公开(公告)号：US12079292B1

公开(公告)日：2024-09-03

申请号：US18486696

申请日：2023-10-13

Applicant: Google LLC

Inventor： Ibrahim Badr ,  Yunsong Guo ,  Imran R. Mansuri

IPC: G06F16/9535 ,  G06F40/20

CPC classification number: G06F16/9535 ,  G06F40/20

Abstract: Systems and methods for proactive query and content suggestion can include obtaining web data, determining a change event occurred, and generating a query and content suggestion. Generating the query and content suggestion can include processing data descriptive of the change event with a generative model to generate one or more model-generated query suggestions. One or more web resources can be obtained then processed to generate a change event summary. The one or more query suggestions and the change event summary can then be provided for display.

公开(公告)号：US20230007980A1

公开(公告)日：2023-01-12

申请号：US17368155

申请日：2021-07-06

Applicant: Google LLC

Inventor： Ibrahim Badr ,  Imran R. Mansuri ,  Sari Onaissi ,  InHan Kang ,  Wenqiong Guo ,  Anner Kushnir

IPC: G06F16/958 ,  G06F16/9535 ,  G06F16/906 ,  G06F16/955 ,  G06F16/901 ,  G06N20/00

Abstract: A computing system and method that can be used to surface a selectable action element for at least one ongoing task. In particular, the present disclosure provides a general pipeline to identify potential tasks that a user has an ongoing interest in or has not yet completed so that a suggestion of a content item can be made to further advance an identified user’s task. This pipeline can incorporate probabilistic transition graphs, machine-learned models, and/or historical data to determine the relevance and completion of tasks that a user may desire to continue acting upon.

公开(公告)号：US20240403185A1

公开(公告)日：2024-12-05

申请号：US18651198

申请日：2024-04-30

Applicant: Google LLC

Inventor： Ibrahim Badr ,  Imran R. Mansuri ,  Sari Onaissi ,  InHan Kang ,  Wenqiong Guo ,  Anner Kushnir

IPC: G06F11/34 ,  G06F16/906 ,  G06F16/9535 ,  G06N20/00

Abstract: A computing system and method that can be used to surface a selectable action element for at least one ongoing task. In particular, the present disclosure provides a general pipeline to identify potential tasks that a user has an ongoing interest in or has not yet completed so that a suggestion of a content item can be made to further advance an identified user's task. This pipeline can incorporate probabilistic transition graphs, machine-learned models, and/or historical data to determine the relevance and completion of tasks that a user may desire to continue acting upon.

公开(公告)号：US20250094511A1

公开(公告)日：2025-03-20

申请号：US18785365

申请日：2024-07-26

Applicant: Google LLC

Inventor： Ibrahim Badr ,  Yunsong Guo ,  Imran R. Mansuri

IPC: G06F16/9535 ,  G06F40/20

Abstract: Systems and methods for proactive query and content suggestion can include obtaining web data, determining a change event occurred, and generating a query and content suggestion. Generating the query and content suggestion can include processing data descriptive of the change event with a generative model to generate one or more model-generated query suggestions. One or more web resources can be obtained then processed to generate a change event summary. The one or more query suggestions and the change event summary can then be provided for display.

公开(公告)号：US12007868B2

公开(公告)日：2024-06-11

申请号：US17368155

申请日：2021-07-06

Applicant: Google LLC

Inventor： Ibrahim Badr ,  Imran R. Mansuri ,  Sari Onaissi ,  InHan Kang ,  Wenqiong Guo ,  Anner Kushnir

IPC: G06F11/34 ,  G06F16/906 ,  G06F16/9535 ,  G06N20/00

CPC classification number: G06F11/3438 ,  G06F16/906 ,  G06F16/9535 ,  G06N20/00

Abstract: A computing system and method that can be used to surface a selectable action element for at least one ongoing task. In particular, the present disclosure provides a general pipeline to identify potential tasks that a user has an ongoing interest in or has not yet completed so that a suggestion of a content item can be made to further advance an identified user's task. This pipeline can incorporate probabilistic transition graphs, machine-learned models, and/or historical data to determine the relevance and completion of tasks that a user may desire to continue acting upon.