公开(公告)号：US20220180857A1

公开(公告)日：2022-06-09

申请号：US17112418

申请日：2020-12-04

Applicant: Google LLC

Inventor： Asaf Aharoni ,  Yaniv LEVIATHAN ,  Eyal SEGALIS ,  Gal ELIDAN ,  Sasha Goldshtein ,  Tomer Amiaz ,  Deborah Cohen

IPC: G10L15/06 ,  G10L15/22 ,  G10L15/04 ,  G10L15/02 ,  H04M3/493 ,  H04L29/06 ,  G06N20/00

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：US20220180858A1

公开(公告)日：2022-06-09

申请号：US17541098

申请日：2021-12-02

Applicant: GOOGLE LLC

Inventor： Asaf Aharoni ,  Yaniv LEVIATHAN ,  Eyal SEGALIS ,  Gal ELIDAN ,  Sasha Goldshtein ,  Tomer Amiaz ,  Deborah Cohen

IPC: G10L15/06 ,  G10L15/22 ,  H04L67/53 ,  G10L15/30 ,  H04L67/133 ,  H04M3/51

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).