基于知识点层次算法的习题推荐
首发时间:2019-09-05
摘要:面向学生的个性化试题推荐是智能教育领域重要的研究课题,现有的试题推荐大多采用协同过滤的方法。然而,协同过滤的试题推荐方法往往忽略了学生的知识点掌握情况和认知层次的区分。针对以上问题,本文提出了一种基于知识点层次算法的习题推荐方法。该推荐方法分为3步。第一步构建知识点层次关系的权重图,该权重图有效反映知识点间的层次关系。第二步根据学生对知识点的掌握情况,在知识点层次图的基础上提出了一种个性化习题推荐算法。第三步通过更新学生-知识点失分率矩阵,获取学生掌握薄弱的知识点,以此实现习题推荐。最后,本文将该推荐方法与协同过滤的试题推荐方法进行对比,证明了该方法在进行学生试题推荐时能够保持更高的精确性和可解释性。
For information in English, please click here
Problem recommendation based on point level algorithm
Abstract:Personalized question recommendation for students is an important research topic in the field of intelligent education. However, the recommendation method of collaborative filtering often neglects the distinction of knowledge point mastery and cognitive level of students. In view of the above problems, this paper proposes a problem recommendation method based on the point level algorithm. The recommended method is divided into three steps. The first step is to construct the weight graph of the hierarchical relations of knowledge points, which can effectively reflect the hierarchical relations among knowledge points. In the second step, according to students\' knowledge of knowledge points, a personalized problem recommendation algorithm is proposed based on the knowledge point hierarchy map. The third step is to obtain the weak knowledge points by updating the student-knowledge point loss rate matrix, so as to realize problem recommendation. Finally, this paper compares the proposed method with the collaborative filtering method, and proves that the proposed method can maintain higher accuracy and interpretability.
Keywords: knowledge points hierarchy map Personalized problem recommendation loss rate matrix
基金:
引用
No.****
动态公开评议
共计0人参与
勘误表
基于知识点层次算法的习题推荐
评论
全部评论0/1000