In order to solve the problem of data link signal identification and classification, a data link recognition and classification method based on Support Vector Machine (SVM) decision tree is proposed. By analyzing the characteristics of the data link communication signals commonly used by the US army, the wavelet transform method is used to analyze the characteristic information of the data link, and the relationship between wavelet coefficients and signal energy distribution is obtained. According to the principle of SVM algorithm, the target feature model is constructed to identify and classify the signal feature quantities. The key parameters of the SVM classifier are optimized and compared with the BP neural network algorithm. The results show that the SVM decision tree network classifier performs well in convergence speed and accuracy, and can improve classification and recognition performance.