Intelligent question-answering method and related device

Abstract

The embodiment of the invention discloses an intelligent question question-answering method and a related device, which are used for improving the accuracy of an intelligent question and answer system. The method comprises the steps that a target user problem is acquired; a target generation problem corresponding to the target user problem is generated according to a problem optimization model, the problem optimization model is obtained based on generative adversarial network training, and the problem optimization model comprises a generator and a discriminator; whether the generation qualityof the target generation problem is higher than a first preset threshold value or not is judged according to the discriminator, wherein the generation quality is used for indicating the probability that the target generation problem is a standard problem; and a target answer is determined according to the target generation question if so.

Description

technical field [0001] The present application relates to the technical field of information recommendation, in particular to an intelligent question answering method and a related device. Background technique [0002] In this era of rapid development, the more human resources can be saved, the greater the liberation of productivity. In order to better meet the needs of users and save human resources, more and more service industries have organized common questions and their answers raised by users, that is, to organize common questions and their answers into a standardized question bank form, and based on this question The library created an intelligent question answering system. Among them, the intelligent question answering system is a new type of information retrieval system that processes natural language. It receives questions raised by users in the form of one question and one answer, and then accurately locates the relevant knowledge in the question and answer datab...

AI Technical Summary

Problems solved by technology

[0004] However, in the actual question answering system, the user's description and wording of the question are various, very colloquial or even irregular, including irregular words such as "how to enter the reading code is not true", word order reversed such as "how Haven’t arrived yet, express”, etc., because the set of questions that can be effectively answered in the question answering system is limited to the questions corresponding to the template library, for example, if the user’s question does not match any template, the answer cannot be given

Therefore, these non-standard expressions bring great difficulties to the problem analysis of the existing question answering system, making it difficult for the question answering system based on matching and retrieval to understand the user's question, and then find the accurate answer, reducing the accuracy of the question answering system

Images