Study Of E-learning Personalized Recommendation System

With the continuous development of the network technology, Web-based E-Learning is changing the way of people acquire knowledge, more and more learners eager to acquire more knowledge through more personalized and intelligent way. In E-Learning environment, with the rapid expansion of teaching resources and information, the "information overload", "resources lost" and other problems appeared one after another. How to push out the most suitable resources information for students from the huge information is the pleas problem to be solved.Bases on Semantic Ontology technology, Agent technology and so on other artificial intelligence theories and in conjunction with the personalized recommendation system technology, on the basis of sufficient analysis for interest of students, this paper proposes a new semantic-oriented strategy of recommendation system, It can be meet the requirements of different students, and select the most suitable knowledge or supplementary material in accordance with the needs and interest of the learners, and intelligently navigate for the study process of students.The main research contents of this paper have: Firstly, it researches the background of E-Learning personalized recommendation system and the development of the current situation at home and abroad. Secondly, based on E-Learning personalized recommendation system functions to be achieved, we offer a system framework of the E-Learning personalized recommendation system. It proposes personalized recommendation workflow system. The paper describes the resources knowledge Ontology base and students' interest Ontology by Ontology theoretic, and discusses the process and methods of construction these Ontology. Thirdly, it proposes a new semantic matching technology to match and filter interest for students. It can not only discover hidden interest for students and but also can filter out the information that students are not interested. We proves that effectiveness of this recommendation methods through experiments. Finally, based on in the front of the chapters,it proves the usefulness and Effectiveness of this personalized recommendation system through experiment.