Application clustering method and device, storage medium and computer equipment

The invention discloses a training method of an application clustering model. The method utilizes an artificial intelligence technology to obtain a training sample pair; performing image coding on the training sample pair through an image coding network to obtain a first feature matrix and a second feature matrix; performing comparison feature extraction based on the first feature matrix and the second feature matrix to obtain a third feature matrix and a fourth feature matrix, and performing clustering feature extraction based on the first feature matrix and the second feature matrix to obtain a fifth feature matrix and a sixth feature matrix; and performing iterative updating on the network parameters based on the first loss determined by the third feature matrix and the fourth feature matrix and the second loss determined by the fifth feature matrix and the sixth feature matrix until a training ending condition is met. The feature representation corresponding to each application can be accurately learned t