公开(公告)号：US20230274205A1

公开(公告)日：2023-08-31

申请号：US18135579

申请日：2023-04-17

Applicant: GOOGLE LLC

Inventor： Robert Stets ,  Valerie Nygaard ,  Bogdan Caprita ,  Bradley M. Abrams ,  Jason Brant Douglas

IPC: G06Q10/0631 ,  G10L15/22

CPC classification number: G06Q10/063112 ,  G10L15/22 ,  G10L2015/223 ,  G06F16/951

Abstract: An example method includes receiving, by one or more processors, a representation of an utterance spoken at a computing device; identifying, by a first computational agent from a plurality of computational agents and based on the utterance, a multi-element task to be performed, wherein the plurality of computational agents includes one or more first party computational agents and a plurality of third-party computational agents; and performing, by the first computational agent, a first sub-set of elements of the multi-element task, wherein performing the first sub-set of elements comprises selecting a second computational agent from the plurality of computational agents to perform a second sub-set of elements of the multi-element task.

公开(公告)号：US20180096284A1

公开(公告)日：2018-04-05

申请号：US15815368

申请日：2017-11-16

Applicant: Google LLC

Inventor： Robert Stets ,  Valerie Nygaard ,  Bogdan Caprita ,  Bradley M. Abrams ,  Jason Brant Douglas

IPC: G06Q10/06 ,  G10L15/22

CPC classification number: G06Q10/063112 ,  G06F9/46 ,  G06F16/951 ,  G10L15/22 ,  G10L2015/223

Abstract: An example method includes receiving, by one or more processors, a representation of an utterance spoken at a computing device; identifying, by a first computational agent from a plurality of computational agents and based on the utterance, a multi-element task to be performed, wherein the plurality of computational agents includes one or more first party computational agents and a plurality of third-party computational agents; and performing, by the first computational agent, a first sub-set of elements of the multi-element task, wherein performing the first sub-set of elements comprises selecting a second computational agent from the plurality of computational agents to perform a second sub-set of elements of the multi-element task.

公开(公告)号：US20180096675A1

公开(公告)日：2018-04-05

申请号：US15815375

申请日：2017-11-16

Applicant: Google LLC

Inventor： Valerie Nygaard ,  Bogdan Caprita ,  Robert Stets ,  Saisuresh Krishnakumaran ,  Jason Brant Douglas

IPC: G10L13/04 ,  G06F3/16 ,  G06F17/30 ,  G10L13/08

CPC classification number: G10L13/043 ,  G06F3/167 ,  G06F17/30864 ,  G10L13/04 ,  G10L13/08 ,  G10L15/26

Abstract: An example method includes receiving, by a computational assistant executing at one or more processors, a representation of an utterance spoken at a computing device; selecting, based on the utterance, an agent from a plurality of agents, wherein the plurality of agents includes one or more first party agents and a plurality of third-party agents; responsive to determining that the selected agent comprises a first party agent, selecting a reserved voice from a plurality of voices; and outputting synthesized audio data using the selected voice to satisfy the utterance.

公开(公告)号：US20190272817A1

公开(公告)日：2019-09-05

申请号：US16417024

申请日：2019-05-20

Applicant: Google LLC

Inventor： Valerie Nygaard ,  Bogdan Caprita ,  Robert Stets ,  Saisuresh Krishnakumaran ,  Jason Brant Douglas

IPC: G10L13/04 ,  G06F16/951 ,  G10L15/26 ,  G06F3/16

Abstract: An example method includes receiving, by a computational assistant executing at one or more processors, a representation of an utterance spoken at a computing device; selecting, based on the utterance, an agent from a plurality of agents, wherein the plurality of agents includes one or more first party agents and a plurality of third-party agents; responsive to determining that the selected agent comprises a first party agent, selecting a reserved voice from a plurality of voices; and outputting synthesized audio data using the selected voice to satisfy the utterance.

公开(公告)号：US11663535B2

公开(公告)日：2023-05-30

申请号：US15815368

申请日：2017-11-16

Applicant: Google LLC

Inventor： Robert Stets ,  Valerie Nygaard ,  Bogdan Caprita ,  Bradley M. Abrams ,  Jason Brant Douglas

IPC: G06Q10/0631 ,  G10L15/22 ,  G06F16/951

CPC classification number: G06Q10/063112 ,  G10L15/22 ,  G06F16/951 ,  G10L2015/223

Abstract: An example method includes receiving, by one or more processors, a representation of an utterance spoken at a computing device; identifying, by a first computational agent from a plurality of computational agents and based on the utterance, a multi-element task to be performed, wherein the plurality of computational agents includes one or more first party computational agents and a plurality of third-party computational agents; and performing, by the first computational agent, a first sub-set of elements of the multi-element task, wherein performing the first sub-set of elements comprises selecting a second computational agent from the plurality of computational agents to perform a second sub-set of elements of the multi-element task.

公开(公告)号：US10854188B2

公开(公告)日：2020-12-01

申请号：US16417024

申请日：2019-05-20

Applicant: Google LLC

Inventor： Valerie Nygaard ,  Bogdan Caprita ,  Robert Stets ,  Saisuresh Krishnakumaran ,  Jason Brant Douglas

IPC: G10L13/00 ,  G06F3/16 ,  G06F16/951 ,  G10L13/04 ,  G10L15/26 ,  G06F9/50 ,  G10L15/22 ,  G10L13/08

Abstract: An example method includes receiving, by a computational assistant executing at one or more processors, a representation of an utterance spoken at a computing device; selecting, based on the utterance, an agent from a plurality of agents, wherein the plurality of agents includes one or more first party agents and a plurality of third-party agents; responsive to determining that the selected agent comprises a first party agent, selecting a reserved voice from a plurality of voices; and outputting synthesized audio data using the selected voice to satisfy the utterance.

公开(公告)号：US10311856B2

公开(公告)日：2019-06-04

申请号：US15815375

申请日：2017-11-16

Applicant: Google LLC

Inventor： Valerie Nygaard ,  Bogdan Caprita ,  Robert Stets ,  Saisuresh Krishnakumaran ,  Jason Brant Douglas

IPC: G10L13/00 ,  G10L13/04 ,  G06F3/16 ,  G06F16/951 ,  G10L15/26 ,  G10L13/08

Abstract: An example method includes receiving, by a computational assistant executing at one or more processors, a representation of an utterance spoken at a computing device; selecting, based on the utterance, an agent from a plurality of agents, wherein the plurality of agents includes one or more first party agents and a plurality of third-party agents; responsive to determining that the selected agent comprises a first party agent, selecting a reserved voice from a plurality of voices; and outputting synthesized audio data using the selected voice to satisfy the utterance.