Material property prediction method, system and equipment based on graph neural network

The invention discloses a material property prediction method, system and equipment based on a graph neural network, and belongs to the field of material prediction and analysis. The method comprises the following steps: obtaining a crystal structure of a material; performing coding initialization and standardization processing on the crystal structure to obtain a graph network of corresponding atoms; constructing a structural feature prediction model, determining network hyper-parameter information of the structural feature prediction model, and setting a network evaluation algorithm, an activation function and an optimizer of the structural feature prediction model; on the basis of network hyper-parameter information, a network evaluation algorithm, an activation function and an optimizer, training and optimizing the structural feature prediction model; and inputting to-be-predicted material data into the trained and optimized structural feature prediction model, and outputting a material property predictio