An intelligent question answering method, device, electronic equipment and storage medium

Abstract

The embodiment of the present invention discloses an intelligent question answering method, which includes detecting the question information and obtaining the target entity word in the question information, the target entity word constitutes the first question information; the extended word is associated with at least one word meaning; the target entity word and the expanded The word meaning matching of word association obtains the extended words of each target entity word; the extended words form at least one second question information; the first question information and the second question information are matched with the question template respectively to obtain the question template with the highest matching degree; Get the answer information associated with the question template with the highest matching degree. In the present invention, the expanded words are creatively added, the range of word segmentation results is expanded, the diversity of word segmentation results is improved, and the problem of low accuracy of matching results caused by the phenomenon of "many words with one meaning" in Chinese is effectively solved. At the same time, due to the increased accuracy of the matching results, the present invention reduces the requirement for user input, and the degree of intelligence is obviously improved.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of data processing, and in particular to an intelligent question answering method, device, electronic equipment, and storage medium. Background technique [0002] Almost since the dawn of computers, people have tried to use them for natural language processing. In the 1950s, British mathematician A. M. Turing predicted that future computers would raise new questions for natural language research. The "Turing Test" he proposed is generally considered to be the beginning of the idea of ​​natural language processing. [0003] In the mid-1950s, with Chomsky's generative linguistics theory proposed, language information processing mainly adopts rule-based methods. Even until the 1980s, the mainstream approach in the field of natural language processing was still a rule-based rationalist approach. Until the 1990s, the research on natural language processing was unprecedentedly prosperou...

AI Technical Summary

Problems solved by technology

[0029] To this end, the embodiments of the present invention provide an intelligent question answering method, device, electronic equipment, and storage medium to solve the problem of low accuracy of matching answers in the prior art due to inability to accurately segment words

Images