A Review of Research on AI Empowering Precise Profiling and Intervention System Construction for College Students’ Physical Health
TL;DR
An integrated AI+physical-health framework consisting of a perception layer, data layer, algorithm layer, application layer, and optimization layer is proposed, which provides a theoretical basis for IoT-enabled physiological monitoring, sensor-network-based health management, and intelligent intervention systems in university environments.
Abstract
Declining physical health among college students and the inefficiency of traditional intervention models require a systematic health-management framework supported by artificial intelligence and multimodal sensing. This review summarizes the technical progress of AI-enabled physical-health profiling and intervention for college students across the full chain of data acquisition, accurate profiling, intelligent diagnosis, personalized intervention, effect evaluation, and iterative optimization. Key technologies are analyzed, including wearable sensing, multimodal data fusion, machine-learning-based health-risk prediction, exercise-prescription generation, intervention-process monitoring, and dynamic feedback control. Existing studies show that AI-supported systems can expand data dimensions, improve risk-warning timeliness, support personalized intervention plans, and strengthen continuous monitoring. However, important bottlenecks remain in data standardization, algorithm generalization, cross-platform compatibility, ethical governance, and long-term campus deployment. Based on these limitations, the study proposes an integrated AI+physical-health framework consisting of a perception layer, data layer, algorithm layer, application layer, and optimization layer. The framework provides a theoretical basis for IoT-enabled physiological monitoring, sensor-network-based health management, and intelligent intervention systems in university environments.