Signal modulation category identification method based on space-time convolutional network

The invention relates to a communication signal modulation recognition technology, in particular to a signal modulation category recognition method based on a space-time convolutional network, which comprises the following steps: constructing and training a space-time convolutional network model, acquiring an IQ component of a modulation signal to be recognized, inputting the IQ component into the trained space-time convolutional network model, and outputting a recognition result. The space-time convolutional network model comprises a time domain feature extraction module, a spatial feature extraction module and a classification identification module; according to the method, wireless signal modulation modes can be identified and classified in a self-adaptive and high-accuracy manner, the model complexity is low, and the method is easier to deploy to a mobile platform and an edge node with limited resources. 本发明涉及通信信号调制识别技术，具体涉及一种基于时空卷积网络的信号调制类别识别方法，包括构建并训练时空卷积网络模型，获取待识别调制信号的IQ分量输入训练好的时空卷积网络模型，输出识别结果；所述时空卷积网络