Enhancing Efficient Personalized Learning and Educational Management in Universities Using Graph Neural Networks in Intelligent Tutoring Systems

Personalized learning has become an essential strategy for accommodating the diverse and evolving needs of learners within contemporary educational environments. Traditional educational models, however, often fall short in capturing the intricate and ever-changing nature of individual learning trajectories. In response to these limitations, this study introduces an innovative framework that utilizes graph-based modeling techniques to advance the field of personalized learning black and university education management. Central to this framework are two core components: the Knowledge Dynamics Model (KDM) and the Adaptive Knowledge Reinforcement Strategy (AKRS). These components collaboratively facilitate the modeling of complex knowledge states, individual learning paces, and the phenomenon of cognitive decay over time. By representing curricular content as a directed acyclic graph (DAG), the framework accurately depicts learning sequences, prerequisite structures, and conceptual dependencies, thus enabling tailored instructional pathways and enhanced skill transfer in university education management scenarios. Moreover, the approach incorporates real-time learner performance feedback and adaptive reinforcement mechanisms to promote sustained knowledge retention and mastery. Empirical evaluations confirm that the integration of KDM and AKRS leads to improved learning outcomes, including a 15.3% increase in learner engagement, by dynamically aligning instructional methods with learners’ cognitive development. This graph-based, data-driven framework offers a responsive and effective approach to delivering personalized education that evolves alongside each learner’s progress.