Internet of Things signal anomaly detection method and system based on graph neural network

The invention discloses an Internet of Things signal anomaly detection method and system based on a graph neural network, and belongs to the field of anomaly detection of Internet of Things signals. According to the method, a static graph structure at the bottommost layer of a smoothness constraint learning system and a dynamic graph structure according with time-varying characteristics of a time sequence are embedded and learned based on sensor characteristics, and spatial-temporal characteristics of the multivariate time sequence are captured by adopting a GAGRU module which integrates a graph attention mechanism into a gating circulation unit. Meanwhile, a system anomaly score is calculated according to a sequence prediction error, anomaly detection is carried out by adopting a traditional anomaly identification method based on a TopK criterion and a point adjustment anomaly identification method based on a POT algorithm, and finally, the performance of the model is jointly verified by adopting a tradition