Test question recommendation method based on information extraction and knowledge graph

Abstract

The present invention claims a method for recommending test questions based on information extraction and knowledge map, including the steps of: performing entity recognition and entity relationship extraction on the test questions through a neural network model to obtain triple knowledge points examined by the test questions and form a test question knowledge map; According to the constructed knowledge map of test questions, a test question network based on the association of triple knowledge points is constructed; test questions are recommended according to wrong questions and test question networks. The present invention automatically extracts knowledge points from test questions through a neural network model, which can effectively save labor and avoid manual subjective deviations. In addition, the triplet knowledge points extracted by the present invention are larger than chapter knowledge points, and keyword knowledge points are more accurate. At the same time, it considers the combined relationship between the knowledge points behind the test questions, builds a test question network, digitizes and refines the relationship between test questions based on knowledge points, and recommends test questions based on the wrong questions and refined correlation information between test questions. It makes the recommended test results more accurate.

Description

technical field [0001] The invention belongs to the technical field of computer software, and in particular relates to a method for recommending test questions based on information extraction and knowledge graphs. Background technique [0002] With the development of Internet technology, the explosive growth of information has made the problem of information flooding in the network particularly serious. It is very difficult for users to find valuable data for themselves from massive data. In recent years, in view of the great value of recommendation technology in various fields, experts and scholars from all walks of life have devoted themselves to the research of recommendation technology. In the field of education, there are currently many online question bank websites that can assist students in extracurricular learning to achieve better learning effects, but it is very difficult to find valuable test questions for themselves among the massive test questions. [0003] On...

AI Technical Summary

Problems solved by technology

Such recommendation results are likely to cause users to repeat similar or identical questions, while ignoring the combination of knowledge points and knowledge points behind the test questions, reducing the user's learning efficiency, and there is also a cold start problem due to data sparsity.

Images