公开(公告)号：US20240078083A1

公开(公告)日：2024-03-07

申请号：US18388465

申请日：2023-11-09

Applicant: GOOGLE LLC

Inventor： Srikanth Pandiri ,  Luv Kolhari ,  Behshad Behzadi ,  Zaheed Sabur ,  Domenico Carbotta ,  Akshay Kannan ,  Qi Wang ,  Gokay Baris Gultekin ,  Angana Ghosh ,  Xu Liu ,  Yang Lu ,  Steve Cheng

IPC: G06F3/16 ,  G06F3/0481 ,  G06F3/0484 ,  G06F3/04886 ,  G06F40/117 ,  G06F40/143 ,  G06F40/174 ,  G06F40/30 ,  G10L15/22 ,  G10L15/26

CPC classification number: G06F3/167 ,  G06F3/0481 ,  G06F3/0484 ,  G06F3/04886 ,  G06F40/117 ,  G06F40/143 ,  G06F40/174 ,  G06F40/30 ,  G10L15/22 ,  G10L15/26

Abstract: Implementations set forth herein relate to an automated assistant that can selectively determine whether to incorporate a verbatim interpretation of portions spoken utterances into an entry field and/or incorporate synonymous content into the entry field. For instance, a user can be accessing an interface that provides an entry field (e.g., address field) for receiving user input. In order to provide input for entry field, the user can select the entry field and/or access a GUI keyboard to initialize an automated assistant for assisting with filling the entry field. Should the user provide a spoken utterance, the user can elect to provide a spoken utterance that embodies the intended input (e.g., an actual address) or a reference to the intended input (e.g., a name). In response to the spoken utterance, the automated assistant can fill the entry field with the intended input without necessitating further input from the user.

公开(公告)号：US11853649B2

公开(公告)日：2023-12-26

申请号：US17619414

申请日：2019-12-13

Applicant: GOOGLE LLC

Inventor： Srikanth Pandiri ,  Luv Kothari ,  Behshad Behzadi ,  Zaheed Sabur ,  Domenico Carbotta ,  Akshay Kannan ,  Qi Wang ,  Gokay Baris Gultekin ,  Angana Ghosh ,  Xu Liu ,  Yang Lu ,  Steve Cheng

IPC: G06F40/117 ,  G06F3/16 ,  G06F40/143 ,  G06F40/30 ,  G06F40/174 ,  G06F3/0481 ,  G06F3/0484 ,  G06F3/04886 ,  G10L15/22 ,  G10L15/26

CPC classification number: G06F3/167 ,  G06F3/0481 ,  G06F3/0484 ,  G06F3/04886 ,  G06F40/117 ,  G06F40/143 ,  G06F40/174 ,  G06F40/30 ,  G10L15/22 ,  G10L15/26

Abstract: Implementations set forth herein relate to an automated assistant that can selectively determine whether to incorporate a verbatim interpretation of portions spoken utterances into an entry field and/or incorporate synonymous content into the entry field. For instance, a user can be accessing an interface that provides an entry field (e.g., address field) for receiving user input. In order to provide input for entry field, the user can select the entry field and/or access a GUI keyboard to initialize an automated assistant for assisting with filling the entry field. Should the user provide a spoken utterance, the user can elect to provide a spoken utterance that embodies the intended input (e.g., an actual address) or a reference to the intended input (e.g., a name). In response to the spoken utterance, the automated assistant can fill the entry field with the intended input without necessitating further input from the user.

公开(公告)号：US20220253277A1

公开(公告)日：2022-08-11

申请号：US17619414

申请日：2019-12-13

Applicant: GOOGLE LLC

Inventor： Srikanth Pandiri ,  Luv Kothari ,  Behshad Behzadi ,  Zaheed Sabur ,  Domenico Carbotta ,  Akshay Kannan ,  Qi Wang ,  Gokay Baris Gultekin ,  Angana Ghosh ,  Xu Liu ,  Yang Lu ,  Steve Cheng

IPC: G06F3/16 ,  G06F3/0481 ,  G06F40/174 ,  G10L15/26 ,  G06F3/0484 ,  G06F3/04886 ,  G06F40/30 ,  G06F40/143 ,  G06F40/117 ,  G10L15/22

Abstract: Implementations set forth herein relate to an automated assistant that can selectively determine whether to incorporate a verbatim interpretation of portions spoken utterances into an entry field and/or incorporate synonymous content into the entry field. For instance, a user can be accessing an interface that provides an entry field (e.g., address field) for receiving user input. In order to provide input for entry field, the user can select the entry field and/or access a GUI keyboard to initialize an automated assistant for assisting with filling the entry field. Should the user provide a spoken utterance, the user can elect to provide a spoken utterance that embodies the intended input (e.g., an actual address) or a reference to the intended input (e.g., a name). In response to the spoken utterance, the automated assistant can fill the entry field with the intended input without necessitating further input from the user.

公开(公告)号：US20240411513A1

公开(公告)日：2024-12-12

申请号：US18808933

申请日：2024-08-19

Applicant: GOOGLE LLC

Inventor： Srikanth Pandiri ,  Luv Kothari ,  Behshad Behzadi ,  Zaheed Sabur ,  Domenico Carbotta ,  Akshay Kannan ,  Qi Wang ,  Gokay Baris Gultekin ,  Angana Ghosh ,  Xu Liu ,  Yang Lu ,  Steve Cheng

IPC: G06F3/16 ,  G06F3/0481 ,  G06F3/0484 ,  G06F3/04886 ,  G06F40/117 ,  G06F40/143 ,  G06F40/174 ,  G06F40/30 ,  G10L15/22 ,  G10L15/26

Abstract: Implementations set forth herein relate to an automated assistant that can selectively determine whether to incorporate a verbatim interpretation of portions spoken utterances into an entry field and/or incorporate synonymous content into the entry field. For instance, a user can be accessing an interface that provides an entry field (e.g., address field) for receiving user input. In order to provide input for entry field, the user can select the entry field and/or access a GUI keyboard to initialize an automated assistant for assisting with filling the entry field. Should the user provide a spoken utterance, the user can elect to provide a spoken utterance that embodies the intended input (e.g., an actual address) or a reference to the intended input (e.g., a name). In response to the spoken utterance, the automated assistant can fill the entry field with the intended input without necessitating further input from the user.

公开(公告)号：US12093609B2

公开(公告)日：2024-09-17

申请号：US18388465

申请日：2023-11-09

Applicant: GOOGLE LLC

Inventor： Srikanth Pandiri ,  Luv Kothari ,  Behshad Behzadi ,  Zaheed Sabur ,  Domenico Carbotta ,  Akshay Kannan ,  Qi Wang ,  Gokay Baris Gultekin ,  Angana Ghosh ,  Xu Liu ,  Yang Lu ,  Steve Cheng

IPC: G06F3/048 ,  G06F3/0481 ,  G06F3/0484 ,  G06F3/04886 ,  G06F3/16 ,  G06F40/117 ,  G06F40/143 ,  G06F40/174 ,  G06F40/30 ,  G10L15/22 ,  G10L15/26

CPC classification number: G06F3/167 ,  G06F3/0481 ,  G06F3/0484 ,  G06F3/04886 ,  G06F40/117 ,  G06F40/143 ,  G06F40/174 ,  G06F40/30 ,  G10L15/22 ,  G10L15/26

Abstract: Implementations set forth herein relate to an automated assistant that can selectively determine whether to incorporate a verbatim interpretation of portions spoken utterances into an entry field and/or incorporate synonymous content into the entry field. For instance, a user can be accessing an interface that provides an entry field (e.g., address field) for receiving user input. In order to provide input for entry field, the user can select the entry field and/or access a GUI keyboard to initialize an automated assistant for assisting with filling the entry field. Should the user provide a spoken utterance, the user can elect to provide a spoken utterance that embodies the intended input (e.g., an actual address) or a reference to the intended input (e.g., a name). In response to the spoken utterance, the automated assistant can fill the entry field with the intended input without necessitating further input from the user.

公开(公告)号：US20240419919A1

公开(公告)日：2024-12-19

申请号：US18238878

申请日：2023-08-28

Applicant: Google LLC

Inventor： Rongjing Xiang ,  Yue Liang ,  Yang Lu ,  Xu Liu ,  Keqian Yan ,  Jiawei Chen

IPC: G06F40/40 ,  G06F40/166 ,  G06F40/35 ,  G06N3/08 ,  G06T11/60

Abstract: The technology provides rewriting suggestions for communication styles in different pre-defined styles. Rewriting may convert text in different ways, including visually enhancing the message. A method provides input to a trained large language model, the input including curated examples associated with one or more writing style choices. The set of curated examples has a first size. The method also includes generating, using the model, a rewriting corpus according to one or more writing style choices. The rewriting corpus has a size two or more orders of magnitude larger than a size of curated examples. The writing style choices include at least one of tone, conversion, application context, or conversation type. A text rewriting model is trained using at least a subset of the rewriting corpus. The model is configured to generate vivid textual information in response to user input in an interactive domain, according to specific writing style choices.

公开(公告)号：US11698699B2

公开(公告)日：2023-07-11

申请号：US17735937

申请日：2022-05-03

Applicant: Google LLC

Inventor： Xu Liu ,  Shumin Zhai ,  Adrian Pittman ,  Billy Dou

IPC: G06F3/048 ,  G06F3/041 ,  G06F3/04886

CPC classification number: G06F3/04186 ,  G06F3/04886

Abstract: A method includes detecting a touch input by a user at a position on a virtual keyboard. The method further includes applying a spatial model to map the touch input to one or more first candidate keys of the virtual keyboard, wherein the spatial model maps the touch input to the one or more first candidate keys based on a heatmap of prior touch inputs by the user. The method further includes applying a language model to map the touch input to one or more second candidate keys of the virtual keyboard, wherein the language model maps the touch input to the one or more second candidate keys based on comparing the position of the touch input to one or more predicted next keys. The method further includes selecting a particular key of the one or more first and second candidate keys as indicated by the touch input.

公开(公告)号：US11347352B2

公开(公告)日：2022-05-31

申请号：US17079492

申请日：2020-10-25

Applicant: Google LLC

Inventor： Xu Liu ,  Shumin Zhai ,  Adrian Pittman ,  Billy Dou

IPC: G06F3/048 ,  G06F3/041 ,  G06F3/04886

Abstract: A method includes detecting a touch input by a user at a position on a virtual keyboard. The method further includes applying a spatial model to map the touch input to one or more first candidate keys of the virtual keyboard, wherein the spatial model maps the touch input to the one or more first candidate keys based on a heatmap of prior touch inputs by the user. The method further includes applying a language model to map the touch input to one or more second candidate keys of the virtual keyboard, wherein the language model maps the touch input to the one or more second candidate keys based on comparing the position of the touch input to one or more predicted next keys. The method further includes selecting a particular key of the one or more first and second candidate keys as indicated by the touch input.