Content recommendation method and device, equipment, storage medium and computer program product

The invention discloses a content recommendation method and device, equipment, a storage medium and a computer program product, and relates to the technical field of Internet. The method comprises the steps that historical accounts and historical recommendation content in a sample data set are acquired to serve as sample data, and interaction data are marked between the historical accounts and the historical recommendation content; inputting the sample data into the probability prediction model, and outputting to obtain a probability prediction result; extracting data features of the sample data through a data classification model; inputting the sample data into the duration prediction model, and outputting to obtain a duration prediction result; probability prediction loss and duration prediction loss are determined based on the interaction data, and prediction loss is obtained through fusion; and training the probability prediction model based on the prediction loss to obtain a target prediction model. In o