A Hybrid Automatic Question Answering Method Based on Educational Knowledge Graph and Text

Abstract

The invention belongs to the technical field of intelligent education question-answer, and particularly relates to a mixed automatic question-answer method based on education knowledge graphs and texts. The mixed automatic question-answer method comprises the following steps: constructing a basic education knowledge graph by constructing a basic education body, semantic annotation and informationextraction; constructing a general template of the question according to the keywords in combination with a regular expression; establishing a full-text search engine, and preprocessing mass texts; training test question and answer pairs as a training set until a deep text matching model converges; identifying the user questions to obtain a subject list, and endowing the subject list with confidence; carrying out template matching to obtain a predicate list, and giving confidence to the predicate list; inquiring a knowledge graph according to the subject and predicate lists to obtain an answerlist, and endowing confidence coefficients; obtaining keywords by using a part-of-speech tagging method, performing coarse-fine granularity matching to obtain answers, and sorting the answers; if thehighest confidence of the answer based on the educational knowledge graph exceeds a threshold value, returning the answer; or, returning the answer with the highest sorting based on the text.

Description

technical field [0001] The invention belongs to the technical field of intelligent education question answering, and in particular relates to a hybrid automatic question answering method based on educational knowledge graphs and texts. Background technique [0002] Smart Education has become an important form of development in the field of education under the background of the information age. The essence of smart education is to use intelligent technical means to build an intelligent environment, so that students can acquire knowledge and answer questions faster and better. The automatic question answering system is undoubtedly a very effective method. On the one hand, the automatic question answering system can help primary and middle school students answer questions and solve doubts, so that they can get answers to questions in a timely manner during the daily learning process. On the other hand, because of its good human-computer interaction, it can significantly impro...

AI Technical Summary

Problems solved by technology

[0005] At present, people have carried out some work on the question answering system in the field of basic education, but these works have the following problems: they only do question answering based on a single source such as knowledge graph or text, and fail to make comprehensive use of the respective advantages of the two sources, which are specifically reflected in: The knowledge in the knowledge map is accurate and highly structured, but the coverage of knowledge is not as good as that of the text; the text contains all the knowledge, but due to unstructured, semantic analysis is more difficult; if only based on the knowledge map to answer user questions, then many None of the questions can be answered; if user questions are answered only based on text, many questions will be answered incorrectly

In addition, for the field of basic education, textbooks and supplementary materials are the most authoritative resources, and the existing question-and-answer system for basic education has not carried out fine excavation and processing of knowledge in textbooks and supplementary materials; the interdisciplinary correlation of knowledge points in the field of basic education Many, the existing basic education question answering system does not comprehensively consider the knowledge of the whole subject

Images