公开(公告)号：US20250006202A1

公开(公告)日：2025-01-02

申请号：US18882580

申请日：2024-09-11

Applicant: GOOGLE LLC

Inventor： Amit Singhal ,  Michael Ng

IPC: G10L17/22 ,  G06F16/33 ,  G06F16/332 ,  G10L17/14

Abstract: Implementations described herein relate to various techniques for biasing interpretations of spoken utterances that are received in a vehicular environment. For example, implementations can receive a spoken utterance that includes a query from a user of a vehicle and obtain a corresponding vehicle sensor data instance generated by vehicle sensor(s) of the vehicle. Some implementations can determine to execute a search over only a first corpus of data, but not a second corpus of data, to obtain a given response to the query based on various criteria, including at least the query, the corresponding vehicle sensor data instance, a corresponding timestamp associated with the corresponding vehicle sensor data instance, and/or a corresponding duration of time the user has been associated with the vehicle. Additional, or alternative, implementations can execute a search over both the first and second corpora of data, and obtain the given response based on the criteria.

公开(公告)号：US12119006B2

公开(公告)日：2024-10-15

申请号：US17690403

申请日：2022-03-09

Applicant: GOOGLE LLC

Inventor： Amit Singhal ,  Michael Ng

IPC: G10L17/22 ,  G06F16/33 ,  G06F16/332 ,  G10L17/14

CPC classification number: G10L17/22 ,  G06F16/3329 ,  G06F16/3344 ,  G10L17/14

Abstract: Implementations described herein relate to various techniques for biasing interpretations of spoken utterances that are received in a vehicular environment. For example, implementations can receive a spoken utterance that includes a query from a user of a vehicle and obtain a corresponding vehicle sensor data instance generated by vehicle sensor(s) of the vehicle. Some implementations can determine to execute a search over only a first corpus of data, but not a second corpus of data, to obtain a given response to the query based on various criteria, including at least the query, the corresponding vehicle sensor data instance, a corresponding timestamp associated with the corresponding vehicle sensor data instance, and/or a corresponding duration of time the user has been associated with the vehicle. Additional, or alternative, implementations can execute a search over both the first and second corpora of data, and obtain the given response based on the criteria.

公开(公告)号：US20230290358A1

公开(公告)日：2023-09-14

申请号：US17690403

申请日：2022-03-09

Applicant: GOOGLE LLC

Inventor： Amit Singhal ,  Michael Ng

IPC: G10L17/22 ,  G10L17/14 ,  G06F16/332 ,  G06F16/33

CPC classification number: G10L17/22 ,  G10L17/14 ,  G06F16/3329 ,  G06F16/3344

Abstract: Implementations described herein relate to various techniques for biasing interpretations of spoken utterances that are received in a vehicular environment. For example, implementations can receive a spoken utterance that includes a query from a user of a vehicle and obtain a corresponding vehicle sensor data instance generated by vehicle sensor(s) of the vehicle. Some implementations can determine to execute a search over only a first corpus of data, but not a second corpus of data, to obtain a given response to the query based on various criteria, including at least the query, the corresponding vehicle sensor data instance, a corresponding timestamp associated with the corresponding vehicle sensor data instance, and/or a corresponding duration of time the user has been associated with the vehicle. Additional, or alternative, implementations can execute a search over both the first and second corpora of data, and obtain the given response based on the criteria.