Method and system for extracting geographic element knowledge of target area

Abstract

The invention relates to the technical field of geographic knowledge, in particular to a target area geographic element knowledge extraction method and system.The target area geographic element knowledge extraction method comprises the steps that a geographic element basic database is constructed according to geographic element source data, and the geographic element source data comprises at least one type of thematic geographic data and basic surveying and mapping geographic data; constructing a geographic element attribute supplement database according to open source geographic element data, wherein the open source geographic element data is geographic element data disclosed by an information source platform; carrying out attribute supplement on the geographic element basic database by utilizing the geographic element attribute supplement database; performing spatial dimension associated information mining on the geographic element source data to obtain geographic element relationship knowledge; and constructing a geographic element knowledge graph according to the geographic element attribute knowledge and the geographic element relationship knowledge, and displaying the geographic element data in a knowledge graph form. According to the method, the problems of incompleteness, attribute information loss and the like caused by lack of spatial relationship description in existing knowledge extraction can be improved.

Description

Technical Field

[0001] The present invention relates to the field of geographical knowledge technology, and in particular to a method and system for extracting geographical element knowledge of a target area. Background Art

[0002] With the popularization of the Internet and the Internet of Things, more and more data resources have emerged. Faced with the explosive growth of data, there are problems such as "massive data, information explosion, and difficulty in obtaining knowledge". Geographical element knowledge is to deeply understand and grasp the properties, characteristics, functions and other attribute characteristics of each type of geographical element. Geographical element attributes refer to the characteristics of the nature, characteristics, functions and other aspects of geographical elements. The analysis of the attributes of geographical elements can deepen the understanding of the internal laws of geographical elements and provide an important basis for conducting regional geographical research and solving practical problems. Taking hydrological elements as an example, its main attributes include the length of the river, the basin area, the flow, the sand content, etc. These attributes directly affect the river's recharge characteristics, runoff conditions, and the impact on the regional environment and human activities. For example, the main attributes of soil elements include soil texture, structure, fertility, pH, drainage performance, etc. These attributes determine the physical and chemical properties of the soil, which in turn affects the growth and development of vegetation and agricultural production conditions.

[0003] In addition to understanding the attributes of geographical elements, geographical element knowledge also requires analyzing the intricate relationships between different geographical elements. Geographical element relationships refer to the mutual influence and constraints formed by the exchange and connection of different geographical elements in terms of matter, energy, information, etc. In the real geographical environment, various geographical elements do not exist in isolation, but are intertwined and interact with each other to jointly shape the complex and diverse geographical landscape. For example, there is a close relationship between topography and climate. The height, undulation, and slope of the terrain directly affect the spatial distribution of climate elements, such as precipitation and vertical differentiation of temperature; conversely, climate conditions, especially precipitation and temperature conditions, will also have an important impact on the development and evolution of terrain by affecting processes such as weathering, erosion, and transportation. For another example, there is also a causal relationship between hydrological elements and vegetation elements. On the one hand, hydrological conditions such as the distribution of rivers and lakes directly affect the type, distribution, and growth of regional vegetation; on the other hand, the type and coverage of vegetation affect the regional hydrological cycle and water resource distribution by affecting processes such as water interception, evapotranspiration, and infiltration.

[0004] With the rapid development of artificial intelligence technology, the expression of geographic feature knowledge is also constantly innovating. Although traditional data models and symbol systems have been widely used in geographic information systems, new knowledge expression methods are constantly emerging in the face of increasingly complex geospatial data and application needs. Knowledge graph is a knowledge expression method that has attracted much attention in recent years. It represents the semantic relationship between geographic entities in the form of a graph, with nodes representing entities and edges representing the relationship between entities. Knowledge graph can effectively organize and integrate heterogeneous geospatial data and support complex semantic queries and reasoning. However, existing general knowledge graphs are mostly built based on non-spatial data such as Wikipedia, with low spatial knowledge coverage and the problem of missing Chinese attributes and coordinate information. In summary, the existing geographic feature knowledge has the problem of "data explosion and lack of knowledge" in the extraction process, and the existing knowledge graph technology generally has the problem of missing spatial relationship description in the field of geography. Summary of the invention

[0005] To this end, the present invention provides a method and system for extracting knowledge of geographic elements in a target area, which solves the problem of unsatisfactory conversion of existing geographic element knowledge data into knowledge, improves the comprehensiveness and accuracy of knowledge extraction of geographic elements in the target area, and can be deployed and implemented in geographic information system application scenarios.

[0006] According to the design scheme provided by the present invention, on the one hand, a method for extracting knowledge of geographical elements in a target area is provided, comprising:

[0007] Obtaining geographic element source data of the target area, and constructing a geographic element basic database based on the geographic element source data, wherein the geographic element source data includes at least one type of thematic geographic data and basic surveying and mapping geographic data of the target area, wherein the geographic data thematic type includes hydrological thematic type, soil thematic type, terrain thematic type, climate thematic type and vegetation thematic type;

[0008] Obtaining open source geographic element data, and constructing a geographic element attribute supplementary database based on the open source geographic element data, wherein the open source geographic element data is geographic element data disclosed by the information source platform;

[0009] Use the geographic element attribute supplement database to supplement the attributes of the geographic element basic database to obtain geographic element attribute knowledge;

[0010] Mining spatial dimension association information of geographic element source data to obtain geographic element relationship knowledge, wherein the spatial dimension association information includes spatial topological relationship, spatial distance relationship and spatial orientation relationship;

[0011] A geographic element knowledge graph is constructed based on the knowledge of geographic element attributes and geographic element relationship, and the geographic element data is displayed in the form of a knowledge graph, where the nodes of the geographic element knowledge graph represent geographic element entities with relevant attributes and attribute values, and the edges represent the relationships between corresponding geographic element entities.

[0012] As a method for extracting knowledge of geographical elements in a target area of ​​the present invention, further, a basic database of geographical elements is constructed based on the source data of geographical elements, including:

[0013] Extracting geographic element categories, semantic structures and attribute contents from geographic element source data, and constructing a mapping relationship template, wherein the mapping relationship template is used to map and fuse the geographic element source data into structured data;

[0014] Mapping relationship templates are used to map at least one type of thematic geographic data and basic surveying and mapping geographic data, and geographic element structured data are obtained through data matching and data fusion to use the geographic element structured data as a geographic element basic database.

[0015] As a method for extracting knowledge of geographic elements in a target area of ​​the present invention, further, a geographic element attribute supplementary database is constructed based on open source geographic element data, including:

[0016] Collect open source geographic element data disclosed by the information source platform, and extract geographic element names and corresponding relationships through thematic types in the geographic element source data;

[0017] The open source geographic feature data is preprocessed, and keywords are extracted from the preprocessed open source geographic feature data based on the geographic feature names and corresponding relationships, attribute supplementary data in the open source geographic feature data is obtained, and a geographic feature attribute supplementary database is constructed based on the attribute supplementary data.

[0018] As a method for extracting knowledge of geographical elements in a target area of ​​the present invention, further, a geographical element attribute supplement database is used to supplement the attributes of the geographical element basic database, including:

[0019] Use the geographic element names in the geographic element basic database as the geographic element entity name dictionary;

[0020] Perform part-of-speech tagging on the geographic feature attribute supplementary database and obtain words with specified parts of speech, perform named entity matching and recognition on the words with specified parts of speech based on the geographic feature entity name dictionary, and obtain supplementary attributes of the corresponding geographic feature entities in the geographic feature attribute supplementary database, so as to use the supplementary attributes to supplement the attributes of the entities in the geographic feature basic database and obtain geographic feature attribute knowledge.

[0021] As a method for extracting knowledge of geographic elements in a target area of ​​the present invention, further, spatial dimension association information mining is performed on the source data of geographic elements, including:

[0022] A 9-intersection model based on dimension expansion is adopted to construct a relationship matrix through the internal, boundary and external intersection dimensions of geographic element data. The relationship matrix is ​​used to obtain the spatial topological relationship of geographic elements in the source data of geographic elements, which is used to describe the proximity and association degree between geographic elements.

[0023] Obtain the distance between the neighboring geographic elements in the cache range and the specified target, and record the spatial distance relationship of the geographic elements in the cache range, the spatial distance relationship includes the number of geographic elements in the cache range, the information of the specified geographic elements sorted from far to near, and the distance value;

[0024] The spatial range relationship of geographic elements is obtained by combining the spatial distance relationship of geographic elements and using the eight-direction cone model and the tic-tac-toe model. The eight-direction cone model is used to extract the spatial direction relationship between geographic elements when the distance between geographic elements is greater than the specified distance threshold, and the tic-tac-toe model is used to extract the spatial direction relationship between geographic elements when the distance between geographic elements is not greater than the specified distance threshold.

[0025] As the target area geographic element knowledge extraction method of the present invention, further, recording the spatial distance relationship of the geographic elements within the cache range also includes:

[0026] After sorting the distances from far to near, record the top N geographic elements; if there are less than N geographic elements in the cache range, record all geographic elements; if there are no adjacent geographic elements in the cache range, increase the distance to the specified target and record the nearest geographic element information and distance value;

[0027] A fixed value is used as the designated distance threshold within the urban area, and a preset distance threshold is used as the designated distance threshold between cities. The preset distance threshold is set according to the speed of the designated transportation tool.

[0028] As a method for extracting knowledge of geographical elements in a target area of ​​the present invention, further, an eight-direction cone model and a tic-tac-toe model are used to obtain the spatial range relationship of geographical elements, including:

[0029] Calculate the coordinates of the centroid of the minimum convex hull of the source and target of the geographic element in the spatial dimension, and obtain the orientation relationship of the centroid relative to the reference target based on the coordinates of the centroid;

[0030] When both the reference target and the source target are point data or the qualitative distance between the reference target and the source target is greater than the specified distance threshold, the eight-direction cone model is used to extract the spatial orientation relationship. Otherwise, the tic-tac-toe model is used to extract the spatial orientation relationship.

[0031] In another aspect, the present invention further provides a target area geographic element knowledge extraction system, comprising: a basic data acquisition module, a supplementary data acquisition module, an attribute knowledge extraction module, a relationship knowledge extraction module and a geographic element display module, wherein:

[0032] A basic data acquisition module is used to acquire the source data of geographic elements in the target area and construct a basic database of geographic elements based on the source data of geographic elements, wherein the source data of geographic elements include at least one type of thematic geographic data of the target area and basic surveying and mapping geographic data, wherein the thematic types of geographic data include hydrological thematic type, soil thematic type, terrain thematic type, climate thematic type and vegetation thematic type;

[0033] A supplementary data acquisition module is used to acquire open source geographic element data and construct a geographic element attribute supplementary database based on the open source geographic element data, wherein the open source geographic element data is the geographic element data disclosed by the information source platform;

[0034] The attribute knowledge extraction module is used to supplement the attributes of the geographic element basic database using the geographic element attribute supplement database to obtain the geographic element attribute knowledge;

[0035] The relationship knowledge extraction module is used to mine the spatial dimension relationship information of the geographic element source data to obtain the geographic element relationship knowledge, wherein the spatial dimension relationship information includes the spatial topological relationship, the spatial distance relationship and the spatial orientation relationship;

[0036] The geographic element display module is used to construct a geographic element knowledge graph based on geographic element attribute knowledge and geographic element relationship knowledge, and to display geographic element data in the form of a knowledge graph, where the nodes of the geographic element knowledge graph represent geographic element entities with relevant attributes and attribute values, and the edges represent the relationships between corresponding geographic element entities.

[0037] Beneficial effects of the present invention:

[0038] The present invention extracts and reorganizes the attribute content of geographic elements in various thematic original data sources, and introduces data from public information source platforms such as the Internet to supplement the attributes of thematic geographic element data, so as to form attribute knowledge of thematic geographic elements; the spatial topological relationship, spatial distance relationship, spatial orientation relationship and other related information of thematic geographic elements are mined to form the relationship knowledge of thematic geographic elements; a knowledge graph is formed based on the attribute knowledge and relationship knowledge data, so as to display the thematic geographic element information using the knowledge graph, thereby improving the problems of incompleteness and missing attribute information caused by the lack of spatial relationship description in the extraction of geographic element knowledge in thematic target areas of the prior art, and can accurately and efficiently realize the transformation of thematic geographic element data into knowledge, which is convenient for deployment and implementation in geographic information system application scenarios, and has good application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a schematic diagram of the target area geographical element knowledge extraction process in the embodiment;

[0040] Figure 2 This is a schematic diagram of the open source data acquisition process in the embodiment;

[0041] Figure 3 It is a schematic diagram of the structure of the eight-direction cone model in the embodiment;

[0042] Figure 4 FIG. 2 is a schematic diagram of the direction relationship model structure in the embodiment. DETAILED DESCRIPTION

[0043] 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.

[0044] In view of the problem that existing geographical element knowledge lacks spatial relationships, the present invention embodiment, see Figure 1 As shown, a method for extracting knowledge of geographical elements in a target area is provided, comprising:

[0045] S101. Obtain geographic element source data of the target area, and construct a geographic element basic database based on the geographic element source data, wherein the geographic element source data includes at least one type of thematic geographic data and basic surveying and mapping geographic data of the target area, wherein the geographic data thematic types include hydrological thematic type, soil thematic type, terrain thematic type, climate thematic type and vegetation thematic type.

[0046] Specifically, by collecting various types of thematic geographic data and basic surveying and mapping geographic data, and extracting the categories, semantic structures and attribute contents of geographic elements in the source data of geographic elements, a mapping relationship template is constructed, and the mapping relationship template is used to map and fuse the source data of geographic elements into structured data; the mapping relationship template is used to perform data mapping on at least one type of thematic geographic data and basic surveying and mapping geographic data, and the geographic element structured data is obtained through data matching and data fusion, so as to use the geographic element structured data as the geographic element basic database. The geographic elements include relevant geographic objects such as points, lines, surfaces and bodies in geographic space data, which can be specific physical objects in geographic space, such as buildings, roads, rivers, etc., or abstract concepts, such as administrative districts, climate regions, etc. The geographic elements can be represented by geometric elements such as points, lines, surfaces, etc., or by adding geographic attributes such as names, classifications, and uses.

[0047] S102: Obtain open source geographic element data, and construct a geographic element attribute supplementary database based on the open source geographic element data, wherein the open source geographic element data is geographic element data disclosed by an information source platform.

[0048] Content management frameworks, document information search technology, big data mining, web crawlers, natural language processing and other methods can be used to conduct real-time capture and analysis of large-scale massive information from news pages, online encyclopedias, social networks, data portals, professional literature and other information sources, so as to collect open source geographic feature data disclosed by information source platforms; extract geographic feature names and geographic feature correspondences through thematic types in geographic feature source data; preprocess open source geographic feature data, and extract keywords from the preprocessed open source geographic feature data based on geographic feature names and correspondences, obtain attribute supplementary data in the open source geographic feature data, and build a geographic feature attribute supplementary database based on the attribute supplementary data.

[0049] Open source data mainly refers to various public websites and platforms. Based on the openness, transparency, and collaboration of the platforms, the rich, real-time geographic information contained therein can be used to supplement data attributes and enrich the hierarchy of knowledge. The feature names and corresponding relationships are extracted through the category information of geographic feature data. The parsed open source data is preprocessed by word segmentation, stop word removal, and word frequency statistics to extract keywords. Based on open source data and entity names, web crawling technology is used to simulate human browsing behavior, starting from one or more initial web pages (seed pages), traversing web pages on the Internet to extract the required information.

[0050] like Figure 2 As shown, in the open source data acquisition process, different websites can write different scripts and use focused crawler technology. The focused crawler is an automated tool for crawling specific topics or fields. It can analyze and filter web pages and data to capture content and data that are highly relevant to the preset topic.

[0051] S103. Use the geographic element attribute supplement database to supplement the attributes of the geographic element basic database to obtain geographic element attribute knowledge.

[0052] Specifically, the names of geographic elements in the geographic element basic database are used as the geographic element entity name dictionary; part-of-speech tagging is performed on the geographic element attribute supplementary database and words with specified parts of speech are obtained, and named entity matching and recognition are performed on the words with specified parts of speech based on the geographic element entity name dictionary to obtain supplementary attributes of the corresponding geographic element entities in the geographic element attribute supplementary database, so as to use the supplementary attributes to supplement the attributes of the entities in the geographic element basic database and obtain geographic element attribute knowledge.

[0053] S104, mining spatial dimension association information on geographic element source data to obtain geographic element relationship knowledge, wherein the spatial dimension association information includes spatial topological relationship, spatial distance relationship and spatial orientation relationship.

[0054] Specifically, a 9-intersection model based on dimensional expansion can be adopted and a relationship matrix can be constructed through the internal, boundary and external intersection dimensions of geographic element data. The spatial topological relationship of geographic elements in the geographic element source data used to describe the proximity and association degree between geographic elements can be obtained by using the relationship matrix; the distance between the adjacent geographic elements and the specified target within the cache range is obtained, and the spatial distance relationship of the geographic elements within the cache range is recorded, and the spatial distance relationship includes the number of geographic elements within the cache range, the specified geographic element information sorted from far to near, and the distance value; the spatial distance relationship of geographic elements is combined and an eight-directional cone model and a tic-tac-toe model are used to obtain the spatial range relationship of geographic elements. The eight-directional cone model is used to extract the spatial direction relationship between geographic elements when the distance between geographic elements is greater than a specified distance threshold, and the tic-tac-toe model is used to extract the spatial direction relationship between geographic elements when the distance between geographic elements is not greater than a specified distance threshold.

[0055] After the distances are sorted from far to near, the top N geographic elements are recorded; if there are less than N geographic elements within the cache range, all geographic elements are recorded; if there are no adjacent geographic elements within the cache range, the distance to the specified target is increased, and the nearest geographic element information and distance value are recorded; and a fixed value is used as the specified distance threshold within the urban area, and a preset distance threshold is used between cities as the specified distance threshold, and the preset distance threshold is set according to the speed of the specified transportation tool.

[0056] Spatial topological relationships include: spatial inclusion, being included, intersection, overlap, proximity, coincidence, and coverage. Topological relationships express the proximity and association between elements. The 9-intersection model based on dimensional expansion can be used to construct a relationship matrix through the dimensions of the interior (interior, I), boundary (boundary, B), and exterior (exterior, E) of the element data, as shown in the following formula:

[0057]

[0058] Extract the topological relationship of elements under the hierarchical constraints of spatial cognition.

[0059] Spatial distance relationships include very close, near, moderate, far, and far. They express the relationship between geographic elements in terms of distance. They can be described qualitatively by very close, near, moderate, far, and far, or quantitatively by precise numerical values. The scale of geographic spatial data varies, and the concept of distance is subjective to a certain extent. Qualitative descriptions can be better associated with physical distances under specific scales and specific needs. Therefore, different distance thresholds can be set according to different layers. In practical applications, there are often needs to find a certain type of element closest to the target, the number of a certain type of element within the target range, etc., which is most obvious in cities. A spatial cache threshold is established to calculate the distance between the neighboring elements and the target within the buffer range, and the number of elements within the range, the feature information of the top 3 elements (if there are less than 3, take all) ranked from far to near, and the distance values ​​are recorded; if there are no neighboring elements within the buffer range, the distance search is expanded, and the nearest feature information and distance data are recorded; in addition, the distance threshold between cities is different from that within the city. The minimum speed of high-speed rail of 250KM / h is used as the judgment standard between cities, and the high-speed rail running for 0.1h is qualitatively described as very close (within about 25km), running for 1h is close (within about 250km), running for 2h is moderate (within 500km), running for 5h is far (within about 1250km), and other distances are far.

[0060] The distance calculation rules between geographic elements can be summarized as follows: the distance between two points is the straight line connecting the two points. The distance from a point to a straight line is the distance from the point to the perpendicular line or the nearest vertex of the straight line. The distance between broken lines depends on the vertex of the line segment. As shown in Table 1, the spatial distance relationship of geographic elements in a certain area of ​​Zhengzhou obtained by using this rule is shown.

[0061] Table 1 Spatial distance relationship

[0062]

[0063]

[0064]

[0065]

[0066] The spatial orientation relationship includes eight directions (four directions / sixteen directions) and superior-female relationships. The orientation relationship expresses the orientation description of the geographic elements in the spatial dimension. Combined with the spatial distance relationship, the eight-direction cone model and the "well" model are used to describe the orientation relationship. During extraction, the centroid point (POINT_X, POINT_Y) of the minimum convex hull of the source target is calculated, and the orientation relationship of the centroid point relative to the reference target is calculated. When the reference target and the source target are both point data, or the qualitative distance between the reference target and the source target is not "very close", the eight-direction cone model is used to extract the orientation relationship. Figure 3As shown in the figure, it is a schematic diagram of the eight-direction cone model. The corresponding relationship between the quantitative angle range and the directional direction is as follows Figure 3 And as shown in Table 2.

[0067] Table 2 Correspondence between quantitative angle and qualitative direction

[0068] Quantitative angle qualitative direction Quantitative angle qualitative direction -22.5°～22.5° north 157.5°~180°or -180°~-157.5° South 22.5°～67.5° northeast -157.5°～-112.5° southwest 67.5°～112.5° East -112.5°～-67.5° West 112.5°～157.5° southeast -67.5°～-22.5° northwest

[0069] When the distance relationship is "very close", the "well" model is used for relationship extraction, as follows Figure 4 As shown in the figure, the center O area is the minimum outer bounding rectangle of the reference target, and the four lines of the "well" are the maximum and minimum X and Y values ​​of the reference target respectively. By judging the size relationship between the coordinates POINT_X, POINT_Y of the source target particle and X_MIN, X_MAX, Y_MIN, and Y_MAX, the corresponding table of the qualitative direction of the well model is shown in Table 3, and the qualitative direction of the source target in the reference target is determined; when the source target particle is located in the center O area, it is considered that the two entities are very close, or are contained, and the eight-direction cone model is still used.

[0070] Table 3 Qualitative direction correspondence table of the “well” model

[0071]

[0072]

[0073] When both the reference target and the source target are point data or the qualitative distance between the reference target and the source target is greater than the specified distance threshold, the eight-direction cone model is used to extract the spatial orientation relationship. Otherwise, the tic-tac-toe model is used to extract the spatial orientation relationship.

[0074] S105. Construct a geographic element knowledge graph based on geographic element attribute knowledge and geographic element relationship knowledge, and display geographic element data in the form of a knowledge graph, wherein the nodes of the geographic element knowledge graph represent geographic element entities with relevant attributes and attribute values, and the edges represent the relationships between corresponding geographic element entities.

[0075] The data layer of the geographic feature 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.

[0076] Specifically, the knowledge extraction obtains the entities, relationships and attributes of geographic elements, and forms knowledge triples according to geographical features, which are sorted and classified for knowledge storage, for example: {Hanjiang River (water system name code: XXX)}-{into}-{Yangtze River (water system name code: XXX)}. 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: according to the Neo4j graph database imported with the CSV file, entity nodes are created; wherein the node name corresponds to the entity in the knowledge triple; according to the Neo4j graph database imported with the CSV file, the relationship between entities is created to obtain the knowledge graph of thematic geographic element data.

[0077] Furthermore, based on the above method, an embodiment of the present invention also provides a target area geographic element knowledge extraction system, comprising: a basic data acquisition module, a supplementary data acquisition module, an attribute knowledge extraction module, a relationship knowledge extraction module and a geographic element display module, wherein:

[0078] A basic data acquisition module is used to acquire the source data of geographic elements in the target area and construct a basic database of geographic elements based on the source data of geographic elements, wherein the source data of geographic elements include at least one type of thematic geographic data and basic surveying and mapping geographic data of the target area, wherein the thematic types of geographic data include hydrological thematic type, soil thematic type, terrain thematic type, climate thematic type and vegetation thematic type;

[0079] A supplementary data acquisition module is used to acquire open source geographic element data and construct a geographic element attribute supplementary database based on the open source geographic element data, wherein the open source geographic element data is the geographic element data disclosed by the information source platform;

[0080] The attribute knowledge extraction module is used to supplement the attributes of the geographic element basic database using the geographic element attribute supplement database to obtain the geographic element attribute knowledge;

[0081] The relationship knowledge extraction module is used to mine the spatial dimension relationship information of the geographic element source data to obtain the geographic element relationship knowledge, wherein the spatial dimension relationship information includes the spatial topological relationship, the spatial distance relationship and the spatial orientation relationship;

[0082] The geographic element display module is used to construct a geographic element knowledge graph based on geographic element attribute knowledge and geographic element relationship knowledge, and to display geographic element data in the form of a knowledge graph, where the nodes of the geographic element knowledge graph represent geographic element entities with relevant attributes and attribute values, and the edges represent the relationships between corresponding geographic element entities.

[0083] Unless otherwise specifically stated, the relative steps, numerical expressions and values ​​of the components and steps set forth in these embodiments do not limit the scope of the present invention.

[0084] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0085] The units and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A person of ordinary skill in the art may use different methods to implement the described functions for each specific application, but such implementation is not considered to be beyond the scope of the present invention.

[0086] Those skilled in the art will appreciate that all or part of the steps in the above method can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, such as a read-only memory, a disk or an optical disk. Optionally, all or part of the steps in the above embodiment can also be implemented using one or more integrated circuits, and accordingly, each module / unit in the above embodiment can be implemented in the form of hardware or in the form of software function modules. The present invention is not limited to any specific form of combination of hardware and software.

[0087] Finally, it should be noted that 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, ordinary technicians in the field should understand that any technician 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 make equivalent replacements for some of the technical features therein; 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 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 extracting knowledge of geographical elements in a target area, characterized in that: Include: Obtaining geographic element source data of the target area, and constructing a geographic element basic database based on the geographic element source data, wherein the geographic element source data includes at least one type of thematic geographic data and basic surveying and mapping geographic data of the target area, wherein the geographic data thematic type includes hydrological thematic type, soil thematic type, terrain thematic type, climate thematic type and vegetation thematic type; Obtaining open source geographic element data, and constructing a geographic element attribute supplementary database based on the open source geographic element data, wherein the open source geographic element data is geographic element data disclosed by the information source platform; Use the geographic element attribute supplement database to supplement the attributes of the geographic element basic database to obtain geographic element attribute knowledge; Mining spatial dimension association information of geographic element source data to obtain geographic element relationship knowledge, wherein the spatial dimension association information includes spatial topological relationship, spatial distance relationship and spatial orientation relationship; A geographic element knowledge graph is constructed based on the knowledge of geographic element attributes and geographic element relationship, and the geographic element data is displayed in the form of a knowledge graph, where the nodes of the geographic element knowledge graph represent geographic element entities with relevant attributes and attribute values, and the edges represent the relationships between corresponding geographic element entities.

2. The method for extracting knowledge of geographical elements of a target area according to claim 1, characterized in that: Construct a basic database of geographic elements based on the source data of geographic elements, including: Extracting geographic element categories, semantic structures and attribute contents from geographic element source data, and constructing a mapping relationship template, wherein the mapping relationship template is used to map and fuse the geographic element source data into structured data; Mapping relationship templates are used to map at least one type of thematic geographic data and basic surveying and mapping geographic data, and geographic element structured data are obtained through data matching and data fusion to use the geographic element structured data as a geographic element basic database.

3. The method for extracting knowledge of geographical elements of a target area according to claim 1, characterized in that: Based on open source geographic feature data, a supplementary database of geographic feature attributes is constructed, including: Collect open source geographic feature data published on the information source platform, and extract geographic feature names and corresponding relationships through thematic types in the geographic feature source data; The open source geographic feature data is preprocessed, and keywords are extracted from the preprocessed open source geographic feature data based on the geographic feature names and corresponding relationships, attribute supplementary data in the open source geographic feature data is obtained, and a geographic feature attribute supplementary database is constructed based on the attribute supplementary data.

4. The method for extracting knowledge of geographical elements of a target area according to claim 1, characterized in that: The geographic element attribute supplement database is used to supplement the attributes of the geographic element basic database, including: Use the geographical element names in the geographical element basic database as the geographical element entity name dictionary; Perform part-of-speech tagging on the geographic feature attribute supplementary database and obtain words with specified parts of speech, perform named entity matching and recognition on the words with specified parts of speech based on the geographic feature entity name dictionary, and obtain supplementary attributes of the corresponding geographic feature entities in the geographic feature attribute supplementary database, so as to use the supplementary attributes to supplement the attributes of the entities in the geographic feature basic database and obtain geographic feature attribute knowledge.

5. The method for extracting knowledge of geographical elements of a target area according to claim 1, characterized in that: Mining spatial dimension association information of geographic element source data, including: A 9-intersection model based on dimension expansion is adopted to construct a relationship matrix through the internal, boundary and external intersection dimensions of geographic element data. The relationship matrix is ​​used to obtain the spatial topological relationship of geographic elements in the source data of geographic elements, which is used to describe the proximity and association degree between geographic elements. Obtain the distance between the neighboring geographic elements in the cache range and the specified target, and record the spatial distance relationship of the geographic elements in the cache range, the spatial distance relationship includes the number of geographic elements in the cache range, the information of the specified geographic elements sorted from far to near, and the distance value; The spatial range relationship of geographic elements is obtained by combining the spatial distance relationship of geographic elements and using the eight-direction cone model and the tic-tac-toe model. The eight-direction cone model is used to extract the spatial direction relationship between geographic elements when the distance between geographic elements is greater than the specified distance threshold, and the tic-tac-toe model is used to extract the spatial direction relationship between geographic elements when the distance between geographic elements is not greater than the specified distance threshold.

6. The method for extracting knowledge of geographical elements of a target area according to claim 5, characterized in that: Records the spatial distance relationship of geographic features within the cache range, including: After sorting the distances from far to near, record the top N geographic elements; if there are less than N geographic elements in the cache range, record all geographic elements; if there are no adjacent geographic elements in the cache range, increase the distance to the specified target and record the nearest geographic element information and distance value; A fixed value is used as the designated distance threshold within the urban area, and a preset distance threshold is used as the designated distance threshold between cities. The preset distance threshold is set according to the speed of the designated transportation tool.

7. The method for extracting knowledge of geographical elements of a target area according to claim 5, characterized in that: The eight-direction cone model and the tic-tac-toe model are used to obtain the spatial range relationship of geographic elements, including: Calculate the coordinates of the centroid of the minimum convex hull of the source and target of the geographic element in the spatial dimension, and obtain the orientation relationship of the centroid relative to the reference target based on the coordinates of the centroid; When both the reference target and the source target are point data or the qualitative distance between the reference target and the source target is greater than the specified distance threshold, the eight-direction cone model is used to extract the spatial orientation relationship. Otherwise, the tic-tac-toe model is used to extract the spatial orientation relationship.

8. A target area geographical element knowledge extraction system, characterized in that: It includes: basic data acquisition module, supplementary data acquisition module, attribute knowledge extraction module, relationship knowledge extraction module and geographic element display module, among which, A basic data acquisition module is used to acquire the source data of geographic elements in the target area and construct a basic database of geographic elements based on the source data of geographic elements, wherein the source data of geographic elements include at least one type of thematic geographic data and basic surveying and mapping geographic data of the target area, wherein the thematic types of geographic data include hydrological thematic type, soil thematic type, terrain thematic type, climate thematic type and vegetation thematic type; A supplementary data acquisition module is used to acquire open source geographic element data and construct a geographic element attribute supplementary database based on the open source geographic element data, wherein the open source geographic element data is the geographic element data disclosed by the information source platform; The attribute knowledge extraction module is used to supplement the attributes of the geographic element basic database using the geographic element attribute supplement database to obtain the geographic element attribute knowledge; The relationship knowledge extraction module is used to mine the spatial dimension relationship information of the geographic element source data to obtain the geographic element relationship knowledge, wherein the spatial dimension relationship information includes the spatial topological relationship, the spatial distance relationship and the spatial orientation relationship; The geographic element display module is used to construct a geographic element knowledge graph based on geographic element attribute knowledge and geographic element relationship knowledge, and to display geographic element data in the form of a knowledge graph, where the nodes of the geographic element knowledge graph represent geographic element entities with relevant attributes and attribute values, and the edges represent the relationships between corresponding geographic element entities.

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