Model design method for efficiently identifying and classifying radar targets of moving unmanned aerial vehicle group

The invention discloses a model design method for efficient identification and classification of radar targets of a moving unmanned aerial vehicle group. The method comprises the following steps: constructing a first classification model based on a neural network; the first classification model is used for performing target identification on echo data of a radar target; converting the first classification model into a graph structure code; optimizing the graph structure code by adopting an evolutionary algorithm to obtain an optimized graph structure code; generating a second classification model according to the optimized graph structure code, and performing target identification on echo data of the radar target by using the second classification model; according to the method, the constructed first classification model is converted into the graph structure code, and then the graph structure code is optimized by adopting the neural network architecture search technology based on the evolutionary algorithm, s