Research On Personalized Learning Path Recommendation Base On Improved Binary Particle Swarm Optimization

With the continuous integration of information technology and educational applications,online learning has been widely used in education.However,the existing online learning system still has many problems,mainly in three aspects: The first is that learners are prone to "learning trek" and "cognitive overload" when faced with a large amount of learning resources in the online learning system."The second phenomenon is that most online learning systems cannot accurately and comprehensively analyze the individualized characteristics of learners,resulting in a low degree of matching between the personalized learning path pushed by the existing online learning system and the learner's needs.The third is that the algorithm used by the personalized learning path recommendation function provided by the current online learning system has a slow convergence speed and a low convergence precision,so that the personalized learning path recommended to the learner cannot satisfy the learner's needs.In order to solve the above problems,this paper proposes a personalized learning path recommendation method MABPSO-PLP based on the modified binary particle swarm optimization algorithm based on the nonlinear increase of inertia weight and the exploration of unknown space.Firstly,the related literatures on personalized learning path recommendation and intelligent optimization algorithm are reviewed.Secondly,the current cognitive ability,expected goal and effective learning time of the learner in the online learning environment are analyzed,and the learning resource difficulty and learning resources are combined.The knowledge points and time features are included to construct the feature model(LEET)for learners and learning resources.Thirdly,for the problem that BSPO algorithm is not easy to escape from local optimization in the late stage of optimization,the improved binary particle swarm optimization algorithm MABPSO is designed.The improvement of the algorithm improves the convergence speed and convergence precision of the algorithm and is easy to jump out of the local optimum,thus solving the problem that the recommendation accuracy of the personalized learning path is not high,and improving the recommendation efficiency.Finally,the LEET model is optimized by the proposed recommendation algorithm MABPSO,and the personalized learning path recommendation method MABPSO-PLP is proposed.In order to verify the recommended effects of the model and algorithm,this paper designed the simulation experiment and the learning platform with C language course as an example to verify the running performance and practical application effect of the proposed method.The above experiments show that the proposed method can improve the matching degree between the personalized learning path and the learner's needs,and improve the accuracy of MABSPO applied to the personalized learning path recommendation.