WO2024246642 - TRACKING CONTENT WITH ARTIFICAL INTELLIGENCE AS IT IS CONSUMED
National phase entry is expected:
Publication Number
WO/2024/246642
Publication Date
05.12.2024
International Application No.
PCT/IB2024/054533
International Filing Date
09.05.2024
Title **
[English]
TRACKING CONTENT WITH ARTIFICAL INTELLIGENCE AS IT IS CONSUMED
[French]
SUIVI DE CONTENU AVEC INTELLIGENCE ARTIFICIELLE AU FUR ET À MESURE DE SA CONSOMMATION
Applicants **
SONY GROUP CORPORATION
1-7-1 Konan
Minato-ku
Tokyo 108-0075, JP
Inventors
CANDELORE, Brant
16535 Via Esprillo
San Diego, California 92127, US
Priority Data
18/328,533
02.06.2023
US
Application details
| Total Number of Claims/PCT | * |
| Number of Independent Claims | * |
| Number of Priorities | * |
| Number of Multi-Dependent Claims | * |
| Number of Drawings | * |
| Pages for Publication | * |
| Number of Pages with Drawings | * |
| Pages of Specification | * |
| * | |
| * | |
International Searching Authority |
EPO
* |
| Applicant's Legal Status |
Legal Entity
* |
| * | |
| * | |
| * | |
| * | |
| Entry into National Phase under |
Chapter I
* |
| Translation |
|
Recalculate
* The data is based on automatic recognition. Please verify and amend if necessary.
** IP-Coster compiles data from publicly available sources. If this data includes your personal information, you can contact us to request its removal.
Quotation for National Phase entry
| Country | Stages | Total | |
|---|---|---|---|
| China | Filing | 1243 | |
| EPO | Filing, Examination | 6281 | |
| Japan | Filing | 594 | |
| South Korea | Filing | 575 | |
| USA | Filing, Examination | 2710 |
Total: 11403 USD
The term for entry into the National Phase has expired. This quotation is for informational purposes only
Abstract[English]
A user starts playback of an audio or AV program, which starts up a large language model (LLM) (210, 220, 304, 404, 500) such as a generative pre-trained transformer. The LLM follows the program with the user as the program is being watched. Audio is converted to text and video is converted to text-based description. The LLM essentially trains on the resulting "corpus" so that should the user subsequently want to access part of the program using a simple conversational query about the program, the LLM can provide the answer.[French]
L'invention se rapporte à un utilisateur qui démarre la lecture d'un programme audio ou audiovisuel, qui démarre un grand modèle de langage (LLM) (210, 220, 304, 404, 500) tel qu'un transformateur pré-entraîné génératif. Le LLM suit le programme avec l'utilisateur lorsque le programme est regardé. Un audio est converti en texte et une vidéo est convertie en une description à base de texte. Le LLM s'entraîne essentiellement le « corpus » résultant, de sorte que si l'utilisateur souhaite ultérieurement accéder à une partie du programme au moyen d'une simple interrogation conversationnelle concernant le programme, le LLM puisse fournir la réponse.