Fine motion motor imagery electroencephalogram signal classification method and device

The invention relates to the technical field of motor intention, and discloses a fine motion motor imagery electroencephalogram signal classification method and device.The method comprises the steps that electroencephalogram signals of a subject during motor imagery are obtained and preprocessed, and preprocessed electroencephalogram signals are obtained; the preprocessed electroencephalogram signals are subjected to two-dimensional linear conversion and three-dimensional space conversion, electroencephalogram data to be input are obtained, and the electroencephalogram data to be input comprise linear data and spatial data; inputting the to-be-input electroencephalogram data into a pre-established parallel multi-scale hybrid convolutional neural network model to extract time features and global spatial features according to the linear data, and extracting spatial-temporal features and local spatial features according to the spatial data, and the motor imagery category of the electroencephalogram signal is det