With the help of spatial calculation and numerical analysis, this paper reveals the spatial distribution of rehabilitation infrastructures and the accessibility difference in the city Xiamen. The calculation of Moran’s I, Z value, and P value are, respectively, −0.229787, −0.122751, and 0.902304 for health facilities and −0.159235, 0.186166, and 0.852315 for fitness facilities. Such calculation results indicate an uneven pattern and varied accessibility numerical values. The reasons for this influence are diverse, but it is worth noting that the two-step floating catchment area (2SFCA) calculation shows that compared to fitness facilities, the standard deviation of accessibility numerical value of health facilities decreased significantly, which indicates that the accessibility of health service facilities is becoming better, while the change of accessibility of fitness facilities is not obvious. It is pointed out this is due to society’s insufficient attention and education on daily health. For better rehabilitation under the pandemic, the importance of fitness facilities should be noticed.

In China, sports parks, and green spaces are often spatially integrated to realize the multiple functions of shared green spaces and play an important role in the production and living services of its residents. In this article, it is collectively referred to as green sport space (GSS). Whether the distribution of GSS is equal has an important impact on the sustainable lifestyle and the rehabilitation under the pandemic. Based on the POI data of the Shanghai urban area, it is preliminarily found that the areas with extremely high and high production and living densities are mainly distributed in downtown Shanghai. Polarization of the GSS distribution area and the high heat of points of interest can be seen. When the service radius of the GSS in Shanghai is 500, 750, and 1,000 m, the green space ecological service area can reach 2089.08, 3164.62, and 4469.75 km2, covering 26.17, 39.64, and 55.99% of the total area, respectively. The coverage for walking accessibility of GSSs in Shanghai is extremely uneven. Based on network analysis, the overall accessibility of GSS under the walking mode in each residential district fails to meet the standard of a 15-min living circle, with an average of 15.37 min. The evaluation results of this plan demonstrate that Shanghai needs to further provide GSS space for the public in future to improve public wellbeing and diversify sports spaces.

This study aims to explore the entrepreneurial psychology of physical Education (PE) students under the “Internet+”environment, to cultivate and improve the entrepreneurial consciousness of PE students, taking the realization of students’ sense of self-efficacy as an intermediary factor. The new educational technology in modern PE is analyzed first. Specifically, the motion sensing technology based on human-computer natural interaction can be used for training, so that learners can effectively improve their physical skills. Subsequently, the current entrepreneurial situation of PE majors is discussed, with 188 students from Tianjin University of Sport and Guangzhou Sport University selected as research subjects. It is found that 62.2% of students have never been exposed to online entrepreneurship, and they are more afraid of entrepreneurial risks. In terms of entrepreneurial motivation, most students choose to start a business because of “personal ideals,” and only 40 people choose to start a business because of economic factors. There is a significant positive correlation between entrepreneurial self-efficacy and entrepreneurial intention of college students majoring in PE, and the correlation coefficient is 0.488. At present, the teaching mode of sports universities focuses on the teaching of professional courses. However, students generally believe that the professional knowledge learned is not useful for future entrepreneurship. The entrepreneurial self-efficacy of college students tends to be positive, and there are notable differences in the entrepreneurial self-efficacy between boys and girls. The regression analysis of entrepreneurial self-efficacy and entrepreneurial intention of college students shows that entrepreneurial self-efficacy can effectively predict entrepreneurial intention. This research promotes the innovation and development of the sports industry under the background of “Internet+”.

The purpose of the study is to improve the performance of intelligent football training. Based on deep learning (DL), the training of football players and detection of football robots are analyzed. First, the research status of the training of football players and football robots is introduced, and the basic structure of the neuron model and convolutional neural network (CNN) and the mainstream framework of DL are mainly expounded. Second, combined with the spatial stream network, a CNN-based action recognition system is constructed in the context of artificial intelligence (AI). Finally, by the football robot, a field line detection model based on a fully convolutional network (FCN) is proposed, and the effective applicability of the system is evaluated. The results demonstrate that the recognition effect of the dual-stream network is the best, reaching 92.8%. The recognition rate of the timestream network is lower than that of the dual-stream network, and the maximum recognition rate is 88%. The spatial stream network has the lowest recognition rate of 86.5%. The processing power of the four different algorithms on the dataset is stronger than that of the ordinary video set. The recognition rate of the time-segmented dual-stream fusion network is the highest, which is second only to the designed network. The recognition rate of the basic dual-stream network is 88.6%, and the recognition rate of the 3D CNN is the lowest, which is 86.2%. Under the intelligent training system, the recognition accuracy rates of jumping, kicking, grabbing, and starting actions range to 97.6, 94.5, 92.5, and 89.8% respectively, which are slightly lower than other actions. The recognition accuracy rate of passing action is 91.3%, and the maximum upgrade rate of intelligent training is 25.7%. The pixel accuracy of the improved field line detection of the model and the mean intersection over union (MIoU) are both improved by 5%. Intelligent training systems and the field line detection of football robots are more feasible. The research provides a reference for the development of AI in the field of sports training.