Abstract: High-speed railway dispatcher play an important role in ensuring railway traffic safety. Taking the working state of dispatchers in different emotions as the research content, the study designed an experimental model for collecting physiological data from high-speed railway dispatching operators in different emotional states, performing dispatching tasks and collecting physiological data. The emotion-induced experiment ensures that the dispatchers enter four working states respectively, collects eye movement data and establishes the K-nearest neighbor classification model and the classification and regression tree decision tree classification model for identification, with the former having a higher identification accuracy of more than 90%, and builds the convolutional neural network-gate recurrent unit fusion model to improve the fatigue prediction effect.