公开(公告)号：US20230343324A1

公开(公告)日：2023-10-26

申请号：US17744440

申请日：2022-05-13

Applicant: GOOGLE LLC

Inventor： Martin Baeuml ,  Thushan Amarasiriwardena ,  Roberto Pieraccini ,  Gianluca Martini

IPC: G06V40/20 ,  G10L25/57 ,  G10L15/06 ,  H04N5/04 ,  G06F40/169 ,  G10L15/183 ,  G06T7/20 ,  G10L13/08 ,  G10L15/22 ,  G06V20/40 ,  G10L13/02

CPC classification number: G10L15/22 ,  G06F40/169 ,  G06T7/20 ,  G06V20/40 ,  G06V40/20 ,  G10L13/02 ,  G10L13/08 ,  G10L15/063 ,  G10L15/183 ,  G10L25/57 ,  H04N5/04 ,  G06T2207/10016 ,  G06T2207/30196

Abstract: Implementations relate to dynamically adapting a given assistant output based on a given persona, from among a plurality of disparate personas, assigned to an automated assistant. In some implementations, the given assistant output can be generated and subsequently adapted based on the given persona assigned to the automated assistant. In other implementations, the given assistant output can be generated specific to the given persona and without having to subsequently adapt the given assistant output to the given persona. Notably, the given assistant output can include a stream of textual content to be synthesized for audible presentation to the user, and a stream of visual cues utilized in controlling a display of a client device and/or in controlling a visualized representation of the automated assistant. Various implementations utilize large language models (LLMs), or output previously generated utilizing LLMs, to reflect the given persona in the given assistant output.

公开(公告)号：US20230343323A1

公开(公告)日：2023-10-26

申请号：US17726244

申请日：2022-04-21

Applicant: GOOGLE LLC

Inventor： Martin Baeuml ,  Thushan Amarasiriwardena ,  Roberto Pieraccini ,  Gianluca Martini

IPC: G10L13/10 ,  G10L15/22 ,  G10L15/18

CPC classification number: G10L13/10 ,  G10L15/22 ,  G10L15/1815 ,  G10L2015/223

Abstract: Implementations relate to dynamically adapting a given assistant output based on a given persona, from among a plurality of disparate personas, assigned to an automated assistant. In some implementations, the given assistant output can be generated and subsequently adapted based on the given persona assigned to the automated assistant. In other implementations, the given assistant output can be generated specific to the given persona and without having to subsequently adapt the given assistant output to the given persona. Notably, the given assistant output can include a stream of textual content to be synthesized for audible presentation to the user, and a stream of visual cues utilized in controlling a display of a client device and/or in controlling a visualized representation of the automated assistant. Various implementations utilize large language models (LLMs), or output previously generated utilizing LLMs, to reflect the given persona in the given assistant output.

公开(公告)号：US12223944B2

公开(公告)日：2025-02-11

申请号：US17744440

申请日：2022-05-13

Applicant: GOOGLE LLC

Inventor： Martin Baeuml ,  Thushan Amarasiriwardena ,  Roberto Pieraccini ,  Gianluca Martini

IPC: G06F40/56 ,  G06F3/16 ,  G06F16/332 ,  G06F40/169 ,  G06T7/20 ,  G06V20/40 ,  G06V40/20 ,  G10L13/02 ,  G10L13/033 ,  G10L13/08 ,  G10L13/10 ,  G10L15/06 ,  G10L15/18 ,  G10L15/183 ,  G10L15/22 ,  G10L25/57 ,  H04N5/04

Abstract: Implementations relate to dynamically adapting a given assistant output based on a given persona, from among a plurality of disparate personas, assigned to an automated assistant. In some implementations, the given assistant output can be generated and subsequently adapted based on the given persona assigned to the automated assistant. In other implementations, the given assistant output can be generated specific to the given persona and without having to subsequently adapt the given assistant output to the given persona. Notably, the given assistant output can include a stream of textual content to be synthesized for audible presentation to the user, and a stream of visual cues utilized in controlling a display of a client device and/or in controlling a visualized representation of the automated assistant. Various implementations utilize large language models (LLMs), or output previously generated utilizing LLMs, to reflect the given persona in the given assistant output.