This research is mainly based on the research on learning space design at home and abroad, researching and discussing the definition, characteristics, significance and theoretical basis design principles of the learning space of SPOC flipped classroom, and then the real space of SPOC flipped classroom implemented by universities Design improvements with virtual space, through continuous classroom observation, interviews and other research, after two rounds of design, the university SPOC flips the classroom real space and virtual space model. In the virtual space, teachers use the platform to teach sports and health care, communicate with students, and formulate corresponding methods for common problems such as video knowledge points on the Internet to further promote the effective implementation of education. At the same time, adopting multiple evaluation modes such as the combination of process evaluation and result evaluation, increasing the reward mechanism of the learning process, can improve the fairness of evaluation and also enhance students' learning enthusiasm. And through questionnaire surveys, interviews to optimize the improvement effect of SPOC flipped classroom real space and virtual space. After the combination of VR and flipped classroom, student satisfaction rose from 4.19 to 4.6486. The research results show that the flipped classroom teaching method based on VR technology realizes the fair distribution of teaching resources and the differential distribution of personalized teaching resources. The comprehensive ability of students has been significantly improved, and the diversification of teaching evaluation models has been realized.

With the rapid development of social economy and the extensive and in-depth development of national fitness activities, national physical fitness monitoring and research work has achieved rapid development. In recent years, the application of deep learning technology has also achieved research breakthroughs in the field of computer vision. How deep learning technology can effectively capture motion information in sample data and use it to realize the recognition and classification of human actions is currently a research hot spot. Today’s popularization of various shooting devices such as mobile phones and portable action cameras has contributed to the vigorous growth of image data. Therefore, through computer vision technology, image data is widely used in practical application scenarios of human feature recognition. This paper proposes a deep learning network based on the recognition of human body feature changes in sports, improves the recognition method, and compares the recognition accuracy with the original method. The experimental results of this paper show that the result of this paper is 1.68% higher than the original recognition method, the accuracy rate of the improved motion history image is increased by 14.8%, and the overall recognition rate is higher. It can be seen from the above experimental results that this method has achieved good results in human body action recognition.