Interactive intelligent question and answer method based on power grid practical training question and answer knowledge base

Abstract

The invention relates to an interactive intelligent question answering method based on a power grid practical training knowledge base. The method comprises the following steps: constructing the power grid practical training knowledge base containing question description and answers of power grid practical training; pre-training a semantic model base based on a neural network based on question description and answers in the power grid practical training knowledge base; the method comprises the steps that a user puts forward a question, an original text put forward by a questioner is obtained and preprocessed, and the original text is converted into a standard text; obtaining a historical problem proposed by a user, and performing context recognition on the standard text in combination with the historical problem to obtain a corresponding context recognition result; performing entity extraction on a standard text based on the context recognition result to obtain an entity extraction result; inputting the context recognition result and the entity extraction result into a semantic recognition model, and outputting a corresponding answer; and converting the answer into a natural language description text and replying to the user.

Description

technical field [0001] The invention relates to an interactive intelligent question-and-answer method based on a power grid practical training question-answer knowledge base, and belongs to the technical field of natural language processing. Background technique [0002] With the vigorous development of artificial intelligence technologies such as image recognition, speech recognition, and natural language processing, as well as the continuous landing in application fields such as electric power inspection, safety supervision, and marketing, power grid enterprises are building an artificial intelligence training environment and cultivating artificial intelligence professional teams. There is also a growing need to advance the broader adoption of AI technologies. It is hoped that through the artificial intelligence training environment of the power grid, it will provide users with an intelligent interactive answer mode based on natural language, provide accurate information a...

AI Technical Summary

Problems solved by technology

The problem with the above-mentioned prior art is that the conversational scene and the relevance of multiple questions asked by the user are not considered, but each question is answered independently, and it is difficult to avoid feedback of wrong answers to questions due to the inability to obtain rich user intention information

In certain conversational scenarios, it is also difficult to avoid feeding back wrong answers to questions due to the inability to obtain coherent user intent information

Images