The online delivery of physical education poses challenges due to its distinctive attributes, primarily stemming from the difficulty in ensuring comprehensive oversight of instructional content. In response, we advocate for the implementation of a multi-faceted computational system within a big data framework tailored explicitly for online physical education. Initially, we engineer a parallel, multi-objective real-time instructional supervision mechanism employing sensor technology and long-range transmission capabilities to cultivate an environment conducive to physical education while efficiently gathering pertinent data. Subsequently, we introduce a multi-functional robot-assisted methodology for supervising physical education intelligently, proficiently overseeing students’ activities and sports engagements, thereby facilitating comprehensive analysis of instructional content. Concluding this framework, we present an adaptive matching algorithm tailored for physical education instruction, utilizing the outcomes of content analysis and sports item recognition to recommend subsequent instructional segments. Our demonstration validates the precision of our teaching assistant methodology in accurately identifying sports items, achieving an impressive accuracy rate of 90.72%. Furthermore, our adaptive matching algorithm garners an 80% approval rating in subjective evaluations, establishing its utility as a supplemental resource for online physical education.
Ye et al. (2026) studied this question.