Natural resource monitoring pattern spot business association method and system based on knowledge graph

Abstract

In order to solve the problem that natural resource monitoring pattern spot data and business management requirements are disjointed and cannot be accurately connected, the invention discloses a natural resource monitoring pattern spot business association method and system based on a knowledge graph, and the method comprises the steps: obtaining the natural resource monitoring pattern spot data; analyzing an association relationship between the natural resource monitoring pattern spot data and a service association object, establishing a mapping relationship between a service management demand and an investigation monitoring object, and constructing a service concept ontology by using an ontology editor to describe an entity and define an object attribute; designing business atlas classes and key attributes and relationships thereof according to entity and object attributes, establishing a relationship model based on a graph database, and constructing a natural resource monitoring business knowledge atlas; and based on the constructed natural resource monitoring business knowledge graph, establishing a monitoring pattern spot automatic pushing model based on the business knowledge graph, and pushing a monitoring result to a management main body according to a business management requirement, thereby realizing accurate pushing and efficient application of the monitoring pattern spots.

Description

Technical Field

[0001] This invention relates to the field of natural resource monitoring and management, specifically to a method and system for business association of natural resource monitoring patches based on knowledge graphs. Background Technology

[0002] Unified natural resource surveys and monitoring are a crucial foundation for supporting natural resource management and ecological civilization construction. Achieving "one-time monitoring" to support "multiple natural resource operational management needs" is of great significance for building a unified natural resource survey and monitoring system. However, effectively linking natural resource monitoring maps with actual operational needs based on scientific cognitive and representational methods still faces both theoretical and technological challenges.

[0003] Natural resource survey and monitoring operations involve numerous applications with complex interrelationships and hierarchical relationships. From the perspective of monitoring map data, this data is updated rapidly with significant incremental changes; between 2022 and 2024, one province extracted over a million monitoring map data points. From the perspective of operational management objects, natural resource monitoring objects are numerous and diverse, posing significant management challenges; the natural resource field alone involves over 100 operational areas and more than 1,700 monitoring objects. However, the information from natural resource monitoring map points fails to accurately align with operational management needs, resulting in both data redundancy and insufficient supporting information in natural resource management practices. This hinders the transformation of massive monitoring results into refined governance effectiveness and fails to meet the multi-level and differentiated operational management needs of natural resources. A key issue that urgently needs to be addressed is how to systematically organize and analyze the numerous and complex natural resource monitoring application systems and the multi-dimensional and complex natural resource monitoring objects and the information implicit in them, constructing a business knowledge graph centered on natural resource monitoring objects. Summary of the Invention

[0004] The purpose of this invention is to provide a knowledge graph-based method and system for business association of natural resource monitoring patches, aiming to solve the problem of the disconnect between natural resource monitoring patch data and business management needs and the inability to accurately connect them in the existing technology, so as to realize the accurate push and efficient application of monitoring patches and improve the efficiency and management level of natural resource monitoring.

[0005] To achieve the above objectives, the technical solution of the present invention is as follows:

[0006] The first invention provides a method for business association of natural resource monitoring patches based on knowledge graphs, the method comprising:

[0007] Obtain natural resource monitoring patch data;

[0008] The relationship between the natural resource monitoring patch data and business-related objects is analyzed, a mapping relationship between business management needs and survey and monitoring objects is established, potential connections hidden in data flow and business logic are explored, business association rules for monitoring patches are established, and a business concept ontology is constructed using an ontology editor to describe entities and clarify object attributes.

[0009] Based on entity and object attributes, design business graph classes and their key attributes and relationships, establish a relational model based on graph database, import instances, and construct a natural resource monitoring business knowledge graph;

[0010] Based on the constructed natural resource monitoring business knowledge graph, an automatic push model for monitoring patches is established to push monitoring results to the management entity according to business management needs.

[0011] Optionally, the natural resource monitoring patch data includes routine monitoring change patch data of the target area and business management data; the business management data includes business classification reference data and information identification reference data.

[0012] Optionally, the natural resource monitoring patch data is obtained in the following way: using real-time acquired remote sensing image data as the monitoring data source, after acquiring the remote sensing image, based on the two valid monitoring images before and after, the monitoring patches are extracted in a rolling manner, and false change patches are removed, patch attributes are assigned, patch boundaries are corrected, and the current land use type is pre-filled according to the latest image to form natural resource routine monitoring change patch data.

[0013] Optionally, the business classification reference data includes land use status data, land use data, planning data, and management data, which are used to determine the business classification of changed map features;

[0014] The land use status data includes data from the national land change survey over the years; the land use data includes data on registered facility agricultural land, data on land use in advance, data on temporary land use, data on land supply, data on land approval, historical approval data for construction land, and self-recorded approval data; the planning data includes data on permanent basic farmland and ecological protection red lines; the management data includes data on high-standard farmland and data on land consolidation and deconsolidation.

[0015] Optionally, the information identification reference data includes land use status data, land use data, planning data, and management data, for use in identifying relevant information of changed map features;

[0016] The land use status data includes data from the national land change survey over the years; the land use data includes data on registered agricultural land, land use in advance, temporary land use, land supply, land approval, historical approvals for construction land, and self-recorded approvals; the planning data includes data on the overall land use plan, permanent basic farmland, ecological protection red line, and nature reserves; the management data includes data on demolition and reclamation, land consolidation and land reclamation, paddy field reclamation, supplementary arable land, and urban renewal.

[0017] Optionally, the business concept ontology includes elements such as core classes, instances, object attributes, and axioms.

[0018] Optionally, the step of establishing an automatic monitoring patch push model based on the constructed natural resource monitoring business knowledge graph to push monitoring results to the management entity according to business management needs includes:

[0019] Based on the geographic information scenario-based knowledge service platform, and the business rules and related logic sorted out from the natural resource monitoring business knowledge graph, the association mapping of business rules is realized;

[0020] Overlay multi-dimensional information from monitoring patches, conduct correlation analysis, and identify information such as business type, fieldwork category, and department to which information is pushed;

[0021] By overlaying routine monitoring patches with business management data, we analyze the monitoring content and frequency requirements, determine the business-related departments of the monitoring patches, and then classify and summarize the monitoring patches to the relevant business departments to establish a closed-loop management mechanism of monitoring-analysis-handling-verification.

[0022] Optionally, the business graph classes and their key attributes and relationships include determining the class name, clarifying the class definition, supplementing the key attributes of the class, and defining the key relationships between each class.

[0023] Optionally, data modeling can be performed using the Neo4j graph database. The identified key classes are used as nodes in the natural resource monitoring business knowledge graph relationship model, and the relationships between the nodes are established. In the modeling process, a total of 20 nodes and 32 relationships are defined to establish the association between business requirements, business departments and land category conversion.

[0024] Secondly, the present invention provides a knowledge graph-based system for linking natural resource monitoring map features, comprising:

[0025] The data acquisition module is used to acquire natural resource monitoring patch data;

[0026] The business rule sorting and ontology construction module is used to construct the relationship between the natural resource monitoring patch data and business-related objects, as well as the mapping relationship between business management needs and survey and monitoring objects. It explores the potential connections hidden in data flow and business logic, establishes business association rules for monitoring patches, and uses the ontology editor to construct the business concept ontology to determine entity and object attributes.

[0027] The business knowledge graph module is used to establish business graph classes and their key attributes and relationships based on the determined entity and object attributes, and to build a natural resource monitoring business knowledge graph based on graph database modeling.

[0028] The business association and automatic push module establishes an automatic push model for monitoring patches based on the constructed natural resource monitoring business knowledge graph, so as to push the monitoring results to the management entity according to the business management needs.

[0029] Compared with the prior art, the advantages of this invention are as follows:

[0030] This invention introduces knowledge graph technology into the research on the business association of natural resource monitoring patches. By constructing the association between natural resource monitoring patches and the business system, it is possible to quickly discover and warn of changes in natural resource patches, thereby promoting the transformation and upgrading of the natural resource monitoring and supervision system towards precision and intelligence. Attached Figure Description

[0031] Figure 1 The main flowchart of the knowledge graph-based natural resource monitoring patch business association method provided in the embodiments of this application;

[0032] Figure 2 Construct a logical graph for the business graph ontology;

[0033] Figure 3 A knowledge graph relationship model for natural resource monitoring map patches;

[0034] Figure 4 A knowledge graph node for a specific business function of law enforcement agencies;

[0035] Figure 5 To facilitate routine monitoring of changes in map features and related business operations;

[0036] Figure 6 A map for monitoring the "non-agriculturalization" of arable land;

[0037] Figure 7 A monitoring map for the "non-grain use" of arable land;

[0038] Figure 8 This is a schematic diagram illustrating the composition of a knowledge graph-based natural resource monitoring map patch business association system provided in an embodiment of this application. Detailed Implementation

[0039] Example:

[0040] The technical solution of the present invention will be further described below with reference to the accompanying drawings and embodiments.

[0041] See Figure 1 As shown in the figure, the knowledge graph-based method for business association of natural resource monitoring patches provided in this embodiment mainly includes the following steps:

[0042] 110, Obtain natural resource monitoring patch data;

[0043] 120. Construct the relationship between the natural resource monitoring patch data and business-related objects, as well as the mapping relationship between business management needs and survey and monitoring objects. Explore the potential connections hidden in data flow and business logic, establish business association rules for monitoring patches, and use the ontology editor to construct a business concept ontology to describe entities and clarify object attributes.

[0044] In this step, the natural resource business rules are systematically reviewed, and the natural resource business management needs and monitoring content are analyzed to accurately match the natural resource monitoring map data with business management needs.

[0045] 130. Design business graph classes and their key attributes and relationships based on entity and object attributes, establish a relational model based on graph database, import instances, and construct a natural resource monitoring business knowledge graph.

[0046] In this step, a business knowledge graph centered on natural resource monitoring objects is constructed to achieve multi-dimensional dynamic association between monitoring patch attributes, business rules, and management needs.

[0047] Based on the constructed natural resource monitoring business knowledge graph, an automatic push model for monitoring patches is established to push monitoring results to the management entity according to business management needs.

[0048] In this step, the monitoring patch automatic push model based on business knowledge graph accurately pushes the monitoring results to the management entity according to business management needs, providing theoretical reference and technical support for the integrated development of natural resource monitoring and management.

[0049] Therefore, this method introduces knowledge graph technology into the business association research of natural resource monitoring patches. By constructing the association between natural resource monitoring patches and the business system, it can achieve rapid discovery and early warning of natural resource change patches, thereby promoting the transformation and upgrading of the natural resource monitoring and supervision system towards precision and intelligence.

[0050] In one specific embodiment, the natural resource monitoring patch data includes routine monitoring change patch data of the target area and business management data, the business management data including business classification reference data and information identification reference data.

[0051] Specifically, the natural resource monitoring patch data is obtained in the following way: acquiring change patch data extracted from monthly province-wide monitoring images, using real-time acquired remote sensing image data as the monitoring data source, and after acquiring remote sensing images, extracting monitoring patches in a rolling manner based on two consecutive valid monitoring images, removing false change patches, assigning patch attributes, correcting patch boundaries, and pre-filling current land use types based on the latest images to form normalized natural resource monitoring change patch data.

[0052] The reference data for this business classification includes land use status data such as historical land change survey results; land use data such as registered facility agricultural land data, preliminary land use data, temporary land use data, land supply data, land approval data, historical construction land approval data, and self-recorded approval data; planning data such as permanent basic farmland data and ecological protection red lines; and management data such as high-standard farmland data and land consolidation data, which are used to determine the business classification of changed land parcels.

[0053] The reference data for this information label includes land use status data such as data from national land change surveys over the years; land use data such as data on registered agricultural facilities, land use in advance, temporary land use, land supply, land approval, historical approvals for construction land, and self-recorded approvals; planning data such as data on overall land use planning, permanent basic farmland, ecological protection red lines, and nature reserves; and management data such as data on demolition and reclamation, land consolidation, paddy field reclamation, supplementary arable land, and urban renewal, used for identifying relevant information on changed land parcels.

[0054] In one specific embodiment, step 120 includes: based on the understanding of the natural resource concept system and the natural resource classification standards, conducting an in-depth analysis of the current status of the natural resource survey and monitoring business application system, systematically sorting out more than 100 business requirements related to natural resource monitoring work, covering more than 1,700 monitoring objects, and sorting out information such as monitoring data sources, monitoring frequencies, regulatory rules, and relevant departments from the perspectives of business management and monitoring data, forming a natural resource monitoring business knowledge system. Based on this, such as... Figure 2 As shown, using the Protégé ontology editor, a conceptual ontology of natural resource business with 20 core classes, including core classes, instances, object attributes, and axioms, was constructed, with the regulatory needs, business rules, and business data of each business department as the core, providing a logical foundation for the knowledge graph.

[0055] The core classes abstract key concepts in business management, organizing complex business objects through hierarchical relationships. These include business departments, business needs, business rules, monitoring operations, business requirements, other attribute requirements, land use change rules, other rules, business data analysis rules, other requirements, monitoring frequency, minimum monitoring area, land use type after change, and land use type before change. Instances are concrete objects of the classes. Through the association of instances with attributes and axioms, semantic expression of business rules and data is achieved, including farmland protection business instances and law enforcement supervision business instances. Object attributes describe the logical relationships between classes or instances, defining business rules. For example, the attributes of the class "Land Use Type Before Change" include land use code, land use name, first-level class name, and third-level class names. Axioms are logical constraints and rules in an ontology, used to define the semantic relationships between classes, attributes, and instances. These include logical constraint axioms (such as the mutual exclusion axiom of land use change rules, i.e., "land use type before change" and "land use type after change" cannot be the same land use type) and data consistency axioms (such as the value of the "monitoring frequency" attribute must be an integer). The construction of the natural resource business concept ontology provides the logical foundation for the knowledge graph, clarifying the data hierarchy and its interrelationships.

[0056] In one specific embodiment, step 130 includes: designing business graph classes and their key attributes and relationships based on the entity and object attributes defined in step 120, including determining the class name, defining the class, supplementing the key attributes of the class, and defining the key relationships between each class. For example, the key attributes of "change patch" include patch number, location coordinates, area, monitoring time, and online time; "monitoring frequency" is associated with "monitoring business" and is included in "business requirements".

[0057] Then, data modeling was performed using the Neo4j graph database. The identified key classes were used as nodes in the business knowledge graph relationship model, and the relationships between these nodes were established. During the modeling process, 20 nodes and 32 relationships were defined, establishing connections between business requirements, business departments, and land category conversions. Based on the above analysis of the natural resources business requirements of a certain province, and combined with the actual business management scenarios of routine monitoring work, corresponding sample data was generated. These samples were imported into the relationship model to achieve the transformation of structured knowledge data, and then visualized using a graph.

[0058] Finally, through instance import, 480 nodes and 1472 relationships were generated, constructing a routine monitoring patch business knowledge graph. This graph comprehensively covers business management scenarios such as farmland protection and law enforcement supervision, clearly demonstrating the correlation between business management and land use changes. Taking the law enforcement department's "Special Investigation on Illegal Occupation of Farmland for Housing Construction in Rural Areas" as an example, such as... Figure 3-4As shown, its knowledge graph mainly includes key nodes such as changed patches, business types, monitoring frequency, previous time-phase land types, and subsequent time-phase land types. These nodes are closely organized through 22 relationships such as "spatial distribution", "overlay", and "change to", forming the patch classification logic under this business management scenario.

[0059] In one specific embodiment, step 140 includes: based on the natural resource monitoring business knowledge graph constructed in step 130, an automatic push model for monitoring patches based on the business knowledge graph is built, and relying on the existing geographic information scenario-based knowledge service platform, accurate push of routine monitoring patches is achieved. Based on the business rules and business association logic sorted out by the knowledge graph, the association and mapping of business rules are realized, and then the location information of monitoring patches, production-related information of patches, land use status information, land use boundary information, management information, etc. are superimposed to perform association analysis on the monitoring patches, and identify information such as business type, field type, and pushing department.

[0060] Specifically, by overlaying routine monitoring patches with operational management data, the system analyzes the monitoring content and frequency requirements of the monitored patches, identifies the relevant departments for each patch, and then accurately categorizes and aggregates them to the relevant operational departments. Based on management needs, an automatic push model directs patches related to farmland protection to the farmland protection department, patches suspected of illegal construction to the law enforcement and supervision department in real time, and patches related to forest changes to the forestry department as leads. By establishing a closed-loop management mechanism of "monitoring-analysis-handling-verification," seamless integration and two-way feedback between survey monitoring and management operations are achieved, forming a full-chain "closed-loop" service model that effectively supports the efficient management and dynamic monitoring of natural resources. Figure 5 As shown.

[0061] The constructed business association and automatic push model first uses key information related to monitored land parcels, reference analysis data, push department names, and classification rules as main nodes. It then organizes a business knowledge graph for monitoring "non-agriculturalization" and "non-grainization" of cultivated land using important relationships such as "combined analysis," "push to," and "reference." Specifically, as follows... Figure 6-7 As shown in the diagram. Then, business-related knowledge and processing results are organized into a graph format, and the processed information is pushed to relevant departments in the form of map features. Finally, a comprehensive sensing system is implemented for routine monitoring of farmland-related map features, and the pushed data is further processed through a three-tiered response mechanism at the provincial, municipal, and county levels. This achieves data-driven and precise services guided by business needs, providing comprehensive support services for farmland protection across the entire chain of "monitoring-control-governance."

[0062] In summary, this method achieves precise matching between natural resource monitoring patches and business management needs. By constructing a knowledge graph to associate business rules, this invention not only solves the problems of disconnect between monitoring patches and business operations and difficulty in information integration in the traditional model, but also leverages the knowledge graph to uncover implicit relationships between monitoring objects and business logic. Furthermore, it develops an automatic monitoring patch push mechanism based on a business knowledge graph, realizing the transformation of natural resource monitoring results into refined management efficiency, and providing data support and decision support for multi-level business control of natural resources and improving governance levels.

[0063] Correspondingly, such as Figure 8 As shown, this embodiment also provides a knowledge graph-based natural resource monitoring patch business association system 800, including:

[0064] Data acquisition module 810 is used to acquire natural resource monitoring patch data;

[0065] The business rule sorting and ontology construction module 820 is used to sort out the relationship between the natural resource monitoring patch data and business-related objects, as well as the mapping relationship between business management needs and survey and monitoring objects, to explore the potential connections hidden in data flow and business logic, to construct business association rules for monitoring patches, and to use the ontology editor to construct business concept ontology to describe entities and clarify object attributes.

[0066] The Business Knowledge Graph Module 830 is used to design business graph classes and their key attributes and relationships based on entity and object attributes, establish a relational model based on the graph database, import instances, and construct a natural resource monitoring business knowledge graph.

[0067] The business association and automatic push module 840 establishes an automatic push model for monitoring patches based on the constructed natural resource monitoring business knowledge graph, so as to push the monitoring results to the management entity according to the business management needs.

[0068] It should be noted that the knowledge graph-based natural resource monitoring patch business association system provided in this application embodiment can execute the knowledge graph-based natural resource monitoring patch business association method provided in any embodiment of this application, and has the corresponding functions and beneficial effects of the execution method, which will not be repeated in this embodiment.

[0069] The above embodiments are merely illustrative of the technical concept and features of the present invention, and are intended to enable those skilled in the art to understand the content of the present invention and implement it accordingly. They should not be construed as limiting the scope of protection of the present invention. All equivalent changes or modifications made based on the essence of the content of the present invention should be covered within the scope of protection of the present invention.

Claims

1. A knowledge graph-based method for business association of natural resource monitoring patches, characterized in that, The method includes: Obtain natural resource monitoring patch data; The relationship between the natural resource monitoring patch data and business-related objects is analyzed, a mapping relationship between business management needs and survey and monitoring objects is established, potential connections hidden in data flow and business logic are explored, business association rules for monitoring patches are established, and a business concept ontology is constructed using an ontology editor to describe entities and clarify object attributes. Based on entity and object attributes, design business graph classes and their key attributes and relationships, establish a relational model based on graph database, import instances, and construct a natural resource monitoring business knowledge graph; Based on the constructed natural resource monitoring business knowledge graph, an automatic push model for monitoring patches is established to push monitoring results to the management entity according to business management needs.

2. The knowledge graph-based method for business association of natural resource monitoring patches as described in claim 1, characterized in that, The natural resource monitoring patch data includes routine monitoring change patch data of the target area and business management data; the business management data includes business classification reference data and information identification reference data.

3. The knowledge graph-based method for business association of natural resource monitoring patches as described in claim 2, characterized in that, The natural resource monitoring patch data is obtained in the following way: using real-time acquired remote sensing image data as the monitoring data source, after acquiring the remote sensing image, the monitoring patches are extracted in a rolling manner based on the two valid monitoring images before and after, and false change patches are removed, patch attributes are assigned, patch boundaries are corrected, and the current land type is pre-filled according to the latest image to form normalized natural resource monitoring change patch data.

4. The knowledge graph-based method for business association of natural resource monitoring patches as described in claim 2, characterized in that, The business classification reference data includes land use status data, land use data, planning data, and management data, which are used to determine the business classification of changed map features; The land use status data includes data from the national land change survey over the years; the land use data includes data on registered facility agricultural land, data on land use in advance, data on temporary land use, data on land supply, data on land approval, historical approval data for construction land, and self-recorded approval data; the planning data includes data on permanent basic farmland and ecological protection red lines; the management data includes data on high-standard farmland and data on land consolidation and deconsolidation.

5. The knowledge graph-based method for business association of natural resource monitoring patches as described in claim 2, characterized in that, The information identification reference data includes land use status data, land use data, planning data, and management data, which are used for identifying relevant information of changed map features; The land use status data includes data from the national land change survey over the years; the land use data includes data on registered agricultural land, land use in advance, temporary land use, land supply, land approval, historical approvals for construction land, and self-recorded approvals; the planning data includes data on the overall land use plan, permanent basic farmland, ecological protection red line, and nature reserves; the management data includes data on demolition and reclamation, land consolidation and land reclamation, paddy field reclamation, supplementary arable land, and urban renewal.

6. The method for business association of natural resource monitoring patches based on knowledge graphs as described in claim 1, characterized in that, The business concept ontology includes core classes, instances, object attributes, and axiom elements.

7. The knowledge graph-based method for business association of natural resource monitoring patches as described in claim 1, characterized in that, The aforementioned method establishes an automatic monitoring patch push model based on the constructed natural resource monitoring business knowledge graph, which pushes monitoring results to the management entity according to business management needs, including: Based on the geographic information scenario-based knowledge service platform, and the business rules and related logic sorted out from the natural resource monitoring business knowledge graph, the association mapping of business rules is realized; Overlay multi-dimensional information from monitoring patches, conduct correlation analysis, and identify business types, fieldwork categories, and push information to relevant departments; By overlaying routine monitoring patches with business management data, we analyze the monitoring content and frequency requirements, determine the business-related departments of the monitoring patches, and then classify and summarize the monitoring patches to the relevant business departments to establish a closed-loop management mechanism of monitoring-analysis-handling-verification.

8. The knowledge graph-based method for business association of natural resource monitoring patches as described in claim 1, characterized in that, The business graph classes and their key attributes and relationships include determining the class name, clarifying the class definition, supplementing the key attributes of the class, and defining the key relationships between each class.

9. The method for business association of natural resource monitoring patches based on knowledge graphs as described in claim 1, characterized in that, Data modeling was performed using the Neo4j graph database. The identified key classes were used as nodes in the natural resource monitoring business knowledge graph relationship model. The relationships between the nodes were established. In the modeling process, a total of 20 nodes and 32 relationships were defined, and the association between business needs, business departments and land category conversion was established.

10. A knowledge graph-based system for linking natural resource monitoring map features, characterized in that: include: The data acquisition module is used to acquire natural resource monitoring patch data; The business rule sorting and ontology construction module is used to sort out the relationship between the natural resource monitoring patch data and business-related objects, as well as the mapping relationship between business management needs and survey and monitoring objects, to explore the potential connections hidden in data flow and business logic, to construct business association rules for monitoring patches, and to use the ontology editor to construct business concept ontology to describe entities and clarify object attributes. The business knowledge graph module is used to design business graph classes and their key attributes and relationships based on entity and object attributes, establish a relational model based on graph database, import instances, and construct a natural resource monitoring business knowledge graph. The business association and automatic push module establishes an automatic push model for monitoring patches based on the constructed natural resource monitoring business knowledge graph, so as to push the monitoring results to the management entity according to the business management needs.

Images