Since the 1980s, machine learning has attracted extensive attention in the field of artificial intelligence. Following the expert system, it opened a precedent for the application of machine learning in the field of artificial intelligence and became one of the important topics of artificial intelligence. However, in the field of volleyball, the application of machine learning and information technology in volleyball is extremely limited. Volleyball has not developed widely in society nor has it become a common event in people’s daily life. Therefore, the development of volleyball in China lags behind. Unlike other sports, volleyball requires both strong skills and playing tactics. While taking into account the technical and tactical aspects, the requirements for the comprehensive quality and learning ability of both sides of the teaching are relatively strict. If the application of modern information technology is neglected, it may affect the teaching effect of volleyball and hinder the long-term spread of volleyball. The article starts with the serving, landing, and blocking of two groups of volleyball players with different sports levels. Through the application of machine learning and digital information technology in volleyball, as well as the use of artificial neural networks and genetic algorithms, the reaction time and accuracy of judging serving, landing, and blocking are improved, and specific application strategies are further proposed. According to the influence of athletes of different levels on the cognition of volleyball landing points, it can be seen that there are three parts that account for 40% of the allocation.

Medical experts and academics are progressively becoming aware of knee injuries faced by tai chi practitioners in China. This occurs when the knee is bent with weight on the foot turned during Tai Chi. We propose an enhanced convolutional neural network (CNN) technique for early warning of joint injury risk during Tai Chi exercise in this research. This improved neural network approach can detect the risk of knee joint injury in practitioners early on to aid in early precaution and treatment. A multiscale feature extraction module is developed by performing several scales of convolutional layer extraction on the input data features and then combining the results to maximize the amount of feature information included in the extracted joint data. The results revealed that in experiments on a Taiwanese Tai Chi community dataset, the proposed method had an average diagnostic accuracy greater than 90 percent, significantly higher than the average diagnostic accuracy of the comparison methods on the dataset.