公开(公告)号：WO2022120200A2

公开(公告)日：2022-06-09

申请号：PCT/US2021/061855

申请日：2021-12-03

Applicant: GOOGLE LLC

Inventor： AHARONI, Asaf ,  LEVIATHAN, Yaniv ,  SEGALIS, Eyal ,  ELIDAN, Gal ,  GOLDSHTEIN, Sasha ,  AMIAZ, Tomer ,  COHEN, Deborah

IPC: G06N3/08 ,  G06F40/56 ,  G06F40/35 ,  H04M3/493 ,  G10L13/027 ,  G06F3/16 ,  H04L51/02 ,  G06Q30/00 ,  G10L25/30 ,  G10L15/18 ,  G06N3/04 ,  G06N3/00 ,  G06F16/3329 ,  G06F3/167 ,  G06F40/279 ,  G06N3/0454 ,  G06N3/084 ,  G06Q10/02 ,  G06Q10/10 ,  G06Q30/016 ,  G06Q30/0601 ,  G06Q50/12 ,  G06Q50/32 ,  G10L15/1822 ,  H04M3/4936

Abstract: Implementations are directed to providing a voice bot development platform that enables a third-party developer to train a voice bot based on training instance(s). The training instance(s) can each include training input and training output. The training input can include a portion of a corresponding conversation and a prior context of the corresponding conversation. The training output can include a corresponding ground truth response to the portion of the corresponding conversation. Subsequent to training, the voice bot can be deployed for conducting conversations on behalf of a third-party. In some implementations, the voice bot is further trained based on a corresponding feature emphasis input that attentions the voice bot to a particular feature of the portion of the corresponding conversation. In some additional or alternative implementations, the voice bot is further trained to interact with third-party system(s) via remote procedure calls (RPCs).

公开(公告)号：WO2022119580A1

公开(公告)日：2022-06-09

申请号：PCT/US2020/064722

申请日：2020-12-12

Applicant: GOOGLE LLC

Inventor： AHARONI, Asaf ,  LEVIATHAN, Yaniv ,  SEGALIS, Eyal ,  ELIDAN, Gal ,  GOLDSHTEIN, Sasha ,  AMIAZ, Tomer ,  COHEN, Deborah

IPC: G06N3/08 ,  G06F40/56 ,  G06F40/35 ,  H04L12/58 ,  H04M3/493 ,  G10L13/027 ,  G06F3/16 ,  G06Q30/00 ,  G10L25/30 ,  G10L15/18 ,  G06N3/04 ,  G06N3/00

Abstract: Implementations are directed to providing a voice bot development platform that enables a third-party developer to train a voice bot based on training instance(s). The training instance(s) can each include training input and training output. The training input can include a portion of a corresponding conversation and a prior context of the corresponding conversation. The training output can include a corresponding ground truth response to the portion of the corresponding conversation. Subsequent to training, the voice bot can be deployed for conducting conversations on behalf of a third-party. In some implementations, the voice bot is further trained based on a corresponding feature emphasis input that attentions the voice bot to a particular feature of the portion of the corresponding conversation. In some additional or alternative implementations, the voice bot is further trained to interact with third-party system(s) via remote procedure calls (RPCs).

公开(公告)号：WO2019236372A1

公开(公告)日：2019-12-12

申请号：PCT/US2019/034625

申请日：2019-05-30

Applicant: GOOGLE LLC

Inventor： FINK, Michael ,  VUSKOVIC, Vladimir ,  SALANT, Shimon Or ,  COHEN, Deborah ,  REVACH, Asaf ,  KOGAN, David ,  CALLAHAN, Andrew ,  BOROVOY, Richard ,  RICHARDSON, Andrew ,  OFEK, Eran ,  SZPEKTOR, Idan ,  BERANT, Jonathan

IPC: G06F16/9032 ,  G06F16/332 ,  G06F16/9535

Abstract: Generating expanded responses that guide continuance of a human-to computer dialog that is facilitated by a client device and that is between at least one user and an automated assistant. The expanded responses are generated by the automated assistant in response to user interface input provided by the user via the client device, and are caused to be rendered to the user via the client device, as a response, by the automated assistant, to the user interface input of the user. An expanded response is generated based on at least one entity of interest determined based on the user interface input, and is generated to incorporate content related to one or more additional entities that are related to the entity of interest, but that are not explicitly referenced by the user interface input.