Domain knowledge extraction method based on inverted list
The invention discloses a domain knowledge extraction method based on an inverted table. The method comprises the following steps: 1) establishing an inverted index table for unstructured, semi-structured and structured data in a ship knowledge base; the inverted index table stores position mapping...
Saved in:
Main Authors | , , , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
15.12.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention discloses a domain knowledge extraction method based on an inverted table. The method comprises the following steps: 1) establishing an inverted index table for unstructured, semi-structured and structured data in a ship knowledge base; the inverted index table stores position mapping of words in the document; 2) searching candidate knowledge of the request problem from the inverted index table cluster based on a polling-based load balancing algorithm; (3) sorting the candidate knowledge according to the searched candidate knowledge; 4) performing triple extraction on the sorted TopN candidate knowledge; 5) performing error correction and knowledge fusion on conflicting triads in the extracted triads; and 6) obtaining a knowledge graph after knowledge extraction according to the processed triple. According to the method, the candidate knowledge range is narrowed, the knowledge is quickly extracted from the knowledge base, and the system response speed is increased.
本发明公开了一种基于倒排表的领域知识抽取方法,包括以下步骤: |
---|---|
Bibliography: | Application Number: CN202310975138 |