Method and device for explaining business processing result of business processing model

The embodiment of the invention provides a method and device for explaining a business processing result of a business processing model, and the method comprises the steps: inputting a to-be-explained sample into a pre-trained generation model, obtaining a first number of disturbance samples, and enabling the to-be-explained sample and the disturbance samples to comprise a plurality of feature dimensions; respectively inputting the to-be-explained sample and the first number of disturbance samples into a business processing model realized through a neural network, and outputting a first business processing result corresponding to the to-be-explained sample and a second business processing result corresponding to each disturbance sample; screening out a second number of disturbance samples from the first number of disturbance samples by taking consistency of the second business processing result and the first business processing result as a screening condition; and counting the difference between the second nu