Based on the network traffic identification method of random sampling multi-classifiers, a network flow data set A with network traffic classification labels and a network flow record set N without network traffic classification labels are given, and network flow records are selected from network flow data set A, Random sampling generates a subset of data B 1 , B 2 ,...,B T , using the decision tree classification algorithm to randomly extract the data subset B 1 , B 2 ,...,B T Carry out learning separately, and record the learning results as T classifiers F 1 , F 2 ,...,F T , randomly extract t classifiers from T classifiers, and use the extracted t classifiers to classify each network flow record in the network flow record set N respectively, and obtain t classification results, and the classification results are counted The classification type with the largest number is used as the classification type of network flow records without network traffic classification labels.