Intelligent question and answer method and device, equipment and storage medium

Abstract

The invention relates to the field of question and answer retrieval and the blockchain technology, and particularly discloses an intelligent question and answer method and device, equipment and a storage medium. The method comprises the following steps: acquiring a to-be-retrieved question; determining a keyword of the to-be-retrieved question, and determining a first retrieval result according to the keyword based on a first retrieval model; inputting the to-be-retrieved problem into a pre-trained second retrieval model to obtain a second retrieval result; performing fusion sorting on the first retrieval result and the second retrieval result to obtain a sorting result; and determining a question and answer result corresponding to the to-be-retrieved question according to the sorting result, and feeding back the question and answer result to the user. Therefore, the answering accuracy of the question-answering system is improved. The first retrieval result, the second retrieval result and the sorting result can be stored in the block chain.

Description

technical field [0001] The present application relates to the field of question-answer retrieval, and in particular to an intelligent question-answer method, device, equipment and storage medium. Background technique [0002] At present, with the gradual increase of online business, some question answering systems for solving user problems are also gradually improved. Existing question answering systems include Q&A-based question answering systems and knowledge graph-based question systems. The question answering system based on Q&A is based on a large number of question and answer pairs, and completes Q-A matching or Q-Q matching for user questions, matching to the closest question or answer, so as to achieve the purpose of searching for questions and answers. The question system based on the knowledge map is based on the knowledge map, according to the user's question, through the entity recognition technology and the relationship extraction technology, combined with the ...

AI Technical Summary

Problems solved by technology

However, existing question answering systems often use a single-source retrieval method and use a more conventional deep neural network model, which cannot be retrieved based on syntax and semantics at the same time, and the accuracy rate is also low.

Images