Encrypted traffic classification method and device based on graph convolutional neural network

The embodiment of the invention provides an encrypted traffic classification method and device based on a graph convolutional neural network, and the method comprises the steps: splitting encrypted traffic data of a to-be-classified application into a plurality of streams, and obtaining the statistical information of each stream; wherein the statistical information is used for indicating the transmission condition of the stream; converting the acquired statistical information into graph embedding as embedding of a stream; utilizing a heterogeneous graph convolutional neural network to obtain embedding of a communication graph corresponding to the to-be-classified application; utilizing a homogeneous graph convolutional neural network to obtain embedding of a flow graph corresponding to theto-be-classified application; and based on the embedding of the flow, the embedding of the communication graph and the embedding of the flow graph, obtaining a classification result of the to-be-classified application by uti