The invention discloses multidata integration circular RNA and a disease correlation prediction method based on double random walk restart. By transforming a circular RNA-disease relationship networkinto an undirected graph, calculating the semantic similarity of circular RNA function annotations, structural similarity and functional similarity, and calculating the disease function and semantic similarity, multiple circular RNA similarity networks and disease similarity networks are integrated into a comprehensive circular RNA similarity network and disease similarity network, a random walk restart algorithm is applied to the integrated circular RNA similarity network and the disease similarity network separately, the cold restart problem is avoided, and a potential circular RNA-disease relationship is predicted. Accordingly, the potential circular RNA-disease relationship can be accurately predicted; simulation experiment results indicate that the precision, recall rate, accuracy, f1-measure and other indexes are better; compared with other relationship prediction methods, the prediction accuracy of the RNA-disease relationship is improved.