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：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.).

公开(公告)号：US20220382565A1

公开(公告)日：2022-12-01

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: G06F9/451 ,  G06N20/00 ,  G06N3/04 ,  G06K9/62

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.).