公开(公告)号：US20220318248A1

公开(公告)日：2022-10-06

申请号：US17217671

申请日：2021-03-30

Applicant: Google LLC

Inventor： Benedict Liang ,  Bryan Christopher Horling ,  Lan Huo ,  Anarghya Mitra

IPC: G06F16/2453 ,  G06F16/248 ,  G06F16/242 ,  G10L15/30 ,  G06F16/2455 ,  G10L15/22

Abstract: Implementations set forth herein relate to conditionally caching responses to automated assistant queries according to certain contextual data that may be associated with each automated assistant query. Each query can be identified based on historical interactions between a user and an automated assistant, and—depending on the query, fulfillment data can be cached according to certain contextual data that influences the query response. Depending on how the contextual data changes, a cached response stored at a client device can be discarded and/or replaced with an updated cached response. For example, a query that users commonly ask prior to leaving for work can have a corresponding assistant response that depends on features of an environment of the users. This unique assistant response can be cached, before the users provide the query, to minimize latency that can occur when network or processing bandwidth is unpredictable.

公开(公告)号：US11567935B2

公开(公告)日：2023-01-31

申请号：US17217671

申请日：2021-03-30

Applicant: Google LLC

Inventor： Benedict Liang ,  Bryan Christopher Horling ,  Lan Huo ,  Anarghya Mitra

IPC: G06F16/2453 ,  G06F16/242 ,  G06F16/2455 ,  G06F16/248 ,  G10L15/22 ,  G10L15/30

Abstract: Implementations set forth herein relate to conditionally caching responses to automated assistant queries according to certain contextual data that may be associated with each automated assistant query. Each query can be identified based on historical interactions between a user and an automated assistant, and—depending on the query, fulfillment data can be cached according to certain contextual data that influences the query response. Depending on how the contextual data changes, a cached response stored at a client device can be discarded and/or replaced with an updated cached response. For example, a query that users commonly ask prior to leaving for work can have a corresponding assistant response that depends on features of an environment of the users. This unique assistant response can be cached, before the users provide the query, to minimize latency that can occur when network or processing bandwidth is unpredictable.

公开(公告)号：US11907214B2

公开(公告)日：2024-02-20

申请号：US18103345

申请日：2023-01-30

Applicant: GOOGLE LLC

Inventor： Benedict Liang ,  Bryan Christopher Horling ,  Lan Huo ,  Anarghya Mitra

IPC: G06F16/27 ,  G06F16/2453 ,  G06F16/242 ,  G06F16/2455 ,  G06F16/248 ,  G10L15/22 ,  G10L15/30

CPC classification number: G06F16/24539 ,  G06F16/243 ,  G06F16/248 ,  G06F16/24552 ,  G10L15/22 ,  G10L15/30 ,  G10L2015/221

Abstract: Implementations set forth herein relate to conditionally caching responses to automated assistant queries according to certain contextual data that may be associated with each automated assistant query. Each query can be identified based on historical interactions between a user and an automated assistant, and—depending on the query, fulfillment data can be cached according to certain contextual data that influences the query response. Depending on how the contextual data changes, a cached response stored at a client device can be discarded and/or replaced with an updated cached response. For example, a query that users commonly ask prior to leaving for work can have a corresponding assistant response that depends on features of an environment of the users. This unique assistant response can be cached, before the users provide the query, to minimize latency that can occur when network or processing bandwidth is unpredictable.

公开(公告)号：US20230177050A1

公开(公告)日：2023-06-08

申请号：US18103345

申请日：2023-01-30

Applicant: GOOGLE LLC

Inventor： Benedict Liang ,  Bryan Christopher Horling ,  Lan Huo ,  Anarghya Mitra

IPC: G06F16/2453 ,  G06F16/242 ,  G06F16/2455 ,  G06F16/248 ,  G10L15/22 ,  G10L15/30

CPC classification number: G06F16/24539 ,  G06F16/243 ,  G06F16/24552 ,  G06F16/248 ,  G10L15/22 ,  G10L15/30 ,  G10L2015/221

Abstract: Implementations set forth herein relate to conditionally caching responses to automated assistant queries according to certain contextual data that may be associated with each automated assistant query. Each query can be identified based on historical interactions between a user and an automated assistant, and—depending on the query, fulfillment data can be cached according to certain contextual data that influences the query response. Depending on how the contextual data changes, a cached response stored at a client device can be discarded and/or replaced with an updated cached response. For example, a query that users commonly ask prior to leaving for work can have a corresponding assistant response that depends on features of an environment of the users. This unique assistant response can be cached, before the users provide the query, to minimize latency that can occur when network or processing bandwidth is unpredictable.