公开(公告)号：US20220148596A1

公开(公告)日：2022-05-12

申请号：US17582926

申请日：2022-01-24

Applicant: Google LLC

Inventor： Barnaby James ,  Bo Wang ,  Sunil Vemuri ,  David Schairer ,  Ulas Kirazci ,  Ertan Dogrultan ,  Petar Aleksic

IPC: G10L15/22 ,  G10L15/18 ,  G06F40/284 ,  G06F40/30 ,  G10L15/183 ,  G06F40/205 ,  G10L15/30

Abstract: Implementations relate to dynamically, and in a context-sensitive manner, biasing voice to text conversion. In some implementations, the biasing of voice to text conversions is performed by a voice to text engine of a local agent, and the biasing is based at least in part on content provided to the local agent by a third-party (3P) agent that is in network communication with the local agent. In some of those implementations, the content includes contextual parameters that are provided by the 3P agent in combination with responsive content generated by the 3P agent during a dialog that: is between the 3P agent, and a user of a voice-enabled electronic device; and is facilitated by the local agent. The contextual parameters indicate potential feature(s) of further voice input that is to be provided in response to the responsive content generated by the 3P agent.

公开(公告)号：US11861393B2

公开(公告)日：2024-01-02

申请号：US17979556

申请日：2022-11-02

Applicant: GOOGLE LLC

Inventor： Yuzhao Ni ,  David Schairer

IPC: G10L15/19 ,  G06F9/48 ,  G10L15/22 ,  G06Q10/02 ,  G06F3/16 ,  G06F40/205 ,  G10L15/26

CPC classification number: G06F9/4831 ,  G06F3/16 ,  G06F3/167 ,  G06F9/4843 ,  G06F40/205 ,  G06Q10/02 ,  G10L15/22 ,  G10L15/26 ,  G10L2015/223

Abstract: Methods, apparatus, systems, and computer-readable media for engaging an automated assistant to perform multiple tasks through a multitask command. The multitask command can be a command that, when provided by a user, causes the automated assistant to invoke multiple different agent modules for performing tasks to complete the multitask command. During execution of the multitask command, a user can provide input that can be used by one or more agent modules to perform their respective tasks. Furthermore, feedback from one or more agent modules can be used by the automated assistant to dynamically alter tasks in order to more effectively use resources available during completion of the multitask command.

公开(公告)号：US20230056213A1

公开(公告)日：2023-02-23

申请号：US17979556

申请日：2022-11-02

Applicant: GOOGLE LLC

Inventor： Yuzhao Ni ,  David Schairer

IPC: G06F9/48 ,  G10L15/22 ,  G06Q10/02 ,  G06F3/16 ,  G06F40/205 ,  G10L15/26

Abstract: Methods, apparatus, systems, and computer-readable media for engaging an automated assistant to perform multiple tasks through a multitask command. The multitask command can be a command that, when provided by a user, causes the automated assistant to invoke multiple different agent modules for performing tasks to complete the multitask command. During execution of the multitask command, a user can provide input that can be used by one or more agent modules to perform their respective tasks. Furthermore, feedback from one or more agent modules can be used by the automated assistant to dynamically alter tasks in order to more effectively use resources available during completion of the multitask command.

公开(公告)号：US20190096406A1

公开(公告)日：2019-03-28

申请号：US16203521

申请日：2018-11-28

Applicant: Google LLC

Inventor： Yuzhao Ni ,  Bo Wang ,  Barnaby James ,  Pravir Gupta ,  David Schairer

IPC: G10L15/22 ,  G10L15/18 ,  G10L15/06 ,  G06F17/30 ,  G10L15/08 ,  G10L15/183 ,  G06F17/28 ,  G06F3/16

Abstract: In various implementations, upon receiving a given voice command from a user, a voice-based trigger may be selected from a library of voice-based triggers previously used across a population of users. The library may include association(s) between each voice-based trigger and responsive action(s) previously performed in response to the voice-based trigger. The selecting may be based on a measure of similarity between the given voice command and the selected voice-based trigger. One or more responsive actions associated with the selected voice-based trigger in the library may be determined. Based on the one or more responsive actions, current responsive action(s) may be performed by the client device. Feedback associated with performance of the current responsive action(s) may be received from the user and used to alter a strength of an association between the selected voice-based trigger and the one or more responsive actions.

公开(公告)号：US12217759B2

公开(公告)日：2025-02-04

申请号：US18434602

申请日：2024-02-06

Applicant: GOOGLE LLC

Inventor： Barnaby James ,  Bo Wang ,  Sunil Vemuri ,  David Schairer ,  Ulas Kirazci ,  Ertan Dogrultan ,  Petar Aleksic

IPC: G10L15/26 ,  G06F40/205 ,  G06F40/284 ,  G06F40/30 ,  G10L15/18 ,  G10L15/183 ,  G10L15/22 ,  G10L15/30

Abstract: Implementations relate to dynamically, and in a context-sensitive manner, biasing voice to text conversion. In some implementations, the biasing of voice to text conversions is performed by a voice to text engine of a local agent, and the biasing is based at least in part on content provided to the local agent by a third-party (3P) agent that is in network communication with the local agent. In some of those implementations, the content includes contextual parameters that are provided by the 3P agent in combination with responsive content generated by the 3P agent during a dialog that: is between the 3P agent, and a user of a voice-enabled electronic device; and is facilitated by the local agent. The contextual parameters indicate potential feature(s) of further voice input that is to be provided in response to the responsive content generated by the 3P agent.

公开(公告)号：US20240274133A1

公开(公告)日：2024-08-15

申请号：US18434602

申请日：2024-02-06

Applicant: GOOGLE LLC

Inventor： Barnaby James ,  Bo Wang ,  Sunil Vemuri ,  David Schairer ,  Ulas Kirazci ,  Ertan Dogrultan ,  Petar Aleksic

IPC: G10L15/26 ,  G06F40/205 ,  G06F40/284 ,  G06F40/30 ,  G10L15/18 ,  G10L15/183 ,  G10L15/22 ,  G10L15/30

CPC classification number: G10L15/26 ,  G06F40/205 ,  G06F40/284 ,  G06F40/30 ,  G10L15/1815 ,  G10L15/183 ,  G10L15/22 ,  G10L15/30 ,  G10L2015/223 ,  G10L2015/228

Abstract: Implementations relate to dynamically, and in a context-sensitive manner, biasing voice to text conversion. In some implementations, the biasing of voice to text conversions is performed by a voice to text engine of a local agent, and the biasing is based at least in part on content provided to the local agent by a third-party (3P) agent that is in network communication with the local agent. In some of those implementations, the content includes contextual parameters that are provided by the 3P agent in combination with responsive content generated by the 3P agent during a dialog that: is between the 3P agent, and a user of a voice-enabled electronic device; and is facilitated by the local agent. The contextual parameters indicate potential feature(s) of further voice input that is to be provided in response to the responsive content generated by the 3P agent.

公开(公告)号：US20230260517A1

公开(公告)日：2023-08-17

申请号：US18125606

申请日：2023-03-23

Applicant: GOOGLE LLC

Inventor： Barnaby James ,  Bo Wang ,  Sunil Vemuri ,  David Schairer ,  Ulas Kirazci ,  Ertan Dogrultan ,  Petar Aleksic

IPC: G10L15/26 ,  G10L15/22 ,  G06F40/284 ,  G06F40/205 ,  G06F40/30 ,  G10L15/183 ,  G10L15/18 ,  G10L15/30

CPC classification number: G10L15/26 ,  G06F40/30 ,  G06F40/205 ,  G06F40/284 ,  G10L15/22 ,  G10L15/30 ,  G10L15/183 ,  G10L15/1815 ,  G10L2015/223 ,  G10L2015/228

Abstract: Implementations relate to dynamically, and in a context-sensitive manner, biasing voice to text conversion. In some implementations, the biasing of voice to text conversions is performed by a voice to text engine of a local agent, and the biasing is based at least in part on content provided to the local agent by a third-party (3P) agent that is in network communication with the local agent. In some of those implementations, the content includes contextual parameters that are provided by the 3P agent in combination with responsive content generated by the 3P agent during a dialog that: is between the 3P agent, and a user of a voice-enabled electronic device; and is facilitated by the local agent. The contextual parameters indicate potential feature(s) of further voice input that is to be provided in response to the responsive content generated by the 3P agent.

公开(公告)号：US11232797B2

公开(公告)日：2022-01-25

申请号：US16791334

申请日：2020-02-14

Applicant: Google LLC

Inventor： Barnaby James ,  Bo Wang ,  Sunil Vemuri ,  David Schairer ,  Ulas Kirazci ,  Ertan Dogrultan ,  Petar Aleksic

IPC: G10L15/26 ,  G10L15/22 ,  G10L15/18 ,  G10L15/30

Abstract: Implementations relate to dynamically, and in a context-sensitive manner, biasing voice to text conversion. In some implementations, the biasing of voice to text conversions is performed by a voice to text engine of a local agent, and the biasing is based at least in part on content provided to the local agent by a third-party (3P) agent that is in network communication with the local agent. In some of those implementations, the content includes contextual parameters that are provided by the 3P agent in combination with responsive content generated by the 3P agent during a dialog that: is between the 3P agent, and a user of a voice-enabled electronic device; and is facilitated by the local agent. The contextual parameters indicate potential feature(s) of further voice input that is to be provided in response to the responsive content generated by the 3P agent.

公开(公告)号：US20240086230A1

公开(公告)日：2024-03-14

申请号：US18516290

申请日：2023-11-21

Applicant: GOOGLE LLC

Inventor： Yuzhao Ni ,  David Schairer

IPC: G06F9/48 ,  G06F3/16 ,  G06F40/205 ,  G06Q10/02 ,  G10L15/22 ,  G10L15/26

CPC classification number: G06F9/4831 ,  G06F3/16 ,  G06F3/167 ,  G06F9/4843 ,  G06F40/205 ,  G06Q10/02 ,  G10L15/22 ,  G10L15/26 ,  G10L2015/223

Abstract: Methods, apparatus, systems, and computer-readable media for engaging an automated assistant to perform multiple tasks through a multitask command. The multitask command can be a command that, when provided by a user, causes the automated assistant to invoke multiple different agent modules for performing tasks to complete the multitask command. During execution of the multitask command, a user can provide input that can be used by one or more agent modules to perform their respective tasks. Furthermore, feedback from one or more agent modules can be used by the automated assistant to dynamically alter tasks in order to more effectively use resources available during completion of the multitask command.

公开(公告)号：US11922945B2

公开(公告)日：2024-03-05

申请号：US18125606

申请日：2023-03-23

Applicant: GOOGLE LLC

Inventor： Barnaby James ,  Bo Wang ,  Sunil Vemuri ,  David Schairer ,  Ulas Kirazci ,  Ertan Dogrultan ,  Petar Aleksic

IPC: G10L15/26 ,  G06F40/205 ,  G06F40/284 ,  G06F40/30 ,  G10L15/18 ,  G10L15/183 ,  G10L15/22 ,  G10L15/30

CPC classification number: G10L15/26 ,  G06F40/205 ,  G06F40/284 ,  G06F40/30 ,  G10L15/1815 ,  G10L15/183 ,  G10L15/22 ,  G10L15/30 ,  G10L2015/223 ,  G10L2015/228

Abstract: Implementations relate to dynamically, and in a context-sensitive manner, biasing voice to text conversion. In some implementations, the biasing of voice to text conversions is performed by a voice to text engine of a local agent, and the biasing is based at least in part on content provided to the local agent by a third-party (3P) agent that is in network communication with the local agent. In some of those implementations, the content includes contextual parameters that are provided by the 3P agent in combination with responsive content generated by the 3P agent during a dialog that: is between the 3P agent, and a user of a voice-enabled electronic device; and is facilitated by the local agent. The contextual parameters indicate potential feature(s) of further voice input that is to be provided in response to the responsive content generated by the 3P agent.