Intelligent question-answering method and system based on knowledge graph and knowledge graph updating system

Abstract

The invention provides an intelligent question-answering method and system based on a knowledge graph and a knowledge graph updating system. The method comprises: receiving a user question; convertingthe user question into a regularization question; and performing question matching on the regularized questions and a template library generated by a knowledge graph based on a heterogeneous information model, and determining a matching result with the highest similarity as an answer. Characteristics of a heterogeneous information network are fully utilized for modeling, richer knowledge and relationship reasoning are provided by combining a ranking collaborative clustering algorithm and a meta-path similarity algorithm, a traditional knowledge graph-based question-answering system is improved, and the accuracy and the intelligent degree of the question-answering system are improved.

Description

technical field [0001] The invention belongs to the technical field of knowledge graphs, in particular to a knowledge graph-based smart question answering method, system and knowledge graph updating system. Background technique [0002] Question answering system is an advanced form of information retrieval system, which can answer the questions asked by users in natural language in accurate and concise natural language. In recent years, a question answering system based on knowledge graph has become a hot spot of research and application in academia and industry. Knowledge graphs are widely used due to their high semantic understanding, data accuracy, and efficient retrieval. However, the rules of the knowledge graph have certain limitations, such as the number of entities under a specific relationship, which affects the breadth of the question and answer range and the accuracy of the question and answer results. [0003] Existing question answering systems based on knowle...

AI Technical Summary

Problems solved by technology

However, the rules of the knowledge graph have certain limitations, such as the number of entities under a specific relationship, which affects the breadth of the Q&A range and the accuracy of the Q&A results.

[0003] Existing question answering systems based on knowledge graphs have been used more and more, but in practical applications, the constructed knowledge graph models are prone to problems of loose data and low coverage, resulting in low knowledge matching coverage in the process of question answering. not getting a satisfactory intelligent answer from time to time

[0004] In addition, the incremental maintenance cost of the knowledge map is relatively high

Images