AI-Enabled Reform of University Physical Education Curriculum under Modern Pedagogical Paradigms: A Deep-Learning–Driven Intelligent Teaching Framework

With the rapid advancement of artificial intelligence (AI) and deep learning, higher education is undergoing a paradigm shift toward intelligent, individualized, and data-driven instructional models.As a core component of university curricula, physical education (PE) must similarly evolve to support precise skill acquisition, personalized training, and objective performance assessment.However, traditional PE instruction often relies on subjective observation, uniform training structures, and limited formative feedback, constraining student engagement, motor-skill development, and learning efficiency.To address these limitations, this study investigates an AI-driven reform pathway for university PE and proposes an integrated intelligent PE framework that combines deep-learning-based human motion analysis, automated feedback mechanisms, and data-driven personalized training plans.The system leverages pose-estimation models and multi-dimensional motion features to evaluate movement quality, track physical literacy development, and generate individualized corrective guidance in real time.Edge-enhanced inference and privacy-preserving data pipelines ensure deployability in real campus environments.Experimental evaluation across benchmark datasets and university pilot scenarios demonstrates that the proposed framework substantially improves motor-skill recognition accuracy, movement-quality scoring, and learning-progress stability, achieving up to +8.5% accuracy, +15.9% biomechanical quality, and +18.3% progression improvement over competitive baselines.