Automatic interaction method, storage medium and terminal

Abstract

The invention discloses an automatic interaction method, a storage medium and a terminal. The automatic interaction method comprises the steps of obtaining a user question; obtaining a plurality of answers for the user question by using at least two ways; and screening the plurality of answers according to the source parameters of the answers and the prediction probability, wherein the source parameters and the prediction probability of the answers are determined according to the obtaining mode of the answers, the source parameters of the answers comprise the generation time of the answers, and the screening specifically comprises the steps of determining the importance weight corresponding to the answer according to the source parameter of each answer; calculating the product of the importance weight of each answer and the prediction probability; calculating the quotient of the product of each answer and the the genratrion time to serve as the effective score of each answer; screeningthe plurality of answers according to the effective scores of the answers; and outputting the screened optimal answer. According to the technical scheme, the response accuracy and continuity in the question and answer interaction process can be improved.

Description

technical field [0001] The invention relates to the technical field of natural language processing, in particular to an automatic interaction method, a storage medium, and a terminal. Background technique [0002] In the field of artificial intelligence technology applications, more and more intelligent question answering products have emerged. Generally speaking, the accuracy and speed of responses to user questions are important factors that affect the quality of intelligent question answering products. [0003] There are many question and answer processing methods in the prior art, and commonly used methods are rule-based, template-matching-based, retrieval-based, and generative-based. Among them, the retrieval-based approach is to generate answers by retrieving existing knowledge points in the knowledge base. The knowledge base usually includes multiple knowledge points, and each knowledge point includes standard questions and corresponding extended questions and answer...

AI Technical Summary

Problems solved by technology

[0004] However, in the methods based on rules, template matching, and retrieval, templates, examples or databases have limitations, and lack of effective language understanding, resulting in certain deficiencies in the accuracy and flexibility of answers; And the training model, the model complexity is high, and the stability of the answer acquisition process is low

Images