基于Web数据挖掘的个性化网络教学平台的研究

Research on personalized network teaching platform based on Web data mining

针对传统的网络教学平台选课过程中缺乏个性化推荐的缺点,提出一种基于Mini Batch K-Means算法的课程推荐聚类分析方法,该方法通过对网络教学平台中的课程及学生分别进行聚类分析来实现个性化研究。与标准的KMeans算法相比,Mini Batch K-Means算法选取小批量的数据子集,从而加快了计算速度,减少了k均值的收敛时间。文章通过一个实例说明了该方法在面对海量的网络数据时,能够更高效地实现选课过程中的课程个性化推荐。

Aiming at the shortcomings of traditional network teaching platform that lacks personalized recommendation,this paper proposes a clustering analysis method based on Mini Batch K-Means algorithm.The method realizes individualized research by clustering the courses and students in the network teaching platform.Compared with the standard K-Means algorithm,Mini Batch K-Means algorithm selects small subsets of data,which speeds up the calculation and reduce the convergence time of K-Means.This paper illustrates an example that can effectively implement the personalized recommendation of the courses during the course selection process in the face of massive network data.