CNN-LSTM-based air formation target intention recognition method and system

The invention provides an air formation target intention recognition method and system based on CNN-LSTM, and belongs to the field of air target recognition, and the method comprises the steps: carrying out the preprocessing of air target attribute data, and carrying out the encoding of an intention space intention; distributing all single-target attribute data to a one-dimensional convolutional layer for deep feature extraction; after the deep features are input into the LSTM network to learn dependency on time, a first Dense layer is adopted to acquire a primitive intention; reorganizing the primitive intention according to the encoded intention space, the formation pattern and the formation composition, and learning the features of the reorganized primitive intention through a second Dense layer; and taking the third Dense layer as an output layer, and receiving the overall intention of the feature recognition formation target output by the second Dense layer. The air formation target intention recognition