Research On The Adaptive System Of Learning Content Based On Learning Style

Today, e-learning is popularization in various fields, it has the characteristics of timeliness and autonomy. Compared with online learning, learners prefer content adaptive learning system (LCAS), LCAS can provide personalized and dynamic interactive knowledge content, LCAS not only can help learners to facilitate their own learning,but also to analyze the individuality of the learner, and help learners to screen and integrate resources.This dissertation studies the LCAS which is based on learning style. First, this dissertation uses the learning style and online behavior matching in theory, builds learner style model; The LCAS model is established by using the convolution neural network and hybrid genetic particle swarm optimization, Which provides a reference for quantifying user characteristics and dynamic content. Then, this dissertation uses Hadoop?database?Ajax?Mahout?SMSH complete the LCAS based on learning style. The system has the functions of curriculum recommendation?route recommendation?style test?online learning?course record?topic square?real-time course review and so on, which can meet the needs of learners' autonomous learning and adaptive content guidance.The LCAS prototype has been completed and tested well on the Hadoop platform.Through the initial trial, the system can provide learners with an intelligent self-learning platform, which meet the needs of learners learning, personalized knowledge navigation can guide students, to achieve the goal of cultivating learners' autonomous learning ability.