WO2024218578 - REALTIME CONTENT METADATA CREATION USING AI

National phase entry:
Publication Number WO/2024/218578
Publication Date 24.10.2024
International Application No. PCT/IB2024/051102
International Filing Date 06.02.2024
Title **
[English] REALTIME CONTENT METADATA CREATION USING AI
[French] CRÉATION DE MÉTADONNÉES DE CONTENU EN TEMPS RÉEL À L'AIDE D'IA
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
18/304,240   20.04.2023   US
front page image
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
*
Applicant's Legal Status
*
*
*
*
*
Entry into National Phase under
*
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 StagesTotal
China Filing1283
EPO Filing, Examination6261
Japan Filing587
South Korea Filing574
USA Filing, Examination2710
MasterCard Visa

Total: 11415

The term for entry into the National Phase has expired. This quotation is for informational purposes only

Abstract[English] A user query for information related to an audio video (AV) program is received (302) and processed (304) by a machine learning (ML) model such as an artificial intelligence (Al) chatbot. The chatbot returns (306) a response to the query in conversational form. To ensure the chatbot does not spoil the ending for a user in the middle of the AV program, the chatbot is fed only portions of corresponding text up to the time the user is in viewing.[French] Une interrogation d'utilisateur pour des informations relatives à un programme audio et vidéo (AV) est reçue (302) et traitée (304) par un modèle d'apprentissage automatique (ML) tel qu'un robot conversationnel d'intelligence artificielle (Al). Le robot conversationnel renvoie (306) une réponse à l'interrogation sous forme conversationnelle. Pour garantir que le robot conversationnel ne divulgâche pas la fin pour un utilisateur au milieu du programme AV, le robot conversationnel n'est alimenté que des parties du texte correspondant jusqu'au moment que l'utilisateur est en train de regarder.
An unhandled error has occurred. Reload 🗙