基于高维张量分解的个性化教育资源推荐算法研究

Research and application of personalized education resource recommendation algorithm based on high-dimensional tensor decomposition

随着互联网及在线教育平台的加速发展,积累了大量的教育资源,学习者对网络平台中教育资源的利用依赖性不断提高,但需要花费大量的时间和精力去筛选符合自己的资源~([1])。目前,在线平台为学习者们提供的内容基本相同,未能针对个性化的要求提供差异化的资源~([2])。文章所构建的基于高维张量分解的个性化教育资源推荐算法,在分解中能够保留高维空间的信息完整性,避免了传统推荐算法在分解中原始信息和特征的丢失,从而为个性化学习资源推荐的研究提供参考。

With the rapid development of Internet and online education platform,it has accumulated a lot of educational resources,learners are increasingly dependent on the use of educational resources in it,but it needs to spend a lot of time and energy to select the suitable resources.At present,the online platform provides basically the same content for learners,and fails to provide differentiated resources for personalized requirements.The personalized education resource recommendation algorithm based on high-dimensional tensor decomposition constructed in this paper can retain the information integrity of the high-dimensional space during decomposition,avoiding the loss of original information and features in the decomposition of traditional recommendation algorithms,thereby providing personalized provide reference for research on learning resource recommendation.