公开(公告)号：US20240169186A1

公开(公告)日：2024-05-23

申请号：US18550203

申请日：2021-06-02

Applicant: Google LLC

Inventor： Xiaoxue Zang ,  Ying Xu ,  Srinivas Kumar Sunkara ,  Abhinav Kumar Rastogi ,  Jindong Chen ,  Blaise Aguera-Arcas ,  Chongyang Bai

IPC: G06N3/0455 ,  G06N3/084

CPC classification number: G06N3/0455 ,  G06N3/084

Abstract: Generally, the present disclosure is directed to user interface understanding. More particularly, the present disclosure relates to training and utilization of machine-learned models for user interface prediction and/or generation. A machine-learned interface Nprediction model can be pre-trained using a variety of pre-training tasks for eventual downstream task training and utilization (e.g., interface prediction, interface generation, etc.).

公开(公告)号：US20230162098A1

公开(公告)日：2023-05-25

申请号：US18152553

申请日：2023-01-10

Applicant: Google LLC

Inventor： Abhinav Kumar Rastogi ,  Raghav Gupta ,  Xiaoxue Zang ,  Srinivas Kumar Sunkara ,  Pranav Khaitan

IPC: G06Q10/02 ,  G06N20/00 ,  G06F40/20 ,  G06Q50/30 ,  G06F9/54 ,  G06F16/242 ,  G06F16/21

CPC classification number: G06Q10/02 ,  G06N20/00 ,  G06F40/20 ,  G06Q50/30 ,  G06F9/54 ,  G06F16/243 ,  G06F16/211

Abstract: Generally, the present disclosure is directed to systems and methods for performing task-oriented response generation that can provide advantages for artificial intelligence systems or other computing systems that include natural language processing for interpreting user input. Example implementations can process natural language descriptions of various services that can be accessed by the system. In response to a natural language input, systems can identify relevant values for executing one of the service(s), based in part on comparing embedded representations of the natural language input and the natural language description using a machine learned model.

公开(公告)号：US20240004677A1

公开(公告)日：2024-01-04

申请号：US18466267

申请日：2023-09-13

Applicant: Google LLC

Inventor： Srinivas Kumar Sunkara ,  Xiaoxue Zang ,  Ying Xu ,  Lijuan Liu ,  Nevan Holt Wichers ,  Gabriel Overholt Schubiner ,  Jindong Chen ,  Abhinav Kumar Rastogi ,  Blaise Aguera-Arcas ,  Zecheng He

IPC: G06F9/451 ,  G06N20/00 ,  G06F18/214 ,  G06F18/2135 ,  G06N3/045

CPC classification number: G06F9/451 ,  G06N20/00 ,  G06N3/045 ,  G06F18/21355 ,  G06F18/214

Abstract: Generally, the present disclosure is directed to user interface understanding. More particularly, the present disclosure relates to training and utilization of machine-learned models for user interface prediction and/or generation. A machine-learned interface prediction model can be pre-trained using a variety of pre-training tasks for eventual downstream task training and utilization (e.g., interface prediction, interface generation, etc.).

公开(公告)号：US11789753B2

公开(公告)日：2023-10-17

申请号：US17335596

申请日：2021-06-01

Applicant: Google LLC

Inventor： Srinivas Kumar Sunkara ,  Xiaoxue Zang ,  Ying Xu ,  Lijuan Liu ,  Nevan Holt Wichers ,  Gabriel Overholt Schubiner ,  Jindong Chen ,  Abhinav Kumar Rastogi ,  Blaise Aguera-Arcas ,  Zecheng He

IPC: G06F9/44 ,  G06F9/451 ,  G06N20/00 ,  G06F18/214 ,  G06F18/2135 ,  G06N3/045

CPC classification number: G06F9/451 ,  G06F18/214 ,  G06F18/21355 ,  G06N3/045 ,  G06N20/00

Abstract: Generally, the present disclosure is directed to user interface understanding. More particularly, the present disclosure relates to training and utilization of machine-learned models for user interface prediction and/or generation. A machine-learned interface prediction model can be pre-trained using a variety of pre-training tasks for eventual downstream task training and utilization (e.g., interface prediction, interface generation, etc.).

公开(公告)号：US12087288B2

公开(公告)日：2024-09-10

申请号：US17273555

申请日：2019-09-04

Applicant: Google LLC

Inventor： Dilek Hakkani-Tur ,  Abhinav Kumar Rastogi ,  Raghav Gupta

IPC: G10L15/18 ,  G06F40/117 ,  G06F40/284 ,  G06F40/35 ,  G06N3/02 ,  G10L15/16 ,  G10L15/22

CPC classification number: G10L15/1815 ,  G06F40/117 ,  G06F40/284 ,  G06F40/35 ,  G06N3/02 ,  G10L15/16 ,  G10L15/22

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for dialogue systems. A transcription of a user utterance is obtained. The transcription of the utterance is tokenized to identify multiple tokens for the utterance. Token-level utterance encodings corresponding to different tokens of the transcription are generated. A system action encoding from data indicating system actions previously performed by the dialogue system are generated. A dialogue context vector based on the utterance encoding and the system action encoding are generated. The token-level utterance encodings, the system action encoding, and the dialogue context vector are processed using a slot tagger to produce token-level output vectors. A limited set of candidate token classifications for the tokens of the user utterance are determined based on the token-level utterance encodings. A response for output is provided in response to the user utterance.

公开(公告)号：US20240221731A1

公开(公告)日：2024-07-04

申请号：US18148037

申请日：2022-12-29

Applicant: Google LLC

Inventor： Raghav Gupta ,  Yuan Cao ,  Abhinav Kumar Rastogi ,  Harrison J. Lee ,  Jeffrey Liangjie Zhao

IPC: G10L15/18 ,  G06F40/35 ,  G10L15/06

CPC classification number: G10L15/1815 ,  G06F40/35 ,  G10L15/063 ,  G10L2015/0633

Abstract: Example methods include determining an input prompt comprising an utterance labeled with a sequence of slot-value pairs, wherein the sequence of slot-value pairs indicates possible slots and values in the utterance, and wherein the utterance relates to a task. The methods include determining a contextual representation comprising a concatenation of a history of utterances exchanged between a user and a service agent. The utterances describe a context for the task. The methods include training, based on a concatenation of the input prompt and the contextual representation, a sequence-to-sequence language model to predict a sequence of dialog states for an input task. The sequence of dialog states comprise an assignment of values to slots for which the user has indicated a preference in dialog sequences. The methods include providing the trained sequence-to-sequence language model.

公开(公告)号：US11551159B2

公开(公告)日：2023-01-10

申请号：US16724604

申请日：2019-12-23

Applicant: Google LLC

Inventor： Abhinav Kumar Rastogi ,  Raghav Gupta ,  Xiaoxue Zang ,  Srinivas Kumar Sunkara ,  Pranav Khaitan

IPC: G06F40/20 ,  G06Q10/02 ,  G06N20/00 ,  G06Q50/30 ,  G06F9/54 ,  G06F16/242 ,  G06F16/21

Abstract: Generally, the present disclosure is directed to systems and methods for performing task-oriented response generation that can provide advantages for artificial intelligence systems or other computing systems that include natural language processing for interpreting user input. Example implementations can process natural language descriptions of various services that can be accessed by the system. In response to a natural language input, systems can identify relevant values for executing one of the service(s), based in part on comparing embedded representations of the natural language input and the natural language description using a machine learned model.

公开(公告)号：US20210192397A1

公开(公告)日：2021-06-24

申请号：US16724604

申请日：2019-12-23

Applicant: Google LLC

Inventor： Abhinav Kumar Rastogi ,  Raghav Gupta ,  Xiaoxue Zang ,  Srinivas Kumar Sunkara ,  Pranav Khaitan

IPC: G06Q10/02 ,  G06F9/54 ,  G06N20/00 ,  G06F40/20 ,  G06Q50/30 ,  G06F16/21 ,  G06F16/242

Abstract: Generally, the present disclosure is directed to systems and methods for performing task-oriented response generation that can provide advantages for artificial intelligence systems or other computing systems that include natural language processing for interpreting user input. Example implementations can process natural language descriptions of various services that can be accessed by the system. In response to a natural language input, systems can identify relevant values for executing one of the service(s), based in part on comparing embedded representations of the natural language input and the natural language description using a machine learned model.

公开(公告)号：US20250117232A1

公开(公告)日：2025-04-10

申请号：US18988564

申请日：2024-12-19

Applicant: Google LLC

Inventor： Srinivas Kumar Sunkara ,  Xiaoxue Zang ,  Ying Xu ,  Lijuan Liu ,  Nevan Holt Wichers ,  Gabriel Overholt Schubiner ,  Jindong Chen ,  Abhinav Kumar Rastogi ,  Blaise Aguera-Arcas ,  Zecheng He

IPC: G06F9/451

Abstract: Generally, the present disclosure is directed to user interface understanding. More particularly, the present disclosure relates to training and utilization of machine-learned models for user interface prediction and/or generation. A machine-learned interface prediction model can be pre-trained using a variety of pre-training tasks for eventual downstream task training and utilization (e.g., interface prediction, interface generation, etc.).

公开(公告)号：US12197930B2

公开(公告)日：2025-01-14

申请号：US18466267

申请日：2023-09-13

Applicant: Google LLC

Inventor： Srinivas Kumar Sunkara ,  Xiaoxue Zang ,  Ying Xu ,  Lijuan Liu ,  Nevan Holt Wichers ,  Gabriel Overholt Schubiner ,  Jindong Chen ,  Abhinav Kumar Rastogi ,  Blaise Aguera-Arcas ,  Zecheng He

IPC: G06F9/44 ,  G06F9/451 ,  G06F18/2135 ,  G06F18/214 ,  G06N3/045 ,  G06N20/00

Abstract: Generally, the present disclosure is directed to user interface understanding. More particularly, the present disclosure relates to training and utilization of machine-learned models for user interface prediction and/or generation. A machine-learned interface prediction model can be pre-trained using a variety of pre-training tasks for eventual downstream task training and utilization (e.g., interface prediction, interface generation, etc.).