Network traffic detection method and system based on meta-learning framework and oriented to Internet of Things security

The invention relates to a network intrusion detection method and system for Internet of Things security based on a meta-learning framework, and the method comprises the steps: 1) carrying out the standardization processing of the attributes of network traffic, and dividing data according to the meta-learning framework; 2) using two weight-shared convolutional neural networks as a feature extraction module to perform feature extraction on the network traffic data; 3) comparing the sample pairs by using Euclidean distance, and extracting feature distance information of the two samples; 4) in a model training stage, combining a coding loss function and a comparison loss function to optimize model training; 5) classifying the samples by using distance measurement; and 6) simulating the small sample condition of the network flow by using the reference data set to evaluate the performance of the model. The invention provides an Internet of Things security-oriented traffic detection method based on a meta-learning