Teaching Strategies and Implementation Paths for Interactive Mobile Learning Platforms in Higher Education

Abstract

Against the backdrop of widespread information technology and mobile devices, the digital transformation of higher education is advancing rapidly, and interactive mobile learning platforms have become key tools for overcoming the time-space limitations of traditional teaching and meeting students’ personalized learning needs. However, existing platforms still face practical challenges in areas such as teaching strategy formulation, implementation path optimization, and technological adaptability, limiting their educational value. Although current research addresses the development and application of mobile learning platforms, there are significant limitations. Some studies focus on technological architecture design but fail to deeply integrate teaching strategies with technology applications. Learning resource recommendations largely rely on historical user data, neglecting real-time learning states and interactive intentions. Furthermore, the application of collaborative filtering algorithms has not effectively incorporated graph neural networks with mobile interaction scenarios, resulting in insufficient recommendation accuracy and scenario adaptability. This paper focuses on two key areas: first, exploring the teaching application of interactive mobile learning platforms based on learning resource recommendations by analyzing the intersections between resource recommendation and teaching processes and developing personalized teaching strategies tailored to higher education scenarios; second, developing a collaborative filtering algorithm that integrates mobile interaction intentions with graph neural networks, incorporating real-time student interaction data into the algorithm model to enhance the accuracy of learning preference prediction and resource recommendations.