基于数据挖掘的学习效果评估算法设计

Design of learning effect evaluation algorithm based on data mining

针对传统的线上教学效果评估方法主要依据学生的考试成绩来判定,存在延迟性较大、无法做到实时反馈等问题,文中使用FP-Growth算法对数据频繁项集进行挖掘,并通过创建FP-Tree来存储学习者的行为数据,进而挖掘出数据间潜在的关联规则。同时,为了克服该算法因存在递归现象而导致数据集膨胀且计算困难的缺点,采用了PFP并行系统来求解FP-Growth算法,有效提升了该算法的运行速度。在实验测试中,所设计算法的运行效率明显优于对比算法,且在数据集数量较大时仍可对其进行处理,这表明该算法还能够提升数据的存储容量。

In view of the traditional online teaching effect evaluation method,which is mainly based on the students’ examination results,there are some problems,such as large delay,unable to achieve realtime feedback and so on,this paper uses FP-Growth algorithm to mine frequent itemsets,and creates FP Tree to store learners’ behavior data,so as to mine potential association rules between data. At the same time,in order to overcome the shortcomings of data set expansion and difficult calculation caused by recursion,PFP parallel system is used to solve FP-Growth algorithm,which effectively improves the running speed of the algorithm. In the experimental test,the operation efficiency of the designed algorithm is obviously better than the comparison algorithm,and it can still be processed when the number of data sets is large,which shows that the algorithm can also improve the storage capacity of data.