Research On The Recommendation Strategy Of Personalized Learning Resources In Mobile Environment

With the popularity of mobile smart devices and the development of communication technology, the main communication media of the Internet has shifted from the traditional PC end to the mobile end in recent years. Although the media has changed, but the mobile users are still faced with persistent ailment of the "information explosion" and "information overload" in the Internet era. By the limit of mobile devices with low computing power and small display area, the problem is more serious. Personalized recommendation technology is proposed and applied to effectively alleviate the current problems, which is based on the user’s interest orientation to predict the user’s preference for resources to form a list of recommendations. With 20 years of research history, personalized recommendation technology research has made extraordinary achievements, especially in the field of electronic commerce. The wave of mobile Internet has promoted the research and application of personalized recommendation technology in mobile field, but it has not reached a perfect level for the lack of application research in specific areas.Based on the personalized recommendation of mobile learning resources, the strategy of recommendation in mobile environment is studied in this paper. The paper gives the present situation of the mobile learning resource recommendation of the domestic and foreign research, mobile learning concept, context aware service system and the various personalized recommendation algorithm realization principles with the advantages and disadvantages, which provide the important theoretical basis. In this paper, the principle of the personalized recommendation algorithm based on collaborative filtering technology is discussed, then, a personalized mobile learning resource recommendation algorithm called MCCF is proposed. The algorithm effectively alleviates the two existing problems in the current research:one is to strengthen the study of the mobile situation context of mobile learning resources in the personalized recommendation, in order to improve the accuracy of the results;the other one is to consider the complexity of the algorithm in order to meet thetimeliness of the requirements in terms of recommendation for the limitations of the computing performance of mobile terminals. By extracting from the learner’s mobile context as the learner’s preference feature, realizing the transformation of U(learner)×I(learning resources)×C(mobile context) three-dimensional model to the U×I two-dimensional model, so the results can be obtained by using the traditional collaborative filtering algorithm. Through further research, the relationship between the mobile situation and the resource characteristics can be obtained by Using the data analysis and data mining technology, which can dynamically reflect the user’s preferences, thus optimizing the final recommendation results. MCCF algorithm is not only fully integrated into the learning situation of mobile information, but also take into account of the complexity of the algorithm.The final experimental results show that the algorithm is superior to the traditional algorithm in both accuracy and user satisfaction, and it is more timely and suitable for the mobile terminal.