基于隐式评分和相似度传递的学习资源推荐

协同过滤推荐算法存在数据稀疏的问题。这使得学习平台中，由于用户学习行为记录的稀疏而无法满足用户的学习需求。为此，本文提出了一种基于隐式评分和相似度传递的学习资源推荐算法。首先，收集用户的学习行为；其次，改进传统的相似度计算方法，并在此基础上引入相似度传递策略；最终应用并实现E-earning平台中学习资源的推荐。实验表明，该算法能够在一定程度上解决相似度计算不准确以及数据稀疏问题，从而提高学习资源的推荐质量。

Learning resource recommendation based on implicit scoring and similarity propagation

Traditional collaborative filtering recommendation algorithm has the problem of sparse data. This makes the learning needs of users cannot be satisfied because of the sparsity of user learning behavior records. To address this issue, this paper proposed a learning resource recommendation algorithm based on implicit rating and similarity propagation. Firstly, collected the user''s learning behavior. Secondly, improved the calculation method of similarity; On the basis of this, introduced the similarity propagation strategy. Finally, applied and implemented the collaborative filtering algorithm based on personalized learning resources in E-learning. Experiments show that the proposed algorithm can solve the problem of inaccurate and sparse data, and improve the quality of learning resources.