Construction of personalized online educational resources based on deep learning in higher education self-study examination environment

Higher education teaching and examination are facing the problems of “information overload” and “learning disorientation”. Online assessment of learners’ cognitive levels, combined with the knowledge structure of test question recommendation technology research, to improve the user’s learning efficiency has an important application value and research significance. In this paper, we propose a deep knowledge tracking model LFKT that takes into account both learning and forgetting behaviors, and comprehensively considers the interval time between learners’ repeated learning of knowledge points, the number of times they repeat learning of knowledge points, the interval time between sequential learning, and their mastery level of knowledge points. On this basis, it builds a personalized online education resource sharing platform that recommends online examination resources. The performance test is carried out on ASSIST2009 and other data and the visualization tracking of the mastery status of five students in the same knowledge point, and it is found that the mastery rhythm of different students for a certain knowledge point is basically the same, which is in line with the actual teaching and education and teaching laws, and the test questions with the same difficulty interval can make the knowledge level of the students grow. This study is a useful exploration for improving the efficiency of higher education.