Closed Home Physical Education Teaching Model and Response Strategies Based on Big Data Technology

Area of Science:

• Sports Science
• Educational Technology
• Artificial Intelligence

Background:

• The COVID-19 pandemic necessitated a nationwide shift to online teaching, including physical education (PE) in schools and universities.
• Online PE represents a significant transition from an auxiliary tool to a primary teaching method, altering subject matter, audience, and pedagogy.
• The shift to online PE supports the popularization of lifelong exercise concepts.

Purpose of the Study:

• To propose measures for enhancing physical education teachers' online teaching capabilities in the post-epidemic era.
• To explore the integration of online and offline physical education, and school sports with social sports.
• To design an AI and big data-based model for accurate evaluation of closed home sports teaching effects.

Main Methods:

• Analysis of online physical education characteristics and teacher training systems.
• Development of a big data and artificial intelligence model for remote sports teaching.
• Utilizing convolutional neural networks (CNNs) to process PE video sequences for performance analysis.

Main Results:

• The proposed AI model, integrated into a big data framework, effectively evaluates online sports teaching effects with high precision.
• The system demonstrates improved computational rates while maintaining high accuracy in assessing PE teaching outcomes.
• The methodology mitigates interference from the home teaching environment.

Conclusions:

• The developed AI model enhances the accuracy and efficiency of evaluating online physical education teaching.
• This approach supports the reform and integration of physical education within broader educational and social contexts.
• Strengthening the management of internet-based physical education resources is crucial for future development.