Encrypted traffic classification method based on network traffic context representation, electronic equipment and storage medium

The invention provides an encrypted traffic classification method based on network traffic context representation, electronic equipment and a storage medium, and belongs to the technical field of encrypted traffic classification. Comprising the following steps: S1, dividing traffic to be classified according to quintuples; s2, constructing a traffic representation sliding window, and dividing traffic into a plurality of traffic data packet fragments; s3, extracting a time feature and a space feature of each traffic segment; s4, generating a context spatio-temporal feature matrix according to the time features and the spatial features of the traffic segments; s5, converting the context space-time matrix into a gray scale picture; s6, constructing a model classifier; and S7, inputting the grayscale image into the model classifier, and outputting a classification result. The problems of low classification accuracy, low timeliness and low efficiency in the prior art are solved. According to the method, the traffi