Systems and methods to predict viewership for media content
US12149791B1 · kind B1 · utility
0Cited by
1References
17Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Sep 15, 2023 |
| Grant date | Nov 19, 2024 |
| Priority date | — |
| Expiry date | Sep 15, 2043 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04N21/4532
- WIPO fieldAudio-visual technology
- WIPO sectorElectrical engineering
Abstract
Systems, methods, and articles for using an ensemble model to predict a number of impressions that media content programs will receive at a future time. The ensemble model is comprised of a plurality of machine learning models trained based on static and dynamic features obtained from historical impression data and media content program attributes. Static and dynamic features extracted from attributes of a media content program are applied to the ensemble model to generate a prediction of the number of impressions that the media content program will receive at a future time.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.