Dynamic ontology construction method based on large model
Through the dynamic ontology construction method based on big models, the ontology update difficulties and relying on experts in the construction of traditional knowledge graphs are solved, the flexibility and timeliness of ontology are realized, and the construction of knowledge graphs is promoted.
CN119691194APending Publication Date: 2025-03-25BEIJING INST OF COMP TECH & APPL
0 Cites 5 Cited by
Patent Information
- Application Number
- CN202411620830.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-14
- Publication Date
- 2025-03-25
AI Technical Summary
Technical Problem
The problems of difficulty in ontology renewal, over-reliance on experts, poor flexibility and timeliness in the construction of traditional knowledge graphs.
Method used
Using a dynamic ontology construction method based on big models, the initial ontology is constructed, and the large language model is used for hierarchical expansion and knowledge expansion, the Prompt strategy is designed for real-time data extraction, and the merger and update of the ontology in the field is achieved through Function Calling technology.
Benefits of technology
It improves the flexibility and adaptability of ontology construction, promotes the construction of knowledge graphs, reduces dependence on experts, and achieves efficient updates of ontology.
✦ Generated by Eureka AI based on patent content.
Abstract
The invention relates to a dynamic ontology construction method based on a large model, and belongs to the field of artificial intelligence, large models and knowledge maps. According to the method, expert knowledge, historical experience, a database and industrial standard data are comprehensively utilized, entity types, attributes and relationships are defined, and an initial ontology O1 is constructed; by means of rich knowledge contained in a large model, extension from a large class to a subclass is achieved, on this basis, extraction of subclass knowledge is further achieved through a large model technology, and an ontology O2 is formed; for structured, semi-structured and non-structured data updated in real time in the business data, forming an ontology set O3 based on small-sample prompt learning of a large model; the merging and updating of the domain ontology are realized through a Function Calling technology based on LLM (Logical Language Model); a function is defined through word similarity calculation based on a'known network ', mathematical calculation is carried out on a large model, merging and updating of domain ontologies are achieved, and an ontology set O4 is formed. According to the invention, the quality of ontology construction is improved.
Need to check novelty before this filing date? Find Prior Art