Problem generation method and device and storage medium

Abstract

The embodiment of the invention provides a problem generation method and device and a computer readable storage medium. The problem generation method comprises the steps of identifying a text type ofa to-be-processed document according to a text structure; Selecting a generation model corresponding to the text type, wherein the generation model comprises at least one of an explicit question generation model, a structured and semi-structured question generation model and a natural language question generation model; And generating a problem for the to-be-processed document by using the selected generation model. According to the embodiment of the invention, aiming at the characteristics of different text types, the most suitable generation model is selected for the whole document or each part of text of the whole document, so that the problem generation accuracy is improved.

Description

technical field [0001] The present invention relates to the field of information technology, and in particular to a question generation method, device and computer-readable storage medium. Background technique [0002] FAQ (Frequently Asked Questions, question answering system) is the main means of providing online help on the current network. It organizes some possible frequently asked question and answer pairs in advance and publishes them on the web page to provide consulting services for users. [0003] FAQ implementation methods in the prior art mainly include the following types: [0004] (1) General question answering system, based on retrieval or knowledge based question answering service. [0005] (2) Customized retrieval, creating an index for document content segmented and word-segmented; or, obtaining question-answer pairs through document structuring or manual screening. [0006] (3) Question retrieval based on word matching or synonym matching. [0007] The ...

AI Technical Summary

Problems solved by technology

[0008] (1) Retrieval-based or knowledge-based general question answering systems cannot address customized needs

[0009] (2) For the question-and-answer method by indexing document content, first of all, not all content is question-and-answer content, so storing the entire text will cause a waste of storage space; secondly, the accuracy of generating questions in this way is low, because words A hit does not mean that the current content is the answer; there is also the inability to judge the boundary of the answer and the inability to form a visual FAQ document

The current technology cannot deeply understand the text or generate good text

[0010] (3) Question retrieval based on synonym matching or word matching has poor generalization ability and low recall rate

Images