Question and answer pair evaluation method and device, storage medium and equipment

Abstract

The invention discloses a question and answer pair evaluation method and device, a storage medium and equipment. The method comprises the following steps: 1, ; first, a first evaluation index is generated according to the number of segmented words of a question in a to-be-evaluated question-answer pair; generating a second evaluation index according to the correlation between the theme and the answer in the to-be-evaluated question and answer pair, and generating a third evaluation index according to the word number of the answer in the to-be-evaluated question-answer pair, then, a pre-constructed question and answer pair evaluation model is used; evaluating the first evaluation index, the second evaluation index and the third evaluation index; the quality of the question-answer pair to beevaluated is obtained; compared with a manual evaluation mode; the quality of the question-answer pair to be evaluated can be quickly and accurately obtained; the evaluation result eliminates the influence caused by the subjectivity of manual evaluation, and when the question and answer pair is evaluated, the word segmentation number of the question in the question and answer pair to be evaluated, the correlation between the theme and the answer and the word number of the answer are considered, so that the quality of the question and answer pair can be evaluated more accurately.

Description

technical field [0001] The present application relates to the field of natural language understanding, and in particular to a question-answer pair evaluation method, device, storage medium and equipment. Background technique [0002] Intelligent question answering is an important application in the field of artificial intelligence. Compared with traditional artificial customer service systems, intelligent question answering systems have many advantages such as high efficiency and low cost. At present, more and more enterprises use intelligent question answering systems to provide users with dialogue services to improve user service satisfaction. [0003] In practical applications, when the intelligent question answering system receives a question from the user, the intelligent question answering system will automatically query the answer corresponding to the question from the pre-built knowledge base and return it to the user. Among them, a large number of question-answer p...

AI Technical Summary

Problems solved by technology

At present, when expanding the knowledge base, it is usually the way of multi-person collaboration or document extraction of question-answer pairs, that is, multiple people simultaneously add question-answer pairs to the knowledge base or automatically extract question-answer pairs from documents, but when multiple people simultaneously contribute to When adding question-answer pairs to the knowledge base, it is easily affected by personal subjective factors. The quality standards of the added question-answer pairs are inconsistent, and the method of automatically extracting question-answer pairs from documents cannot guarantee the quality of the extracted question-answer pairs. Therefore, for adding to Question-answer pairs in various fields in the knowledge base usually require manual evaluation and screening by professionals in various fields. However, this manual evaluation method is highly subjective and difficult to quantify. Not only the evaluation efficiency is low, but also requires spend a lot of human resources

Images