Dynamic electrocardiogram(ECG) is one of the most commonly used tests in the clinical diagnosis of silent myocardial ischemia, but manual analysis has a heavy workload, limited efficiency and accuracy. Based on deep learning technology, the paper proposes an algorithm to assist doctors in intelligent analysis of silent myocardial ischemia dynamic ECG, which greatly improves the accuracy of dynamic ECG analysis and reduces the misdiagnosis rate of ECG interpretation.