公开(公告)号：US12182829B2

公开(公告)日：2024-12-31

申请号：US17849320

申请日：2022-06-24

Applicant: Adobe Inc.

Inventor： Sarthak Chakraborty ,  Sunav Choudhary ,  Atanu R. Sinha ,  Sapthotharan Krishnan Nair ,  Manoj Ghuhan Arivazhagan ,  Yuvraj ,  Atharva Anand Joshi ,  Atharv Tyagi ,  Shivi Gupta

IPC: G06Q30/0201 ,  G06N3/04 ,  G06Q30/0251

Abstract: A system includes a representation generator subsystem configured to execute a user representation model and a task prediction model to generate a user representation for a user. The user representation model receives user event sequence data comprises a sequence of user interactions with the system. The task prediction model is configured to train the user representation model. The user representation includes a vector of a predetermined size that represents the user event sequence data and is generated by applying the trained user representation model to the user event sequence data. A storage requirement of the user representation is less than a storage space requirement of the user event sequence data. The system includes a data store configured for storing the user representation in a user profile associated with the user.

公开(公告)号：US20240292046A1

公开(公告)日：2024-08-29

申请号：US18176114

申请日：2023-02-28

Applicant: ADOBE INC.

Inventor： Sunav Choudhary ,  Atanu R. Sinha ,  Sarthak Chakraborty ,  Sai Shashank Kalakonda ,  Liza Dahiya ,  Purnima Grover ,  Kartavya Jain

IPC: H04N21/262 ,  H04N21/2187 ,  H04N21/233 ,  H04N21/234 ,  H04N21/25 ,  H04N21/442 ,  H04N21/4788 ,  H04N21/81

CPC classification number: H04N21/262 ,  H04N21/2187 ,  H04N21/233 ,  H04N21/23418 ,  H04N21/251 ,  H04N21/44218 ,  H04N21/4788 ,  H04N21/812

Abstract: Systems and methods for identifying key moments, such as key moments within a livestream, are described. Embodiments of the present disclosure obtain video data and text data. In some cases, the text data is aligned with a timeline of the video data. The system then computes a moment importance score for a time of the video data using a machine learning model based on the video data and the text data, and presents content to a user at the time of the video data based on the moment importance score.

公开(公告)号：US20230419339A1

公开(公告)日：2023-12-28

申请号：US17849320

申请日：2022-06-24

Applicant: Adobe Inc.

Inventor： Sarthak Chakraborty ,  Sunav Choudhary ,  Atanu R. Sinha ,  Sapthotharan Krishnan Nair ,  Manoj Ghuhan Arivazhagan ,  Yuvraj ,  Atharva Anand Joshi ,  Atharv Tyagi ,  Shivi Gupta

IPC: G06Q30/02 ,  G06N3/04

CPC classification number: G06Q30/0201 ,  G06N3/04 ,  G06Q30/0269 ,  G06Q30/0255

Abstract: A system includes a representation generator subsystem configured to execute a user representation model and a task prediction model to generate a user representation for a user. The user representation model receives user event sequence data comprises a sequence of user interactions with the system. The task prediction model is configured to train the user representation model. The user representation includes a vector of a predetermined size that represents the user event sequence data and is generated by applying the trained user representation model to the user event sequence data. A storage requirement of the user representation is less than a storage space requirement of the user event sequence data. The system includes a data store configured for storing the user representation in a user profile associated with the user.