The invention discloses an identity recognition method based on an electroencephalogram signal channel attention convolutional neural network. The method comprises the following steps that S1, EEG signals of different channels are selected from an emotion electroencephalogram database to serve as original signals; S2, a band-pass filter is used for removing electro-oculogram artifact signals and power frequency interference signals in the original signals to obtain pure emotion electroencephalogram signals; and S3, the preprocessed emotion electroencephalogram signals are input into a deep learning identity recognition model, and a deep learning algorithm is used for carrying out identity recognition on the emotion electroencephalogram signals. According to the method, the emotion EEG signals are selected for identity recognition, the emotion EEG is easy to obtain, and the identity recognition method has higher universality and generalization. According to the method, the number of neurons connected between the front layer and the rear layer is reduced, the gradient disappearance problem is solved, feature propagation is enhanced, network parameters are reduced, EEG signal features in different emotion states are more effectively utilized, and therefore identity recognition of the emotion electroencephalogram signals is effectively carried out.