Product purchase probability determination method and product purchase probability determination device

The invention provides a product purchase probability determination method and device, and the method comprises the steps: obtaining target historical sales data and a target generation network, inputting the target historical sales data into the target generation network for processing, and obtaining target sample data; a probability prediction model is obtained, the probability prediction model is trained through machine learning by using multiple groups of historical data, and each group of data in the multiple groups of historical data comprises target sample data and a purchase probability corresponding to the target sample data; and obtaining to-be-predicted user data, and inputting the to-be-predicted user data into the probability prediction model to obtain a purchase probability corresponding to the to-be-predicted user data, the to-be-predicted user data being sales data of to-be-predicted users who do not purchase products at the current moment, and the purchase probability being a probability that