Method and device for training model and method and device for generating information

Abstract

The invention discloses a method and a device for training a model, and a method and a device for generating information. The implementation scheme of the method for training the model comprises the steps of acquiring a training sample set, and a machine learning algorithm being utilized to take behavior feature information, other feature information and object feature information included in training samples in the training sample set as input data; taking a user behavior vector corresponding to the input behavior characteristic information, an object vector corresponding to the input objectcharacteristic information, and preference values between the user corresponding to the other input area characteristic information, the user behavior vector and the object vector and each to-be-predicted object as expected output data; and training to obtain a vector and a user preference generation model. According to the scheme, the user behavior embedding, the to-be-predicted object embeddingand the user portrait preference estimation are carried out at the same time by using one model, so that the prediction of the user preference information has higher accuracy and wider coverage.

Description

technical field [0001] The present application relates to the field of computer technology, specifically to the field of big data technology, and especially to methods and devices for training models, and methods and devices for generating information. Background technique [0002] User portrait is one or more user labels and preference models abstracted based on information such as user identity and behavior. In many fields such as e-commerce, user portraits, as a basic feature of artificial intelligence algorithms, are widely used in various scenarios such as search, recommendation, and advertisement. However, in the face of billions of users, with limited information, how to make the data produced by user portraits more accurate, and how to predict the preferences of users with only a small amount of behavior data, is currently a difficult point in the industry. [0003] At present, the commonly used method is to analyze and predict the preference of the user’s recent be...

AI Technical Summary

Problems solved by technology

Another method is to try to use the embedding vector. Although this method can further accurately characterize the user behavior or the characteristics of the predicted object, the embedding vector comes from another system that specializes in embedding output. These embeddings Output systems often require separate data and methods for model training

Images