Question answer prediction method and device, storage medium and electronic equipment

Abstract

The invention discloses a question answer prediction method and device, a storage medium and electronic equipment. In the method, the method comprises the steps of obtaining a target question statement; identifying entity words in the target question statement, respectively matching the target question statement with each question cluster sequence mode in the question cluster sequence mode set toobtain a target question cluster sequence mode, and determining an answer type label corresponding to the target question cluster sequence mode; and taking the entity words in the target question statement and the answer type label corresponding to the target question cluster sequence mode as feature information, inputting the feature information into a Bayesian model, and predicting to obtain answer entity words corresponding to the target question statement. Since the entity words in the target question statement and the answer type corresponding to the target question cluster sequence modeare mutually independent feature information, the feature independence requirement of the Bayesian model can be met, and the accuracy of the answer entity words corresponding to the target question statement predicted by the Bayesian model is higher.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, and in particular to a method, device, storage medium and electronic equipment for predicting answers to questions. Background technique [0002] With the rapid development of artificial intelligence technology, the function of the question answering system based on artificial intelligence technology is also becoming more and more perfect, and it has been applied to many application scenarios such as intelligent customer service on e-commerce platforms and automatic question answering services on search engines. Existing question answering systems are mainly constructed based on Bayesian models. Specifically, in an existing question answering system, multiple word features in a question input by a user are input into a trained Bayesian model, and the trained Bayesian model outputs a predicted answer corresponding to the question. [0003] However, Bayesian models are bu...

AI Technical Summary

Problems solved by technology

In the existing question answering system, there is a contextual relationship between the multiple word features contained in the question, and they are not completely irrelevant independent features. Therefore, the existing question answering system based on the Bayesian model cannot well satisfy The assumption of feature independence, which leads to the low accuracy of the answers predicted by the question answering system

Images