An information retrieval-based question and answer system and method for knowledge graph energization

Abstract

The invention discloses an information retrieval-based question and answer system and method for knowledge graph energization, which integrally improve the question and answer effect of the system, expand the user consultation range and improve the question feedback accuracy. According to the technical scheme, the system comprises a knowledge map database for storing domain knowledge map information; a word segmentation and part-of-speech tagging module which segments the user questions and tags the part-of-speech of the user questions; an entity identification and link module which identifiesentities in the user questions and links the entities to nodes in the knowledge graph database; an intention understanding module which obtains an intention understanding result of the user problem based on the entity link result and the distributed representation vector; a retrieval module which retrieves a plurality of corresponding question and answer pairs as roughing results according to theinformation in the user questions based on the retrieval data source; a sorting module which is used for resorting the roughing results by utilizing the distributed representation vectors of the entities; and a semantic matching module which scores the reordering result by using the distributed representation vector of the entity and finally outputs an answer.

Description

technical field [0001] The present invention relates to a question answering system (Question Answering System, QA System) and method in the field of artificial intelligence and natural language processing, in particular to a question answering system based on Information Retrieval (Information Retrieval) empowered by Knowledge Graph (KG) and method. Background technique [0002] Question answering system is a research direction that has attracted much attention and has broad development prospects in the field of artificial intelligence and natural language processing. The question answering system can answer questions raised by users in natural language with accurate and concise natural language. [0003] In practical application scenarios, there are a large number of question-answer pairs, such as the accumulated FAQ data, which can be used as the basis for building a question-answer system. In this field, only the question-answer method based on Information Retrieval is ...

AI Technical Summary

Problems solved by technology

[0009] (1) At present, the existing research work is mainly to use the constructed general knowledge graph to empower the semantic information module in the information retrieval-based question answering system, such as the intent recognition module, but there is no overall empowerment for the information retrieval-based question answering system. limited improvement

[0010] (2) The currently public question-answering system based on information retrieval is mainly for question-and-answer pairs, and information retrieval is achieved by indexing lucene, solr, or elastic-search to achieve question-and-answer. The modules empowered by knowledge graphs are only for knowledge in general fields , did not find an information retrieval-based question answering system that can be well integrated into the domain knowledge map

[0011] Therefore, at present, it is difficult to achieve satisfactory question answering tasks by using the question answering system based on information retrieval and using some modules of the general knowledge graph to empower the question answering system. There is an urgent need for an information retrieval based question answering system powered by knowledge graph

Images