Abstract: Under the current background of intelligent transformation of mines，the application of in‐ telligent dispatching systems may cause excessive psychological burden on mine truck drivers，thereby af‐ fecting their operating conditions and increasing the risk of accidents. To address this issue，the research first conducted a detailed analysis of the operation process of mine truck drivers，identifying key task links and potential stressors. Subsequently，the formation mechanism of psychological load was discussed，com‐ prehensively considering multiple influencing factors such as task complexity，time urgency and working environment. To verify the analysis results，a simulated driving test is designed. The electroencephalogram (EEG) data of drivers are collected in the simulated mine environment to objectively measure cognitive load. Meanwhile，the NASA-TLX task scale is used to evaluate their subjective workload，and the random forest algorithm was utilized to construct a psychological load prediction model. The research results show that this model can identify the electroencephalogram (EEG) characteristics under various levels of psycho‐ logical load with an accuracy rate of 85%，providing a reliable basis for real-time monitoring. Finally，a dynamic perception and intelligent dispatching system for psychological load is proposed. It uses wearable sensors and machine learning algorithms to continuously track the psychological state of drivers. When it detects that the load exceeds the standard，it intervenes by adjusting task allocation or arranging rest，ef‐ fectively reducing psychological load，preventing operational errors and accidents，and ensuring the safe production and efficient operation of smart mines.

Key words: intelligent scheduling, mine truck driver, psychological load, real-time monitoring