Research on the Optimization of Teaching Scenarios and Teaching Effectiveness in University Physical Education Classroom Teaching in the Context of Artificial Intelligence

Liu Yang

Guangdong University of Science & Technology

Abstract：

Artificial Intelligence (AI) is profoundly changing the ways in which university Physical Education (PE) teaching is organized, evaluated, and provided. Taking university PE classroom teaching scenarios as its research object and focusing on improving teaching effectiveness in the context of AI, this paper constructs a “scenario–technology–effect–feedback” analytical framework to systematically examine the current application, practical problems, and optimization paths of AI in university PE classrooms. The study finds that the current application of AI in university PE classrooms remains relatively superficial. Problems coexist, including incomplete data collection, single evaluation indicators, delayed learning feedback, vague student profiles, and insufficient precise provision, which constrain the overall improvement of teaching effectiveness. Accordingly, this paper proposes: strengthening the integration of intelligent devices and real-time multimodal data collection to realize a shift from experience-driven to data-driven teaching; optimizing the teaching effectiveness analysis system and constructing multidimensional evaluation indicators that combine process-based and outcome-based dimensions; transferring new media marketing thinking to achieve personalized teaching provision based on user profiles and enhance learning stickiness through community interaction; and improving implementation mechanisms such as teacher competence, data standards, platform sharing, and ethical safeguards. The study argues that the key to AI improving the effectiveness of university PE classroom teaching lies in deeply embedding technology into core teaching links, connecting data throughout the entire evaluation process, precisely matching student needs,and forminga closed-loop mechanism of “collection–analysis–feedback–optimization.”

Key Words：

Artificial Intelligence; university Physical Education; classroom teaching scenarios; teaching effectiveness; multimodal data; user profiles