Football is regarded as the world’s number one sport and is loved by all countries, and large-scale football matches are held basically every year. The key to football matches is to shoot goals, and how to improve the accuracy of football shooting requires the identification and analysis of football shooting actions. Deep learning enables machines to imitate human activities such as seeing, hearing, and thinking. It solves many complex pattern recognition problems. Especially, the deep learning algorithm is unique in the recognition of pictures with high accuracy, and it provides technical support for the recognition and analysis of football shooting actions. What this paper will discuss is the recognition method of football shooting action based on a deep learning algorithm. Experiments show that the football shooting action recognition method developed in this paper has a great effect on promoting the accuracy of football shooting, which can make the accuracy rate reach about 96%. The research in this paper has great reference value and practical significance for the team’s ability to shoot and grasp the opportunity to score.

Football is a popular sport in the world. Playing football can not only exercise the body and improve physical fitness but also learn some offensive and defensive skills. Football games are popular events all over the world. With the development of science and technology, virtual football games have also become popular. The virtual football game is an entertainment project that combines computer technology and virtual reality technology to analyze the attack and defense relationship in the virtual football game. It can understand the decision-making mechanism and apply the decision-making mechanism to the Internet of Things decision-making system, which will be able to make accurate and fast decisions like virtual players. This is also the content of this paper. This paper proposes a decision system based on virtual football, applies the system to the Internet of Things, and shows that the data of the system fluctuate within 1.5%, that is, the calculation accuracy of the system model is as high as 98.5%, with high calculation stability, high accuracy, and certain reliability.