Cross-subject emotion recognition method, electronic equipment and storage medium

The invention discloses a cross-subject emotion recognition method, electronic equipment and a storage medium, the cross-subject emotion recognition method comprises the following steps: training an electroencephalogram converter by using label-free data in one-to-one correspondence of a source domain and a target domain; migrating labeled data of a source domain to a target domain by using the electroencephalogram converter; training an emotion classifier by using the migrated data of the source domain; and performing emotion recognition on the labeled data of the target domain by using the trained emotion classifier. According to the method provided by the embodiment of the invention, the characteristics of the time alignment data are fully utilized, the performance in an experiment is superior to that of other domain adaptation algorithms, and a new thought is provided for cross-subject emotion recognition. Furthermore, according to the embodiment of the invention, the DE features of different subjects are