摘要

人工智能逐步应用于高校体育教学中的动作识别、学习反馈和内容生成。操舞类体育课程兼具动作规范性与艺术表现性，动作学习、队形创编、团队配合和艺术表现等任务在技术适用性上存在明显差异。本文采用文献资料法和课例分析法，以高校校园健身操舞课程为例，从任务的可观测性、判断标准明确程度和情境依赖程度分析课程中的人机任务分工。研究认为，动作标准较明确、外部表现容易识别的任务，适合由人工智能承担较多动作识别、问题筛查和基础反馈工作；动作组合、队形及团队配合等情境依赖较强的任务，需要人工智能提供信息或方案，由教师和学生结合具体教学条件共同判断；艺术表现、审美评价及育人任务则更多依赖教师专业指导。在此基础上，研究进一步将操舞课程中的人机协同概括为智能筛查、专业判读和教学注意力再配置三个相互衔接的环节。人工智能对重复性、标准相对明确的问题进行初步处理后，教师能够将更多课堂时间用于个体指导、艺术表现、团队协作等需要综合判断的教学任务。

Abstract

Artificial intelligence (AI) is increasingly being applied in higher education physical education, particularly in movement recognition, learning feedback, and content generation. Dance-based physical education courses involve both movement standardization and artistic expression. Students are required not only to repeatedly practise and refine bodily movements, but also to engage in rhythmic expression, group coordination, and creative choreography. These instructional tasks vary considerably in their suitability for AI-assisted teaching. Using literature review and lesson-based case analysis, this study takes a university campus fitness dance (line dance) course as an illustrative case. Drawing on the course syllabus, teaching plans, individual lesson designs, and choreography materials, it examines the division of tasks between AI and human participants along three dimensions: task observability, clarity of evaluation criteria, and contextual dependence. The findings suggest that tasks characterized by clearly defined movement standards and readily observable external performance are well suited to AI-assisted movement recognition and preliminary feedback. Tasks involving movement combinations, spatial formations, and group coordination are more context-dependent and therefore require collaborative judgment involving AI, teachers, and students. By contrast, artistic expression, aesthetic evaluation, and educational development rely more heavily on teachers’ professional guidance. On this basis, the study identifies a three-stage collaborative process: movement learning and AI-assisted diagnosis—professional interpretation and collaborative decision-making—embodied correction and creative iteration. Through repeated practice, AI-generated feedback, teacher judgment, and embodied learning are continuously integrated into the instructional process.

参考文献