Aviation Medical Simulation Training Based on Interactive Technology

China is one of the countries with the most serious natural disasters in the world. It is urgent to strengthen the construction of emergency medical rescue capacity. In recent years, more and more people realize the necessity of interaction in aviation medical rescue simulation training for major disasters. China's professional aviation medical rescue training is relatively late, and the training equipment and system are relatively backward, mainly using medical simulator training. This paper proposes a gesture recognition algorithm which combines aviation medical simulation training with virtual environment. Based on the existing joint point extraction technology, 22 joint points of the hand are obtained. Combined with the key operations of aviation emergency medical rescue, neural network is used for learning and action recognition, so as to realize natural interaction.