Intrusion detection method and system

The invention discloses an intrusion detection method and system, and the method comprises the steps: carrying out the construction of an edge intrusion detection model for the equipment feature data of an edge side through an edge node, and training the global model parameters of a cloud node through the model input and model output of the edge intrusion detection model of all edge nodes through the cloud node, the global model is a model based on Bayesian deep learning; and meanwhile, the cloud node adaptively adjusts the sampling data volume input by the global model based on the error precision predicted by the global model, so that the pressure of communication transmission of the cloud node can be reduced, and the service response capability of the cloud node is improved. Meanwhile, the intrusion detection model is updated every other detection period, and the parameter update of the global model changes along with the change of the data distribution of the edge nodes, so that the accuracy of intrusion