Knowledge ontology construction method, terminal equipment and storage medium
A technology of ontology construction and knowledge, applied in the field of knowledge graph construction, which can solve the problems of uneven business experience of personnel and executives, stuck in analysis, and the effect of case handling cannot develop in the expected direction.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0036] The embodiment of the present invention provides a knowledge ontology construction method, based on neo4j as the storage medium of the knowledge base, based on Java as the application-level technology, such as figure 1 As shown, the method includes the following steps:
[0037] S1: Construct a knowledge ontology and configure metadata corresponding to the ontology.
[0038] Usually, the domain ontology is constructed in a top-down manner. On the one hand, compared with the open domain knowledge graph, the concepts and scope involved in the domain knowledge graph are fixed or controllable; on the other hand, for the domain knowledge graph, we It is required to meet higher precision. In this embodiment, the ontology of the burglary case is unlocked through the ontology construction tool Protege construction technology, such as figure 2 , image 3 and Figure 4 As shown, a knowledge ontology file expressed in OWL is obtained.
[0039] In this embodiment, after the ow...
example 1
[0045] Example 1: In the case relationship in the same region, the rule file defining the case relationship is as follows Figure 7 shown.
[0046] Rule description: Find out whether the case area (CODE_XZQHDM_LEV3 or CODE_XZQHDM_LEV2) of the current evaluation case is the same and is not another case node of the current case, and build the case relationship in the same area, and create the area adjacent relationship if the CODE_XZQHDM_LEV3 is the same.
example 2
[0047] Example 2: The rule file containing the relationship with the suspect is as follows Figure 8 shown.
[0048] Rule description: Query all suspects in the current case and query other related cases of the suspect set, and the related case number is not the knowledge node of the current case, and build a relationship with the same suspect.
[0049] Through the above rules to mine the case relationship, backfill and supplement the knowledge base, and improve the ability of the knowledge base.
[0050] The rule engine realizes ontology object attribute reasoning:
[0051]Taking the case number A440305030000201XXXXX as an example, to query all the relations of the burglary case, the Neo4j library cypher statement is expressed as: match(s: Case)-[p*]->(n)return s, p, o;
[0052] Among them, s, p, and o are case knowledge, reception relationship, and knowledge node objects connected by cases respectively.
[0053] Texture: the returned data format
[0054] Query through th...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


