【摘要】 学习路径推荐是解决信息超载、学习迷航等问题的关键，但当前的学习路径推荐相关研究存在推荐方法脱离学习场景、推荐结果缺乏解释等问题。为此，文章构建了基于知识图谱的可解释学习路径推荐模型：首先利用邻域标定的图注意力网络表征知识图谱语义信息并生成候选学习路径集，然后计算不同学习场景下学习者与候选学习路径之间的契合度和匹配度，最终实现可解释的学习路径推荐。之后，文章通过对基于知识图谱的可解释学习路径推荐模型与学习路径推荐基线模型进行对照实验和可解释案例分析，发现基于知识图谱的可解释学习路径推荐模型不仅提高了推荐结果的准确度，而且提升了推荐结果的可解释性。文章的研究有助于学习者获得准确、可解释的学习路径，从而提升个性化学习效果。更多还原

【Abstract】 Learning path recommendation is the key to solving the problems of information overload and learning disorientation. However, the current research on learning path recommendation has some problems, such as the separation of recommendation methods from learning scenarios, and the lack of explanation of recommendation results.Therefore, this paper proposed an explainable learning path recommendation model based on knowledge graph. Firstly,the neighborhood calibrated graph attention network was used to represent the semantic information of knowledge graph and generated the candidate learning path set, and then the integrating and match degree between learners and candidate learning paths under different learning scenarios were calculated, and finally the explainable learning path recommendation was realized. After that, through the comparative experiment and explainable case analysis of explainable learning path recommendation model based on knowledge graph and the learning path recommendation baseline model, it was found that the explainable learning path recommendation model based on knowledge graph not only enhanced the precision degree of recommendation outcomes, but also improved the explanation of recommendation outcomes. The research of this paper could help learners to obtain precise and explainable learning paths, thereby improving personalized learning effects.更多还原