This disclosure relates to an emotion recognition and neural modulationsystem and method based on bilateral amygdala phase difference, comprising: a physiological signal acquisition device for acquiring a user's physiological signals; a facial expression acquisition device for acquiring the user's facial expressions and eye movement information; an electroencephalogram (EEG) device for acquiring the user's electroencephalogram (EEG) signals; a magnetic resonance imaging (MRI) device for acquiring the user's brain activity map; and a data processing module for preprocessing the physiological signals, facial expressions, and eye movement information before inputting them into an emotion recognition model to obtain an emotion category, determining neural activity patterns based on the EEG signals and brain activity map using a neural network model, and adjusting the operating parameters of the emotion recognition model, the EEG device, and the MRI device based on the comparison results of the neural activity patterns and the emotion category. Using the above technical solution, high-precision monitoring and regulation of emotional states and neural activity are achieved.