Training method and device of transformation prediction model, equipment, storage medium and computer program product

Abstract

This application provides a training method, apparatus, device, storage medium, and computer program product for a conversion prediction model, applicable to various conversion prediction scenarios such as cloud technology, artificial intelligence, smart transportation, and vehicle-mounted systems. The method includes: acquiring recommended information samples with a conversion waiting time of a first duration up to the current training time and conversion tags for the recommended information samples; extracting first sample features of the recommended information samples based on the conversion prediction model to be trained, and extracting second sample features of the recommended information samples based on a second feature extraction module in an auxiliary training model, wherein the auxiliary training model is trained with a second duration shorter than the first duration; predicting a first predicted conversion probability corresponding to the sample fusion feature of the first and second sample features based on the conversion prediction model to be trained; and training the conversion prediction model to be trained based on the difference between the first predicted conversion probability and the conversion tag, thereby obtaining the conversion prediction model. This application can improve the accuracy of the model.

Images