-
公开(公告)号:US20220284198A1
公开(公告)日:2022-09-08
申请号:US17825778
申请日:2022-05-26
Applicant: GOOGLE LLC
Inventor: James Kuczmarski , Vibhor Jain , Amarnag Subramanya , Nimesh Ranjan , Melvin Jose Johnson Premkumar , Vladimir Vuskovic , Luna Dai , Daisuke Ikeda , Nihal Sandeep Balani , Jinna Lei , Mengmeng Niu , Hongjie Chai , Wangqing Yuan
Abstract: Techniques described herein relate to facilitating end-to-end multilingual communications with automated assistants. In various implementations, speech recognition output may be generated based on voice input in a first language. A first language intent may be identified based on the speech recognition output and fulfilled in order to generate a first natural language output candidate in the first language. At least part of the speech recognition output may be translated to a second language to generate an at least partial translation, which may then be used to identify a second language intent that is fulfilled to generate a second natural language output candidate in the second language. Scores may be determined for the first and second natural language output candidates, and based on the scores, a natural language output may be selected for presentation.
-
公开(公告)号:US12118981B2
公开(公告)日:2024-10-15
申请号:US17475897
申请日:2021-09-15
Applicant: GOOGLE LLC
Inventor: Wangqing Yuan , Bryan Christopher Horling , David Kogan
CPC classification number: G10L13/086 , G10L15/22 , G10L2015/223 , G10L2015/225
Abstract: Implementations relate to determining multilingual content to render at an interface in response to a user submitted query. Those implementations further relate to determining a first language response and a second language response to a query that is submitted to an automated assistant. Some of those implementations relate to determining multilingual content that includes a response to the query in both the first and second languages. Other implementations relate to determining multilingual content that includes a query suggestion in the first language and a query suggestion in a second language. Some of those implementations relate to pre-fetching results for the query suggestions prior to rendering the multilingual content.
-
13.
公开(公告)号:US12019999B2
公开(公告)日:2024-06-25
申请号:US17351872
申请日:2021-06-18
Applicant: GOOGLE LLC
Inventor: Wangqing Yuan , David Kogan , Vincent Lacey , Guanglei Wang , Shaun Post , Bryan Christopher Horling , Michael Anthony Schuler
IPC: G06F40/51 , G06F40/211 , G06F40/289
CPC classification number: G06F40/51 , G06F40/211 , G06F40/289
Abstract: Implementations relate to determining a well-formed phrase to suggest to a user to submit in lieu of a not well-formed phrase. The suggestion is rendered via an interface that is provided to a client device of the user. Those implementations relate to determining that a phrase is not well-formed, identifying alternate phrases that are related to the not well-formed phrase, and scoring the alternate phrases to select one or more of the alternate phrases to render via the interface. Some of those implementations are related to identifying that the phrase is not well-formed based on occurrences of the phrase in documents that are generated by a source with the language of the phrase as the primary language of the creator.
-
公开(公告)号:US11222030B2
公开(公告)日:2022-01-11
申请号:US16710802
申请日:2019-12-11
Applicant: Google LLC
Inventor: David Kogan , Wangqing Yuan , Wei Chen , Bryan Horling , Michael Itz
IPC: G06F16/2457 , G06N20/00 , G06F16/332 , G06F40/169 , G10L15/22 , H04L12/58 , H04W4/14
Abstract: Methods, apparatus, systems, and computer-readable media are provided for automatically augmenting message exchange threads based on a detected tone of messages exchanged between participants. In various implementations, a message contributed to a message exchange thread involving one or more message exchange clients by a participant may be determined. In various implementations, an idle chatter score associated with the message may be calculated. In various implementations, either a conversational response to the message or content responsive to a search query generated based on the message may be selectively incorporated into the message exchange thread based at least in part on the idle chatter score. In some implementations, a search query suitability score associated with the message may also be calculated.
-
公开(公告)号:US10783456B2
公开(公告)日:2020-09-22
申请号:US16611725
申请日:2018-12-14
Applicant: Google LLC
Inventor: Brian Strope , Yun-hsuan Sung , Wangqing Yuan
IPC: G06N20/00 , G06F16/35 , G06F16/332 , G06F16/33 , G06N5/04
Abstract: Systems, methods, and computer readable media related to: training an encoder model that can be utilized to determine semantic similarity of a natural language textual string to each of one or more additional natural language textual strings (directly and/or indirectly); and/or using a trained encoder model to determine one or more responsive actions to perform in response to a natural language query. The encoder model is a machine learning model, such as a neural network model. In some implementations of training the encoder model, the encoder model is trained as part of a larger network architecture trained based on one or more tasks that are distinct from a “semantic textual similarity” task for which the encoder model can be used.
-
公开(公告)号:US10515635B2
公开(公告)日:2019-12-24
申请号:US16181874
申请日:2018-11-06
Applicant: Google LLC
Inventor: Bryan Horling , David Kogan , Maryam Garrett , Daniel Kunkle , Wan Fen Nicole Quah , Ruijie He , Wangqing Yuan , Wei Chen , Michael Itz
IPC: G10L15/22 , G06F16/9535 , G10L15/18 , G10L15/30 , G10L15/26
Abstract: Techniques are described herein for chatbots to achieve greater social grace by tracking users' states and providing corresponding dialog. In various implementations, input may be received from a user at a client device operating a chatbot, e.g., during a first session between the user and the chatbot. The input may be semantically processed to determine a state expressed by the user to the chatbot. An indication of the state expressed by the user may be stored in memory for future use by the chatbot. It may then be determined, e.g., by the chatbot based on various signals, that a second session between the user and the chatbot is underway. In various implementations, as part of the second session, the chatbot may output a statement formed from a plurality of candidate words, phrases, and/or statements based on the stored indication of the state expressed by the user.
-
公开(公告)号:US12093270B2
公开(公告)日:2024-09-17
申请号:US18236285
申请日:2023-08-21
Applicant: GOOGLE LLC
Inventor: David Kogan , Wangqing Yuan , Wei Chen , Bryan Horling , Michael Itz
IPC: G06F16/332 , G06F16/2457 , G06F40/169 , G06N20/00 , G10L15/22 , H04L51/02 , H04L51/216 , H04W4/14
CPC classification number: G06F16/24578 , G06F16/3329 , G06F40/169 , G06N20/00 , G10L15/22 , H04L51/02 , H04L51/216 , H04W4/14
Abstract: Methods, apparatus, systems, and computer-readable media are provided for automatically augmenting message exchange threads based on a detected tone of messages exchanged between participants. In various implementations, a message contributed to a message exchange thread involving one or more message exchange clients by a participant may be determined. In various implementations, an idle chatter score associated with the message may be calculated. In various implementations, either a conversational response to the message or content responsive to a search query generated based on the message may be selectively incorporated into the message exchange thread based at least in part on the idle chatter score. In some implementations, a search query suitability score associated with the message may also be calculated.
-
公开(公告)号:US11842253B2
公开(公告)日:2023-12-12
申请号:US16995149
申请日:2020-08-17
Applicant: Google LLC
Inventor: Brian Strope , Yun-hsuan Sung , Wangqing Yuan
IPC: G06N20/00 , G06F16/35 , G06F16/332 , G06F16/33 , G06N5/04
CPC classification number: G06N20/00 , G06F16/3329 , G06F16/3344 , G06F16/3346 , G06F16/35 , G06N5/04
Abstract: Systems, methods, and computer readable media related to: training an encoder model that can be utilized to determine semantic similarity of a natural language textual string to each of one or more additional natural language textual strings (directly and/or indirectly); and/or using a trained encoder model to determine one or more responsive actions to perform in response to a natural language query. The encoder model is a machine learning model, such as a neural network model. In some implementations of training the encoder model, the encoder model is trained as part of a larger network architecture trained based on one or more tasks that are distinct from a “semantic textual similarity” task for which the encoder model can be used.
-
公开(公告)号:US11762865B2
公开(公告)日:2023-09-19
申请号:US17497264
申请日:2021-10-08
Applicant: Google LLC
Inventor: David Kogan , Wangqing Yuan , Wei Chen , Bryan Horling , Michael Itz
IPC: G06F16/2457 , G06F16/332 , H04L51/216 , G10L15/22 , H04L51/02 , H04W4/14 , G06N20/00 , G06F40/169
CPC classification number: G06F16/24578 , G06F16/3329 , G06F40/169 , G06N20/00 , G10L15/22 , H04L51/02 , H04L51/216 , H04W4/14
Abstract: Methods, apparatus, systems, and computer-readable media are provided for automatically augmenting message exchange threads based on a detected tone of messages exchanged between participants. In various implementations, a message contributed to a message exchange thread involving one or more message exchange clients by a participant may be determined. In various implementations, an idle chatter score associated with the message may be calculated. In various implementations, either a conversational response to the message or content responsive to a search query generated based on the message may be selectively incorporated into the message exchange thread based at least in part on the idle chatter score. In some implementations, a search query suitability score associated with the message may also be calculated.
-
20.
公开(公告)号:US20220405488A1
公开(公告)日:2022-12-22
申请号:US17351872
申请日:2021-06-18
Applicant: GOOGLE LLC
Inventor: Wangqing Yuan , David Kogan , Vincent Lacey , Guanglei Wang , Shaun Post , Bryan Christopher Horling , Michael Anthony Schuler
IPC: G06F40/51 , G06F40/289 , G06F40/211 , G06F16/632
Abstract: Implementations relate to determining a well-formed phrase to suggest to a user to submit in lieu of a not well-formed phrase. The suggestion is rendered via an interface that is provided to a client device of the user. Those implementations relate to determining that a phrase is not well-formed, identifying alternate phrases that are related to the not well-formed phrase, and scoring the alternate phrases to select one or more of the alternate phrases to render via the interface. Some of those implementations are related to identifying that the phrase is not well-formed based on occurrences of the phrase in documents that are generated by a source with the language of the phrase as the primary language of the creator.
-
-
-
-
-
-
-
-
-