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 paper proposes a learning path planning algorithm based on collaborative analysis of learning behavior through collaborative data analysis of online learning behaviors. The algorithm, based on the learner's online learning behavior data set, first establishes the concept interaction degree model of knowledge points and the directed learning path network, and proposes a local structure similarity measurement method between the knowledge nodes of the directed learning path network. Second, based on the learner's Kullback-Leibler divergence (KLD) 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 analyze the personalized optimal learning path of each kind of learners. Finally, the clustering algorithm and the evaluation index of the directed complex network have both verified the advantages of the algorithm. This paper 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 hereof. The results show that the learner's learning effect has been improved, verifying the validity and reliability of the algorithm. INDEX TERMS local structural similarity on the knowledge node of the directed learning path network, similarity measure on learning behavior, concept interaction degree of knowledge points, individualized optimal learning path

To improve learners’ performance in online learning, a teacher needs to understand the difficulty of knowledge points learners of different cognitive encounter levels in the learning process. This paper proposes a difficulty-based knowledge point clustering algorithm based on collaborative analysis of multi-interactive behaviors. Firstly, combining the group-directed learning path network, forgetting factors and the degree of student-system interaction, we propose a measurement model to calculate the similarity of the difficulty between knowledge points on student-system interactive behavior. Secondly, to solve the data sparsity problem of interaction, we propose an improved similarity model to calculate the similarity of the difficulty between knowledge points on student-teacher and student-student interactive behavior. Finally, the knowledge point difficulty similarity matrix is obtained by integrating the difficulty similarity of knowledge points obtained from student-system interactive behavior, student-teacher interactive behavior, and student-student interactive behavior. The spectral clustering algorithm is used to achieve knowledge point difficulty classification based on the obtained similarity matrix. The experiments on real datasets show that the proposed method has better knowledge point difficulty classification results than the existing methods.