Model training method and device, service recommendation method and device, electronic equipment

Abstract

Embodiments of the present disclosure provide a model training method and device, a service recommendation method and device, and electronic equipment. The method includes: acquiring a sample data set; wherein, the sample data set includes the first type of sample data, and the second The second type of sample data; obtaining the first weight corresponding to the first type of sample data, and the second weight corresponding to the second type of sample data; sequentially using the first weight and the second weight to the first weight A loss function corresponding to one type of sample data and a loss function corresponding to the second type of sample data are weighted to obtain an overall loss function; based on the overall loss function, model training is performed using the sample data set. Through the embodiments of the present disclosure, it is possible to use multiple types of sample data for model training, so that when the amount of the first type of sample data is small, the second type of sample data is used as a supplement to the first type of sample data, and the model is improved. The effect of training.

Description

technical field [0001] Embodiments of the present disclosure relate to the technical field of artificial intelligence, and in particular, relate to a model training method and device, a service recommendation method and device, and electronic equipment. Background technique [0002] Machine learning (Machine Learning, ML) is the core of artificial intelligence, and its application pervades all fields of artificial intelligence, and it is the fundamental way to make computers intelligent. [0003] In the existing technology, the training set samples of machine learning usually need to be physically consistent with the prediction set. For example, the training set samples and the prediction set are aimed at the same type of users, so as to ensure that the trained machine learning model can make predictions on the prediction set. precision. [0004] However, in some business scenarios, the number of training set samples that are physically consistent with the prediction set is...

AI Technical Summary

Problems solved by technology

[0004] However, in some business scenarios, the number of training set samples that are physically consistent with the prediction set is small, and it will be difficult to apply the existing machine learning method, which will lead to a decrease in the accuracy of the machine learning model's prediction.

Images