Learning Path Planning Algorithm Based On KL Divergence And Matrix Similarity

Studying learning path planning can help find useful implicit learning behavior patterns from learners' online learning behavior data,which is conducive to helping beginners or learners with low participation to reasonably arrange the learning sequence of online knowledge points.This path helps online learners complete learning goals efficiently and systematically.Through collaborative analysis of online learning behavior data,two learning path planning algorithms are studied in this thesis.The main content of the research constitutes the following two aspects:1.Aiming at the problem that the existing learning path planning algorithm fails to consider to which degree has the online learner mastered the knowledge points,a learning path planning algorithm based on KL divergence and matrix eigenvector similarity is proposed.The algorithm,based on the learner's online learning behavior data set,first establishes the conceptual interaction achievement model of knowledge points and the directed weighted learning path network,and proposes a local structure similarity measurement method between the knowledge nodes of the directed weighted learning path network.Second,based on the learner's KL divergence matrix,a learning behavior similarity calculation method on the basis of eigenvector matrix similarity is proposed,which is used to perform cluster analysis on learners with similar learning behaviors and to analysis the personalized optimal learning path of each kind of learners.Finally,the clustering algorithm and the evaluation index of the directed weighted complex network have both verified the advantages of the algorithm.2.Aiming at the problem of inaccurate clustering of learning behavior data in existing learning path planning algorithms,a new one based on KL divergence and difference matrix similarity is proposed.The algorithm first proposes a similarity calculation method for learning behavior based on the similarity of the difference matrix on the basis of the KL divergence matrix.Second,compared with the clustering algorithm based on the European norm matrix similarity model and the matrix eigenvector similarity model,the clustering algorithm based on the difference matrix similarity model has further improved the clustering evaluation index.Finally,a clustering algorithm based on the difference matrix similarity clusters learners with similar learning behaviors,and analysis the personalized optimal learning path of each kind of learners.The advantages of the algorithm have also been verified through the evaluation index of the directed weighted complex network.This author employs the online behavior data set and online test data set obtained from the e-learning platform to conduct an empirical analysis of the learning path planning algorithm proposed in this thesis.And the results show that the learner's learning effect has been improved,verifying the effectiveness and reliability of the algorithm.