A knowledge graph question answering method based on multiple strategies

Through a multi-strategy knowledge graph question-answering method, specific query strategies and models are adopted for different types of questions, which solves the problem of low accuracy of answers to static attribute questions in the existing technology, realizes accurate answer retrieval for static and dynamic questions, and improves the recall rate and ease of use of the question-answering system.

CN115422330BActive Publication Date: 2025-09-1210TH RES INST OF CETC
2 Cites 0 Cited by

Patent Information

Application Number
CN202210603640.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-05-30
Publication Date
2025-09-12
Estimated Expiration
2042-05-30

AI Technical Summary

Technical Problem

The existing knowledge graph question-answering method has a single model and can only query static attribute questions. The answer accuracy is low and it cannot effectively handle dynamic questions.

Method used

A multi-strategy knowledge graph question answering method is adopted. Through question classification, entity recognition and fuzzy query, different query strategies are selected for different types of questions using the BERT model and Cypher statements, and the most similar nodes or edges are selected as answers using the semantic similarity model.

Benefits of technology

It achieves accurate answer retrieval for static and dynamic questions, improves the recall rate and answer accuracy of the question-answering system, and enhances the generalization ability of the question-answering system.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The present invention discloses a multi-strategy knowledge graph question-answering method. The method includes classifying question types according to question content, identifying question entities using an entity recognition model, linking question entities to graph nodes using fuzzy queries, converting the required search content into Cypher statements based on the question, selecting different query strategies for different question types, obtaining triples corresponding to the question, matching similar graph nodes to question entities using fuzzy queries, matching relevant nodes and edges to question relationships using the BERT model, and selecting the node or edge most similar to the question using a semantic similarity model, and outputting the node or edge as the answer to the question. The present invention provides an attribute query retrieval method for static questions and a temporal reasoning or statistical query retrieval method for dynamic questions. Different question-answering strategies are proposed for different question types, thereby enabling answer retrieval for dynamic questions.
Need to check novelty before this filing date? Find Prior Art