面向在线学习平台的个性化学习路径推荐研究

Research on Personalized Learning Path Recommendation for Online Learning Platforms

信息时代飞速发展的同时带动了在线学习平台的发展,个性化学习路径推荐也成为其中的重要一环。论文主要对学习者的在线学习行为数据进行分析,使用K-means算法构建相似学习者模型,以此设计个性化学习路径推荐模型,同时采用Lasso-Lars算法,分析影响学习效果的各个影响因素的强度序列,进一步优化个性化学习路径推荐模型。该模型能够有效解决学习平台中学习者面临的信息过载问题,向在线学习者提供个性化、精准化学习服务。

The rapid development of the information age has led to the development of online learning platforms,and personal⁃ized learning path recommendations have become an important part of them.In this paper,learners'online learning behavior data is analyzed and the K-means algorithm is used to build a similar learner model to design a personalized learning path recommendation model,and the Lasso-Lars algorithm is used to analyze the intensity sequence of each influencing factor that affects the learning ef⁃fect and further optimize the personalized learning path recommendation model.The model effectively solves the problem of cumber⁃some learning resources faced by learners in online learning platforms,and provides personalised and accurate learning services to online learners.