Combined wrong question recommendation method based on knowledge graph

Abstract

The invention discloses a combined wrong question recommendation method based on a knowledge graph. Wrong questions relevant to weak knowledge points of a learner can be accurately recommended for the learner by adopting the method. The method comprises the steps that knowledges are extracted from large-scale unstructured test question data to establish the knowledge graph; text mining and word segmentation are conducted on the wrong questions of the learner to extract wrong question keywords, and thus knowledge points including in the wrong questions are determined; semantic near neighbors of the knowledge points are obtained by analyzing semantic similarity of the test questions; the wrong question knowledge points are mapped into the knowledge graph to obtain test question entities conforming to their knowledge points. In addition, similarity weight calculation is conducted on a test question library to obtain similarity matrixes of test paper, a collaborative filtering technology is utilized to obtain recommended test questions of the wrong questions. Finally, two recommendation results are further combined in weighing, mixing, superposing and element-level modes, and a final recommendation result is given.

Description

technical field [0001] The invention belongs to the technical field of computer software, and in particular relates to a method for recommending combined wrong questions based on knowledge graphs. Background technique [0002] With the rapid development of the Internet, people have gradually entered an era of information overload from an era of information scarcity. The explosive growth of information has made the problem of information flooding in the network extremely serious. It is difficult for users to find valuable data for themselves from the massive data, and some useful information that is rarely paid attention to is often overwhelmed In the ocean of information, become an island of information. The recommendation system is an effective way to solve such problems, and its essence is to find resource objects that match their interests and preferences for users. [0003] In recent years, in view of the great value of recommendation technology in various fields, expe...

AI Technical Summary

Problems solved by technology

Content-based recommendations are not friendly enough to deal with complex attributes, and at the same time cannot produce good recommendations for new users

Rule-based recommendation technology relies too much on grammatical rules defined by language experts in professional fields. It takes a lot of time to extract rules, and the labor cost is too high. At the same time, the migration cost is huge.

The similarity measurement is inaccurate and the recommendation quality is low in the case of extremely sparse data in the item-based collaborative filtering recommendation algorithm.

At the same time, with the continuous development of recommendation algorithms, people are beginning to realize the defects of existing recommendation systems, such as the cold start problem caused by data sparseness, recommendation accuracy and Gray sheep

Images