Intelligent automatic question answering method and system based on bi-directional long-short-term memory neural network

Abstract

The invention discloses an intelligent automatic question answering method and a system based on a bi-directional long-short-term memory neural network. The method comprises the following steps: firstly, constructing a bi-directional long-short memory neural network model and an intelligent automatic question answering database; Secondly, the user input question text is processed by word segmentation and vector transformation to obtain feature words and user question matrix, and the question list matching with feature words is extracted from intelligent automatic question answering database, and the user question matrix is inputted into bi-directional long-short term memory neural network model to obtain user goal vector. Finally, the similarity between the user target vector and each target vector in the question list is calculated, and the answer of the question corresponding to the target vector with the highest similarity is determined as the answer required by the user. The invention satisfies people's demand for fast and accurate information acquisition through matching of core feature words and matching of problem semantics of a bi-directional long-short memory neural network model.

Description

technical field [0001] The invention relates to the technical field of question answering systems, in particular to an intelligent automatic question answering method and system based on a bidirectional long-short-term memory neural network. Background technique [0002] Question Answering System (QA) is an advanced form of information retrieval system, which can answer questions raised by users in natural language with accurate and concise natural language. The main reason for the rise of its research is people's demand for fast and accurate access to information. 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. [0003] The intelligent question answering system accurately locates the questioning knowledge needed by website users in the form of one question and one answer, and provides personalized information services for website ...

AI Technical Summary

Problems solved by technology

[0014] In the traditional question answering system, the answer matching is mainly based on the feature word matching of the question data, and the processing of the question analysis level is relatively rough. This phenomenon is even worse on the question data. By generating search keywords Unable to fully cover the actual semantics of the question, ignoring the contextual semantics, and unable to avoid the problem that the answer after similar replacement of keywords cannot be queried

Images