公开(公告)号：US20230186198A1

公开(公告)日：2023-06-15

申请号：US17643830

申请日：2021-12-12

Applicant: Google LLC

Inventor： Oliver Siohan ,  Kishan Sachdeva ,  Joshua Maynez ,  Benyah Shaparenko

IPC: G06Q10/06 ,  G06Q10/10 ,  G10L15/06 ,  G06F40/166 ,  G10L15/22 ,  G10L15/183

CPC classification number: G06Q10/063118 ,  G06Q10/103 ,  G10L15/063 ,  G06F40/166 ,  G10L15/22 ,  G10L15/183 ,  G10L2015/223

Abstract: A method includes obtaining a transcript of multiple dialog acts during a multi-party communication session and extracting, from the transcript, a plurality of extractive action items each associated with a task expected to be completed within a timeframe to begin after the multi-party communication session ends. The method also includes generating, using an abstractive action item identification model configured to receive the extractive action items extracted from the transcript, one or more abstractive action items. Each abstractive action item is associated with a respective group of one or more of the extractive action items that are associated with a same respective task. For each of the one or more abstractive action items, the method also includes presenting, in one or more graphical user interfaces, information related to the corresponding abstractive action item.

公开(公告)号：US20230267922A1

公开(公告)日：2023-08-24

申请号：US17678657

申请日：2022-02-23

Applicant: GOOGLE LLC

Inventor： Olivier Siohan ,  Takaki Makino ,  Joshua Maynez ,  Ryan Mcdonald ,  Benyah Shaparenko ,  Joseph Nelson ,  Kishan Sachdeva ,  Basilio Garcia

IPC: G10L15/18 ,  G06F40/279 ,  H04L12/18

CPC classification number: G10L15/1815 ,  G06F40/279 ,  H04L12/1831 ,  H04L12/1818

Abstract: Implementations relate to an application that can bias automatic speech recognition for meetings using data that may be associated with the meeting and/or meeting participants. A transcription of inputs provided during a meeting can additionally and/or alternatively be processed to determine whether the inputs should be incorporated into a meeting document, which can provide a summary for the meeting. In some instances, entries into a meeting document can be designated as action items, and those action items can optionally have conditions for reminding meeting participants about the action items and/or for determining whether an action item has been fulfilled. In this way, various tasks that may typically be manually performed by meeting participants, such as creating a meeting summary, can be automated in a more accurate manner. This can preserve resources that may otherwise be wasted during video conferences, in-person meetings, and/or other gatherings.

公开(公告)号：US12199783B2

公开(公告)日：2025-01-14

申请号：US17678657

申请日：2022-02-23

Applicant: GOOGLE LLC

Inventor： Olivier Siohan ,  Takaki Makino ,  Joshua Maynez ,  Ryan Mcdonald ,  Benyah Shaparenko ,  Joseph Nelson ,  Kishan Sachdeva ,  Basilio Garcia

IPC: H04L12/18 ,  G06F40/279 ,  G10L15/18

Abstract: Implementations relate to an application that can bias automatic speech recognition for meetings using data that may be associated with the meeting and/or meeting participants. A transcription of inputs provided during a meeting can additionally and/or alternatively be processed to determine whether the inputs should be incorporated into a meeting document, which can provide a summary for the meeting. In some instances, entries into a meeting document can be designated as action items, and those action items can optionally have conditions for reminding meeting participants about the action items and/or for determining whether an action item has been fulfilled. In this way, various tasks that may typically be manually performed by meeting participants, such as creating a meeting summary, can be automated in a more accurate manner. This can preserve resources that may otherwise be wasted during video conferences, in-person meetings, and/or other gatherings.