Human brain activity decoding method and system based on neural network

The invention belongs to the field of brain brain-computer interfaces, and particularly relates to a human brain activity decoding method and system based on a neural network. The method comprises the following steps: acquiring an image feature vector and inputting the image feature vector into a pre-trained image generator to obtain a stimulation image; collecting an electroencephalogram signal and an electro-oculogram signal generated when the user observes the stimulation image; preprocessing the electroencephalogram signal and the electro-oculogram signal to obtain a preprocessed electroencephalogram signal; performing feature coding on the electroencephalogram signals by adopting a pre-trained electroencephalogram signal coding network to obtain primary electroencephalogram features; obtaining an electroencephalogram signal classification result according to the primary electroencephalogram characteristics; processing the primary electroencephalogram features by adopting a pre-trained mapping network to