USER PROFILE-BASED OBJECT RECOMMENDATION METHOD AND DEVICE
The present disclosure, which provides a method and device for recommending objects based on a user profile, relates to the field of computer technology. A specific embodiment of the method comprises: receiving user behavior data and user attribute information, and converting, by means of feature en...
Saved in:
Main Author | |
---|---|
Format | Patent |
Language | English French German |
Published |
13.09.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The present disclosure, which provides a method and device for recommending objects based on a user profile, relates to the field of computer technology. A specific embodiment of the method comprises: receiving user behavior data and user attribute information, and converting, by means of feature engineering, them into user behavior data to be processed and user attribute information to be processed; acquiring a current tag calculation task, determining whether or not the tag calculation task is a prediction type task, if the tag calculation task is a prediction type task, invoking a preset prediction model, and, if the tag calculation task is not a prediction type task, invoking a preset statistical rule model; and obtaining, according to the prediction model or the statistical rule model, a user profile based on the user behavior data to be processed and the user attribute information to be processed, and then pushing object information to the user according to the user profile. Therefore, the embodiments of the present disclosure can solve the problem of a low marketing campaign efficiency caused by the existing low-accuracy user profiles. |
---|---|
Bibliography: | Application Number: EP20210891044 |