Multi-traffic-participant interaction behavior recognition method, system and device, and medium

The invention relates to a multi-traffic-participant interaction behavior recognition method, system and device, and a medium, and belongs to the field of traffic participant behavior recognition. The method comprises the following steps: obtaining a data set; dividing the data set to obtain a training set and a verification set; establishing a graph neural network model, wherein the graph neural network model comprises an instance layer and a category layer; preprocessing the training set and the verification set to obtain a preprocessed training set and a preprocessed verification set; inputting the preprocessed training set into the graph neural network model for training to obtain a trained graph neural network model; finally, inputting the preprocessed verification set into the trained graph neural network model to obtain a recognition result of interaction behaviors of multiple traffic participants. By comprehensively considering interaction behaviors among all traffic participants, the recognition prec