User loss prediction method based on Internet television using behaviors and terminal
The invention discloses a user loss prediction method based on Internet television using behaviors and a terminal, and the method comprises the steps: obtaining the basic attribute features of a userand the startup information in a preset period, and constructing a user matrix; obtaining program inf...
Saved in:
Main Author | |
---|---|
Format | Patent |
Language | Chinese English |
Published |
05.03.2021
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention discloses a user loss prediction method based on Internet television using behaviors and a terminal, and the method comprises the steps: obtaining the basic attribute features of a userand the startup information in a preset period, and constructing a user matrix; obtaining program information data, performing word segmentation vectorization processing on a program introduction, constructing a program matrix, and performing dimension reduction processing on the program matrix to obtain a program introduction matrix; acquiring viewing behavior data of the user, and constructing aprogram preference matrix; and combining the user matrix, the program introduction matrix and the program preference matrix into a calculation matrix, and inputting the calculation matrix into a prediction model to predict a user loss probability. According to the invention, the feature number is increased by collecting the program information in different time periods in the preset period, richuser behavior feature data |
---|---|
Bibliography: | Application Number: CN202011247722 |