Abstract: A method for constructing a large prediction model of coal burst based on multimodal data is provided. The method includes: constructing a multimodal data set by collecting data from different modalities; preprocessing the multimodal data set to construct precursor pattern sequences; and converting, according to features of different mining areas, each precursor pattern sequence into a corresponding grade form to assign a corresponding risk grade label of coal burst; processing graded precursor pattern sequences by using Transformer to predict an occurrence probability of risk grade of coal burst; evaluating, by using a comprehensive index method, risk degrees of mining information data and geological structure data, and evaluating an overall risk grade of coal burst comprehensively by combining the prediction result output by the coal burst prediction module.