Course recommendation method based on attention mechanism and knowledge graph

The invention discloses a course recommendation method based on an attention mechanism and a knowledge graph. The method comprises the following steps: collecting learning records of a learner; constructing a knowledge graph; analyzing demands and interests of the learner; and finally, carrying out personalized course recommendation. According to the method, the relationship between complex knowledge points is considered, the importance of different neighbor nodes under the same head node and the same relationship is deeply mined in the knowledge graph through an attention mechanism, and the attention degree of a learner to different head nodes and different relationships is deeply mined through the value of the normalized vector inner product; the two kinds of information are integrated to provide a basis for course recommendation, so that the recommendation effect is improved, and the recommendation accuracy is improved. 本发明公开了一种基于注意力机制与知识图谱的课程推荐方法，先收集学习者的学习记录；再构建知识图谱；分析学习者的需求和兴趣；最后进行个性化课程推荐。本发明考虑了复杂的知识点之间的