0007] Extracting thematic geographic entities based on geographic element knowledge ontology, taking thematic geographic entities as spatial objects to obtain thematic geographic entity relationships, and obtaining thematic geographic entity attributes based on the characteristics of thematic geographic entities themselves, wherein the thematic geographic entity relationships include spatial relationships, temporal relationships, and semantic relationships;

[0008] Thematic geospatial knowledge triples are constructed based on thematic geographic entities, thematic geographic entity attributes and thematic geographic entity relationships. The thematic geospatial knowledge triples are stored in the Neo4 graph database and form a thematic geographic element data knowledge graph, so that the thematic geographic element data knowledge graph can be used to retrieve and query geospatial data.

[0009] As a method for constructing a geographic spatial data knowledge graph based on geographic element classification in the present invention, further, the first-level classification of geographic elements includes but is not limited to: positioning basis, water system, settlements and facilities, transportation, pipelines, boundaries and political regions, landforms, vegetation and soil quality, geophysical fields, military-specific and geology.

[0010] As a method for constructing a geographic spatial data knowledge graph based on geographic element classification in the present invention, further, the first-level classification of geographic elements is divided into fine-grained hierarchical levels according to geographical location and spatial distribution, including:

[0011] Based on the geographical location and spatial distribution, the geographical elements after each first-level classification are subdivided into second-level geographical element subclasses, third-level geographical element subclasses and fourth-level geographical element subclasses according to the hierarchical relationship;

[0012] An orderly thematic geographic element classification system is formed based on the first-level classification of geographic elements, the second-level subclasses of geographic elements, the third-level subclasses of geographic elements and the fourth-level subclasses of geographic elements.

[0013] As a method for constructing a geographic spatial data knowledge graph based on geographic element classification in the present invention, further, a geographic element knowledge ontology library is constructed according to each geographic element subclass, including:

[0014] Extracting ontology objects according to each geographic element subclass in the geographic space data, and constructing ontology object attribute sets according to the common attributes and unique attributes of the ontology object type, wherein the common attributes are feature descriptions common to the ontology objects in the geographic space, and the unique attributes are feature descriptions unique to each ontology object category in the geographic space;

[0015] Construct an ontology object relationship set according to the ontology spatial relationship, temporal relationship and semantic relationship in the geographic spatial data, wherein the spatial relationship includes spatial topological relationship, spatial distance relationship and spatial orientation relationship, the temporal relationship includes the time sequence before and after the ontology object is changed, and the semantic relationship includes hierarchical relationship, dependency relationship and equivalent relationship;

[0016] The geographic feature knowledge ontology database is constructed based on ontology objects, ontology object attribute sets and ontology object relationship sets.

[0017] As a method for constructing a geographic spatial data knowledge graph based on geographic element classification in the present invention, further, the hierarchical relationship includes: a whole relationship for the ontology object to belong to or include the corresponding structure / terrain, a genus-species relationship for describing the type to which the ontology object belongs or includes, and an instance relationship for the ontology object to belong to or include the model concept.

[0018] As a method for constructing a geographic spatial data knowledge graph based on geographic element classification of the present invention, further, extracting geographic entities based on a geographic element knowledge ontology library includes:

[0019] Obtain basic geographic information vector data, and obtain thematic geographic element knowledge ontology database data based on the basic geographic information vector data;

[0020] Thematic geographic entities are extracted from the thematic geographic element knowledge ontology database data to obtain thematic geographic entity attributes and thematic geographic entity relationships based on the thematic geographic entities.

[0021] As a method for constructing a geographic spatial data knowledge graph based on geographic element classification in the present invention, further, the geographic spatial knowledge triple is represented as: {entity (attribute: attribute value)}-{relationship}-{entity (attribute: attribute value)}, wherein the entity is a thematic geographic entity in a thematic geographic element knowledge ontology library, the attributes and attribute values ​​correspond to the attributes and attribute values ​​of the thematic geographic entity, and the relationship is the correspondence between the two thematic geographic entities.

[0022] On the other hand, the present invention also provides a geographic spatial data knowledge graph construction system based on geographic element classification, comprising: a knowledge classification module, a knowledge base construction module, a knowledge extraction module and a knowledge display module, wherein:

[0023] A knowledge classification module is used to classify geographical elements into primary categories according to geographical location and spatial distribution, and to divide the primary categories of geographical elements into fine-grained hierarchical categories according to geographical location and spatial distribution in each primary category of geographical elements, so as to obtain subcategories of each geographical element in the primary category of geographical elements, wherein the geographical elements are geographical factors used to describe differences between geographical types and / or geographical areas;

[0024] A knowledge base construction module is used to construct a geographic element knowledge ontology base based on each geographic element subclass. The knowledge ontology base includes an ontology object, an ontology attribute set, and an ontology relationship set. The ontology object is a model used to describe a geographic space object. The ontology attribute set is used to describe the characteristic attributes of the ontology object. The ontology relationship set is used to describe the association relationship between each ontology object.

[0025] The knowledge extraction module is used to extract thematic geographic entities based on the geographic element knowledge ontology library, obtain thematic geographic entity relationships using thematic geographic entities as spatial objects, and obtain thematic geographic entity attributes based on the characteristics of thematic geographic entities themselves. The thematic geographic entity relationships include spatial relationships, temporal relationships, and semantic relationships.

[0026] The knowledge display module is used to construct thematic geospatial knowledge triples based on thematic geographic entities, thematic geographic entity attributes and thematic geographic entity relationships, store the thematic geospatial knowledge triples in the Neo4 graph database and form the thematic geographic element data knowledge graph, so as to use the thematic geographic element data knowledge graph to search and query the geospatial data.

[0027] Beneficial effects of the present invention:

[0028] The present invention classifies thematic geographic elements and constructs a thematic geographic element subclass ontology; constructs a thematic geographic element knowledge ontology library based on the thematic geographic element subclass ontology, wherein the ontology library includes an ontology object, an ontology attribute set and an ontology relationship set; the attribute set is used to describe the attributes of the ontology; the relationship set is used to describe the association relationship between each ontology; obtains the thematic geographic element knowledge ontology library data based on basic geographic information vector data, and extracts thematic geographic entities, attributes and relationships therefrom; constructs knowledge triples based on the extracted thematic geographic entities, attributes and relationships, stores the knowledge triples in a Neo4 graph database, obtains a knowledge graph of thematic geographic element data, and can fully utilize geographic spatial data to realize the transformation of data into knowledge through fine-grained division of geographic elements and construction of a knowledge graph of thematic geographic element data, so as to utilize the knowledge graph of thematic geographic element data to search and query geographic spatial objects, realize the use of the knowledge graph to analyze and understand the characteristics and relationships of geographic spatial objects, and provide data support and guidance for decision-making and planning for environmental monitoring, population distribution, administrative division, flood and other geographic disaster risk assessment, etc., and has good application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 The following is a schematic diagram of the process of constructing a geospatial data knowledge graph based on geographic element classification in an embodiment;

[0030] Figure 2 Schematic diagram of the geospatial data knowledge graph in the embodiment. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solutions and advantages of the present invention clearer and more understandable, the present invention is further described in detail below in conjunction with the accompanying drawings and technical solutions.

[0032] Embodiments of the present invention, see Figure 1As shown, a method for constructing a geographic spatial data knowledge graph based on geographic element classification is provided, comprising:

[0033] S101. Classify the geographical elements into primary categories according to their geographical locations and spatial distributions, and divide the primary categories of the geographical elements into fine-grained hierarchical categories according to their geographical locations and spatial distributions in each primary category of the geographical elements, so as to obtain subcategories of the geographical elements in the primary category of the geographical elements. The geographical elements are geographical factors used to describe the differences between geographical types and / or geographical areas.

[0034] Specifically, the first-level classification of geographical elements may include, but is not limited to: positioning basis, water system, settlements and facilities, transportation, pipelines, boundaries and political divisions, landforms, vegetation and soil quality, geophysical fields, military-specific and geology.

[0035] Among them, the first-level classification of geographical elements is divided into fine-grained levels according to geographical location and spatial distribution, which may include:

[0036] Based on the geographical location and spatial distribution, the geographical elements after each first-level classification are subdivided into second-level geographical element subclasses, third-level geographical element subclasses and fourth-level geographical element subclasses according to the hierarchical relationship;

[0037] An orderly thematic geographic element classification system is formed based on the first-level classification of geographic elements, the second-level subclasses of geographic elements, the third-level subclasses of geographic elements and the fourth-level subclasses of geographic elements.

[0038] The orderly thematic geographic element classification system constructed based on the primary classification of geographic elements can be shown in Table 1:

[0039] Table 1 Example of hierarchical classification of thematic geographic elements

[0040]

[0041]

[0042]

[0043]

[0044]

[0045]

[0046]

[0047]

[0048]

[0049]

[0050]

[0051] It should be noted that this level of classification can be adjusted by merging, adding, reducing, deleting, etc. according to specific thematic applications.

[0052] S102. Construct a geographic element knowledge ontology library based on each geographic element subclass, wherein the knowledge ontology library includes an ontology object, an ontology attribute set, and an ontology relationship set. The ontology object is a model for describing a geographic space object, the ontology attribute set is used to describe the characteristic attributes of the ontology object, and the ontology relationship set is used for the association relationship between each ontology object.

[0053] Specifically, the geographic element knowledge ontology library is constructed based on each geographic element subclass, which can be designed to include:

[0054] Extracting ontology objects according to each geographic element subclass in the geographic space data, and constructing ontology object attribute sets according to the common attributes and unique attributes of the ontology object type, wherein the common attributes are feature descriptions common to the ontology objects in the geographic space, and the unique attributes are feature descriptions unique to each ontology object category in the geographic space;

[0055] Construct an ontology object relationship set according to the ontology spatial relationship, temporal relationship and semantic relationship in the geographic spatial data, wherein the spatial relationship includes spatial topological relationship, spatial distance relationship and spatial orientation relationship, the temporal relationship includes the time sequence before and after the ontology object is changed, and the semantic relationship includes hierarchical relationship, dependency relationship and equivalent relationship;

[0056] The geographic feature knowledge ontology database is constructed based on ontology objects, ontology object attribute sets and ontology object relationship sets.

[0057] The hierarchical relationship may include: a whole relationship for the ontology object to belong to or include the corresponding structure / terrain, a genus-species relationship for describing the type to which the ontology object belongs or includes, and an instance relationship for the ontology object to belong to or include a model concept.

[0058] The attribute set mainly includes the common attributes of various types of data and the unique attributes of specific types. Among them, the common attributes refer to the attributes of the subject element field, and the unique attributes refer to the attributes of more specific knowledge categories. For example, the common attributes of the water system are names, the unique attributes of rivers are length and width, the unique attributes of lakes are water quality, and the unique attributes of reservoirs are storage capacity. The common attributes and unique attributes can be shown in Table 2 and Table 3.

[0059] Table 2 Common attributes of thematic geographic element knowledge data

[0060]

[0061] Table 3 Unique attributes of thematic geographic element knowledge data

[0062]

[0063]

[0064] The types of relational knowledge mainly include spatial relations, temporal relations, semantic relations and the like. Spatial relations include spatial topological relations, spatial distance relations, and spatial orientation relations; semantic relations include hierarchical relations, dependency relations, and equivalence relations.

[0065] Among them, spatial relations include spatial topological relations, spatial distance relations, and spatial orientation relations. Spatial topological relations include spatial inclusion, being included, intersection, overlap, adjacency, coincidence, and coverage. Spatial distance relations include very close, close, moderate, far, and far. Spatial orientation relations include eight directions (four directions / sixteen directions) and superior and subordinate relations.

[0066] The time relationship includes the time before and after the entity is changed.

[0067] Semantic relations include hierarchical relations, dependency relations, and equivalence relations. Hierarchical relations include whole relations, genus-species relations, and instance relations. Whole relations may include (structure / terrain) belonging, (structure / terrain) containing, entity aggregation, and entity containing. Genus-species relations may include type belonging and type containing. Instance relations may include concept belonging and concept containing. Dependency relations describe the relationship that a spatial object depends on or is depended on. Equivalence relations describe the relationship between synonyms, near-synonyms, and antonyms between spatial objects.

[0068] The knowledge of the object relationships of the thematic geographic element knowledge data ontology can be shown in the example of Table 4.

[0069] Table 4 Thematic geographic element knowledge data relationship knowledge (partial)

[0070]

[0071]

[0072]

[0073]

[0074]

[0075]

[0076]

[0077]

[0078]

[0079]

[0080]

[0081]

[0082] S103. Extract thematic geographic entities based on the geographic element knowledge ontology library, obtain thematic geographic entity relationships using thematic geographic entities as spatial objects, and obtain thematic geographic entity attributes based on the characteristics of thematic geographic entities themselves. The thematic geographic entity relationships include spatial relationships, temporal relationships, and semantic relationships.

[0083] Specifically, the extraction of geographic entities based on the geographic element knowledge ontology library can be designed to include:

[0084] Obtain basic geographic information vector data, and obtain thematic geographic element knowledge ontology database data based on the basic geographic information vector data;

[0085] Thematic geographic entities are extracted from the thematic geographic element knowledge ontology database data to obtain thematic geographic entity attributes and thematic geographic entity relationships based on the thematic geographic entities.

[0086] When extracting thematic geographic entities and their attributes and relationships, such as taking the Han River as a geographic entity and taking the geographic entity as a spatial object, we extract the associated spatial relationships (such as the Han River merging into the Yangtze River) and temporal relationships (such as the data acquisition time July 2023), and extract attributes based on the characteristics of the geographic entity itself (such as the river length of the geographic entity object "Han River", water system name code and other attribute information).

[0087] S104. Construct thematic geospatial knowledge triples based on thematic geographic entities, thematic geographic entity attributes and thematic geographic entity relationships, store the thematic geospatial knowledge triples in the Neo4 graph database and form the thematic geographic element data knowledge graph, so as to use the thematic geographic element data knowledge graph to search and query the geospatial data.

[0088] According to the extracted thematic geographic entities, attributes and relationships, knowledge triples are constructed; wherein the knowledge triples are "{entity(attribute:attribute value)}-{relationship}-{entity(attribute:attribute value)}"; entities correspond to thematic geographic entities in the thematic geographic element knowledge ontology library; attributes and attribute values ​​correspond to the attributes and attribute values ​​of entities; relationships are the corresponding relationships between two entities; the knowledge triples are stored in the Neo4 graph database to obtain the knowledge graph of thematic geographic element data; wherein the knowledge graph of the thematic geographic element data can be used for retrieval and query.

[0089] The data layer of the thematic geographic element knowledge graph is composed of entities, entity attributes, and entity relationships. Each piece of knowledge is composed of knowledge triples, namely, "{entity (attribute: attribute value)}-{relationship}-{entity (attribute: attribute value)}", where attributes and attribute values ​​correspond to entity attributes and attribute values. The geographic entities, relationships, and attributes obtained by knowledge extraction form knowledge triples based on geographical characteristics, which are sorted and classified for the next step of knowledge storage, such as: {Han River (water system name code: XXX)}-{into}-{Yangtze River (water system name code: XXX)}.

[0090] The table of the knowledge triples is converted into a CSV file, and then the CSV file is imported into the Neo4j graph database using C++ statements: entity nodes are created based on the Neo4j graph database into which the CSV file is imported; wherein the node names correspond to entities in the knowledge triples; relationships between entities are created based on the Neo4j graph database into which the CSV file is imported, and a knowledge graph of thematic geographic feature data is obtained.

[0091] like Figure 2 As shown in the figure, an example of a knowledge graph of a certain area in Beijing generated by Neo4j graph database can be used to add, delete and adjust the entities of thematic geospatial data such as water systems through layer management, select basic geographic information and geospatial data from other information source platforms through data source management, form a knowledge graph through geographic element classification and entity attributes and relationship extraction, and maintain entity attributes and entity relationships using entity relationship attribute tables, so as to make full use of geospatial knowledge to realize the transformation of geospatial data into knowledge data, and realize the dynamic retrieval and query of spatial objects in related thematic geospatial data using geospatial knowledge graphs.

[0092] Furthermore, based on the above method, an embodiment of the present invention also provides a geographic spatial data knowledge graph construction system based on geographic element classification, comprising: a knowledge classification module, a knowledge base construction module, a knowledge extraction module and a knowledge display module, wherein:

[0093] A knowledge classification module is used to classify geographical elements into primary categories according to geographical location and spatial distribution, and to divide the primary categories of geographical elements into fine-grained hierarchical categories according to geographical location and spatial distribution in each primary category of geographical elements, so as to obtain subcategories of each geographical element in the primary category of geographical elements, wherein the geographical elements are geographical factors used to describe differences between geographical types and / or geographical areas;

[0094] A knowledge base construction module is used to construct a geographic element knowledge ontology base based on each geographic element subclass. The knowledge ontology base includes an ontology object, an ontology attribute set, and an ontology relationship set. The ontology object is a model used to describe a geographic space object. The ontology attribute set is used to describe the characteristic attributes of the ontology object. The ontology relationship set is used to describe the association relationship between each ontology object.

[0095] The knowledge extraction module is used to extract thematic geographic entities based on the geographic element knowledge ontology library, obtain thematic geographic entity relationships using thematic geographic entities as spatial objects, and obtain thematic geographic entity attributes based on the characteristics of thematic geographic entities themselves. The thematic geographic entity relationships include spatial relationships, temporal relationships, and semantic relationships.

[0096] The knowledge display module is used to construct thematic geospatial knowledge triples based on thematic geographic entities, thematic geographic entity attributes and thematic geographic entity relationships, store the thematic geospatial knowledge triples in the Neo4 graph database and form the thematic geographic element data knowledge graph, so as to use the thematic geographic element data knowledge graph to search and query the geospatial data.

[0097] The above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, it should be understood by those skilled in the art that any person familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or perform equivalent replacements on some of the technical features thereof; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for constructing a knowledge graph of geographic spatial data based on geographic element classification, characterized in that: Include: Classify the geographical elements into primary categories according to their geographical location and spatial distribution, and divide the primary categories of the geographical elements into fine-grained hierarchical categories according to their geographical location and spatial distribution, so as to obtain subcategories of the geographical elements in the primary categories of the geographical elements, wherein the geographical elements are geographical factors used to describe differences between geographical types and / or geographical areas; Constructing a geographic element knowledge ontology library according to each geographic element subclass, the knowledge ontology library includes an ontology object, an ontology attribute set and an ontology relationship set, the ontology object is a model for describing a geographic space object, the ontology attribute set is used to describe the characteristic attributes of the ontology object, and the ontology relationship set is used for the association relationship between each ontology object; Extracting thematic geographic entities based on geographic element knowledge ontology, taking thematic geographic entities as spatial objects to obtain thematic geographic entity relationships, and obtaining thematic geographic entity attributes based on the characteristics of thematic geographic entities themselves, wherein the thematic geographic entity relationships include spatial relationships, temporal relationships, and semantic relationships; Thematic geospatial knowledge triples are constructed according to thematic geographic entities, thematic geographic entity attributes and thematic geographic entity relationships. The thematic geospatial knowledge triples are stored in the Neo4j graph database and form a thematic geographic element data knowledge graph, so that the thematic geographic element data knowledge graph can be used to retrieve and query geospatial data.

2. The method for constructing a geographic spatial data knowledge graph based on geographic element classification according to claim 1, characterized in that: The first-level classification of geographical elements includes but is not limited to: positioning basis, water system, settlements and facilities, transportation, pipelines, boundaries and political divisions, landforms, vegetation and soil quality, geophysical fields, military-specific and geology.

3. The method for constructing a geographic spatial data knowledge graph based on geographic element classification according to claim 1 or 2, characterized in that: The first-level classification of geographic elements is divided into fine-grained levels based on geographical location and spatial distribution, including: Based on the geographical location and spatial distribution, the geographical elements after each first-level classification are subdivided into second-level geographical element subclasses, third-level geographical element subclasses and fourth-level geographical element subclasses according to the hierarchical relationship; An orderly thematic geographic element classification system is formed based on the first-level classification of geographic elements, the second-level subclasses of geographic elements, the third-level subclasses of geographic elements and the fourth-level subclasses of geographic elements.

4. The method for constructing a geographic spatial data knowledge graph based on geographic element classification according to claim 1, characterized in that: The geographic element knowledge ontology library is constructed based on each geographic element subclass, including: Extracting ontology objects according to each geographic element subclass in the geographic space data, and constructing ontology object attribute sets according to the common attributes and unique attributes of the ontology object type, wherein the common attributes are feature descriptions common to the ontology objects in the geographic space, and the unique attributes are feature descriptions unique to each ontology object category in the geographic space; Construct an ontology object relationship set according to the ontology spatial relationship, temporal relationship and semantic relationship in the geographic spatial data, wherein the spatial relationship includes spatial topological relationship, spatial distance relationship and spatial orientation relationship, the temporal relationship includes the time sequence before and after the ontology object is changed, and the semantic relationship includes hierarchical relationship, dependency relationship and equivalent relationship; The geographic feature knowledge ontology database is constructed based on ontology objects, ontology object attribute sets and ontology object relationship sets.

5. The method for constructing a geographic spatial data knowledge graph based on geographic element classification according to claim 4 is characterized in that: The hierarchical relationships include: a whole relationship for the ontology object to belong to or include the corresponding structure / terrain, a genus-species relationship for describing the type to which the ontology object belongs or includes, and an instance relationship for the ontology object to belong to or include a model concept.

6. The method for constructing a geographic spatial data knowledge graph based on geographic element classification according to claim 1, characterized in that: Extract geographic entities based on geographic feature knowledge ontology library, including: Obtain basic geographic information vector data, and obtain thematic geographic element knowledge ontology database data based on the basic geographic information vector data; Thematic geographic entities are extracted from the thematic geographic element knowledge ontology database data to obtain thematic geographic entity attributes and thematic geographic entity relationships based on the thematic geographic entities.

7. The method for constructing a geographic spatial data knowledge graph based on geographic element classification according to claim 1 or 6, characterized in that: The triple of geographic spatial knowledge is expressed as: {entity (attribute: attribute value)}-{relationship}-{entity (attribute: attribute value)}, where the entity is the thematic geographic entity in the thematic geographic element knowledge ontology library, the attributes and attribute values ​​correspond to the attributes and attribute values ​​of the thematic geographic entity, and the relationship is the correspondence between the previous and next two thematic geographic entities.

8. A geographic spatial data knowledge graph construction system based on geographic element classification, characterized in that: It includes: knowledge classification module, knowledge base construction module, knowledge extraction module and knowledge display module, among which, A knowledge classification module is used to classify geographical elements into primary categories according to geographical location and spatial distribution, and to divide the primary categories of geographical elements into fine-grained hierarchical categories according to geographical location and spatial distribution in each primary category of geographical elements, so as to obtain subcategories of each geographical element in the primary category of geographical elements, wherein the geographical elements are geographical factors used to describe differences between geographical types and / or geographical areas; A knowledge base construction module is used to construct a geographic element knowledge ontology base based on each geographic element subclass. The knowledge ontology base includes an ontology object, an ontology attribute set, and an ontology relationship set. The ontology object is a model used to describe a geographic space object. The ontology attribute set is used to describe the characteristic attributes of the ontology object. The ontology relationship set is used to describe the association relationship between each ontology object. The knowledge extraction module is used to extract thematic geographic entities based on the geographic element knowledge ontology library, obtain thematic geographic entity relationships using thematic geographic entities as spatial objects, and obtain thematic geographic entity attributes based on the characteristics of thematic geographic entities themselves. The thematic geographic entity relationships include spatial relationships, temporal relationships, and semantic relationships. The knowledge display module is used to construct thematic geospatial knowledge triples based on thematic geographic entities, thematic geographic entity attributes and thematic geographic entity relationships, store the thematic geospatial knowledge triples in the Neo4j graph database and form the thematic geographic element data knowledge graph, so as to use the thematic geographic element data knowledge graph to search and query the geospatial data.

9. An electronic device, characterized in that: include: at least one processor, and a memory coupled to the at least one processor; The memory stores a computer program, and the computer program can be executed by the at least one processor to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the method according to any one of claims 1 to 7 can be implemented.

Images