公开(公告)号：US12287827B2

公开(公告)日：2025-04-29

申请号：US18230457

申请日：2023-08-04

Applicant: GOOGLE LLC

Inventor： Diana Avram ,  Mugurel-Ionut Andreica ,  Alice Liang ,  Andrea D'olimpio ,  Cliff Kuang ,  Andre Elisseeff ,  Dana Ritter ,  Florian Hasler ,  Radu Voroneanu

IPC: G06F16/638 ,  G06F16/635 ,  H04L67/50

Abstract: Implementations relate to identifying actions performed by a user while the user is interacting with multiple applications and providing a routine suggestion to the user based on the identified actions. While a user is interacting with one or more applications, the user actions are determined. The user actions are compared to one or more template routines and a template routine is selected that matches the actions of the user and provided to the user as a suggested routine. The suggested routine can be implemented by an automated assistant to perform the actions of the template by providing a corresponding command.

公开(公告)号：US12271742B2

公开(公告)日：2025-04-08

申请号：US18230561

申请日：2023-08-04

Applicant: GOOGLE LLC

Inventor： Cliff Kuang ,  Diana Avram ,  Mugurel-Ionut Andreica ,  Radu Voroneanu ,  Sneha Ashok ,  Deepak Goyal ,  Kyunghoon Lee ,  Alice Liang ,  Dana Ritter ,  Adam Coimbra ,  Anton Berezin ,  Andre Elisseeff

IPC: G06F9/451 ,  G06F3/0482 ,  G06F3/0484

Abstract: Implementations relate to determining a rendering type for an application that is executing automatically. Based on user interactions with an application that is associated with specified input from the user while the user is interacting with the application, a confidence metric is generated for each specified input and a rendering type is determined based on the confidence metrics. Subsequently, when the user requests that a sequence of actions be performed, the application will be displayed according to the rendering type.

公开(公告)号：US20250045327A1

公开(公告)日：2025-02-06

申请号：US18230457

申请日：2023-08-04

Applicant: GOOGLE LLC

Inventor： Diana Avram ,  Mugurel-Ionut Andreica ,  Alice Liang ,  Andrea D'olimpio ,  Cliff Kuang ,  Andre Elisseeff ,  Dana Ritter ,  Florian Hasler ,  Radu Voroneanu

IPC: G06F16/638 ,  G06F16/635 ,  H04L67/50

Abstract: Implementations relate to identifying actions performed by a user while the user is interacting with multiple applications and providing a routine suggestion to the user based on the identified actions. While a user is interacting with one or more applications, the user actions are determined. The user actions are compared to one or more template routines and a template routine is selected that matches the actions of the user and provided to the user as a suggested routine. The suggested routine can be implemented by an automated assistant to perform the actions of the template by providing a corresponding command.

公开(公告)号：US20250045079A1

公开(公告)日：2025-02-06

申请号：US18230566

申请日：2023-08-04

Applicant: GOOGLE LLC

Inventor： Diana Avram ,  Mugurel-Ionut Andreica ,  Andrea D'olimpio ,  Bogdan Prisacari ,  Felix Weissenberger ,  Andre Elisseeff ,  Cliff Kuang ,  Dana Ritter ,  Adam Coimbra

IPC: G06F9/451

Abstract: Implementations relate to identifying actions performed by a user while the user is interacting with an application and providing a routine suggestion to the user based on the identified actions. While a user is interacting with an application, screenshots of the user actions are captured and processed to determine what actions were performed by the user. The identified actions are compared to one or more template routines and a template routine is selected that matches the actions and intent of the user and provided to the user as a suggested routine. The suggested routine can be implemented by an automated assistant to perform the actions of the template by providing a corresponding command.

公开(公告)号：US20250045071A1

公开(公告)日：2025-02-06

申请号：US18230561

申请日：2023-08-04

Applicant: GOOGLE LLC

Inventor： Cliff Kuang ,  Diana Avram ,  Mugurel-Ionut Andreica ,  Radu Voroneanu ,  Sneha Ashok ,  Deepak Goyal ,  Kyunghoon Lee ,  Alice Liang ,  Dana Ritter ,  Adam Coimbra ,  Anton Berezin ,  Andre Elisseeff

IPC: G06F9/451 ,  G06F3/0482 ,  G06F3/0484

Abstract: Implementations relate to determining a rendering type for an application that is executing automatically. Based on user interactions with an application that is associated with specified input from the user while the user is interacting with the application, a confidence metric is generated for each specified input and a rendering type is determined based on the confidence metrics. Subsequently, when the user requests that a sequence of actions be performed, the application will be displayed according to the rendering type.

公开(公告)号：US20230050054A1

公开(公告)日：2023-02-16

申请号：US17974086

申请日：2022-10-26

Applicant: GOOGLE LLC

Inventor： Gökhan Bakir ,  Andre Elisseeff ,  Torsten Marek ,  João Paulo Pagaime da Silva ,  Mathias Carlen ,  Dana Ritter ,  Lukasz Suder ,  Ernest Galbrun ,  Matthew Stokes ,  Marcin Nowak-Przygodzki ,  Mugurel-Ionut Andreica ,  Marius Dumitran

IPC: G06F16/9535 ,  G06F16/9032

Abstract: Implementations are described herein for analyzing existing interactive web sites to facilitate automatic engagement with those web sites, e.g., by automated assistants or via other user interfaces, with minimal effort from the hosts of those websites. For example, in various implementations, techniques described herein may be used to abstract, validate, maintain, generalize, extend and/or distribute individual actions and “traces” of actions that are useable to navigate through various interactive websites. Additionally, techniques are described herein for leveraging these actions and/or traces to automate aspects of interaction with a third party website. For example, in some implementations, techniques described herein may enable users to engage with an automated assistant (via a spoken or typed dialog session) to interact with the third party website without requiring the user to visually interact with the third party web site directly and without requiring the third party to implement their own third party agent.

公开(公告)号：US20240232272A1

公开(公告)日：2024-07-11

申请号：US18612174

申请日：2024-03-21

Applicant: GOOGLE LLC

Inventor： Gökhan Bakir ,  Andre Elisseeff ,  Torsten Marek ,  João Paulo Pagaime da Silva ,  Mathias Carlen ,  Dana Ritter ,  Lukasz Suder ,  Ernest Galbrun ,  Matthew Stokes ,  Marcin Nowak-Przygodzki ,  Mugurel-Ionut Andreica ,  Marius Dumitran

IPC: G06F16/9535 ,  G06F16/9032

CPC classification number: G06F16/9535 ,  G06F16/90332

Abstract: Implementations are described herein for analyzing existing interactive web sites to facilitate automatic engagement with those web sites, e.g., by automated assistants or via other user interfaces, with minimal effort from the hosts of those websites. For example, in various implementations, techniques described herein may be used to abstract, validate, maintain, generalize, extend and/or distribute individual actions and “traces” of actions that are useable to navigate through various interactive websites. Additionally, techniques are described herein for leveraging these actions and/or traces to automate aspects of interaction with a third party website. For example, in some implementations, techniques described herein may enable users to engage with an automated assistant (via a spoken or typed dialog session) to interact with the third party website without requiring the user to visually interact with the third party web site directly and without requiring the third party to implement their own third party agent.

公开(公告)号：US11971936B2

公开(公告)日：2024-04-30

申请号：US17974086

申请日：2022-10-26

Applicant: GOOGLE LLC

Inventor： Gökhan Bakir ,  Andre Elisseeff ,  Torsten Marek ,  João Paulo Pagaime da Silva ,  Mathias Carlen ,  Dana Ritter ,  Lukasz Suder ,  Ernest Galbrun ,  Matthew Stokes ,  Marcin Nowak-Przygodzki ,  Mugurel-Ionut Andreica ,  Marius Dumitran

IPC: G06F16/00 ,  G06F16/9032 ,  G06F16/9535

CPC classification number: G06F16/9535 ,  G06F16/90332

Abstract: Implementations are described herein for analyzing existing interactive web sites to facilitate automatic engagement with those web sites, e.g., by automated assistants or via other user interfaces, with minimal effort from the hosts of those websites. For example, in various implementations, techniques described herein may be used to extract, validate, maintain, generalize, extend and/or distribute individual actions and “traces” of actions that are useable to navigate through various interactive websites. Additionally, techniques are described herein for leveraging these actions and/or traces to automate aspects of interaction with a third party website. For example, in some implementations, techniques described herein may enable users to engage with an automated assistant (via a spoken or typed dialog session) to interact with the third party website without requiring the user to visually interact with the third party web site directly and without requiring the third party to implement their own third party agent.

公开(公告)号：US11487832B2

公开(公告)日：2022-11-01

申请号：US16619777

申请日：2019-05-09

Applicant: Google LLC

Inventor： Gökhan Bakir ,  Andre Elisseeff ,  Torsten Marek ,  João Paulo Pagaime da Silva ,  Mathias Carlen ,  Dana Ritter ,  Lukasz Suder ,  Ernest Galbrun ,  Matthew Stokes ,  Marcin Nowak-Przygodzki ,  Mugurel-Ionut Andreica ,  Marius Dumitran

IPC: G06F16/00 ,  G06F16/9535 ,  G06F16/9032

Abstract: Implementations are described herein for analyzing existing interactive web sites to facilitate automatic engagement with those web sites, e.g., by automated assistants or via other user interfaces, with minimal effort from the hosts of those websites. For example, in various implementations, techniques described herein may be used to abstract, validate, maintain, generalize, extend and/or distribute individual actions and “traces” of actions that are useable to navigate through various interactive websites. Additionally, techniques are described herein for leveraging these actions and/or traces to automate aspects of interaction with a third party website. For example, in some implementations, techniques described herein may enable users to engage with an automated assistant (via a spoken or typed dialog session) to interact with the third party web site without requiring the user to visually interact with the third party web site directly and without requiring the third party to implement their own third party agent.

公开(公告)号：US20200342039A1

公开(公告)日：2020-10-29

申请号：US16619777

申请日：2019-05-09

Applicant: Google LLC

Inventor： Gökhan Bakir ,  Andre Elisseeff ,  Torsten Marek ,  João Paulo Pagaime da Silva ,  Mathias Carlen ,  Dana Ritter ,  Lukasz Suder ,  Ernest Galbrun ,  Matthew Stokes

IPC: G06F16/9535 ,  G06F16/9032

Abstract: Implementations are described herein for analyzing existing interactive web sites to facilitate automatic engagement with those web sites, e.g., by automated assistants or via other user interfaces, with minimal effort from the hosts of those websites. For example, in various implementations, techniques described herein may be used to abstract, validate, maintain, generalize, extend and/or distribute individual actions and “traces” of actions that are useable to navigate through various interactive websites. Additionally, techniques are described herein for leveraging these actions and/or traces to automate aspects of interaction with a third party website. For example, in some implementations, techniques described herein may enable users to engage with an automated assistant (via a spoken or typed dialog session) to interact with the third party web site without requiring the user to visually interact with the third party