Method for improving interpretability of depth model recommendation scheme

The invention provides a method for improving interpretability of a depth model recommendation scheme. The method comprises the following steps: preprocessing user return visit data; training an abstract classifier; performing feature extraction on the return visit data; generating a digest using a digest generator and calculating a digest generation loss; calculating digest classification loss based on the digest classifier; calculating return visit text classification loss; performing model parameter training updating with the goal of minimizing the sum of abstract generation loss, abstract classification loss and return visit text classification loss; and training and updating based on the model parameters to obtain a business recommendation model. In addition, the invention further provides a method for generating the business recommendation scheme and the user return visit abstract based on the user return visit text, and the generated user return visit abstract can be corrected by using a sequence copyi