In order to solve the problem that it is difficult to find evidence from a large number of legal document statements and the irrelevant statements in a large number of document sample data will cause a great interference to the prediction results and further improve the accuracy of evidence prediction, this paper puts forward an intelligent evidence criterion prediction method for legal documents based on the comprehensive consideration of legal problems, the nature of statements, and the characteristics of answers. The binary cross-entropy of different statements is used to obtain the interaction information between different statements. Through experiments, it is found that the score of Joint F1 proposed in this paper is 70.07%, which is more accurate than the mainstream model and also verifies the effectiveness of the scheme.