公开(公告)号：US20230274090A1

公开(公告)日：2023-08-31

申请号：US18144707

申请日：2023-05-08

Applicant: GOOGLE LLC

Inventor： Keun Soo Yim ,  Kyung Yul Lim ,  Umesh Patil

IPC: G06F40/295 ,  G06F40/205 ,  G06F40/279 ,  G10L15/19

CPC classification number: G06F40/295 ,  G06F40/205 ,  G06F40/279 ,  G10L15/19

Abstract: Implementations are described herein for recommending actions based on entity or entity type. In various implementations, a partial free-form natural language input may be received from a user at an input component of a computing device. The partial free-form natural language input may identify an entity without identifying a responsive action and may be directed by the user to an automated assistant that operates at least in part on the computing device. The partial free-form natural language input may be analyzed to identify the entity. Based on the identified entity, a plurality or superset of candidate responsive actions may be identified, filtered, and/or ranked based on one or more signals. The automated assistant may then provide output that recommends one or more of the candidate responsive actions based on the ranking and/or filtering.

公开(公告)号：US10748541B2

公开(公告)日：2020-08-18

申请号：US16666780

申请日：2019-10-29

Applicant: Google LLC

Inventor： Gaurav Bhaya ,  Robert Stets ,  Umesh Patil

IPC: G10L15/00 ,  G10L15/22 ,  G06F3/16 ,  G06F40/279 ,  G10L15/18 ,  G10L15/08

Abstract: A system of multi-modal transmission of packetized data in a voice activated data packet based computer network environment is provided. A natural language processor component can parse an input audio signal to identify a request and a trigger keyword. Based on the input audio signal, a direct action application programming interface can generate a first action data structure, and a content selector component can select a content item. An interface management component can identify first and second candidate interfaces, and respective resource utilization values. The interface management component can select, based on the resource utilization values, the first candidate interface to present the content item. The interface management component can provide the first action data structure to the client computing device for rendering as audio output, and can transmit the content item converted for a first modality to deliver the content item for rendering from the selected interface.

公开(公告)号：US12147767B2

公开(公告)日：2024-11-19

申请号：US18144707

申请日：2023-05-08

Applicant: GOOGLE LLC

Inventor： Keun Soo Yim ,  Kyung Yul Lim ,  Umesh Patil

IPC: G06F40/295 ,  G06F40/205 ,  G06F40/279 ,  G10L15/19

Abstract: Implementations are described herein for recommending actions based on entity or entity type. In various implementations, a partial free-form natural language input may be received from a user at an input component of a computing device. The partial free-form natural language input may identify an entity without identifying a responsive action and may be directed by the user to an automated assistant that operates at least in part on the computing device. The partial free-form natural language input may be analyzed to identify the entity. Based on the identified entity, a plurality or superset of candidate responsive actions may be identified, filtered, and/or ranked based on one or more signals. The automated assistant may then provide output that recommends one or more of the candidate responsive actions based on the ranking and/or filtering.

公开(公告)号：US11790173B2

公开(公告)日：2023-10-17

申请号：US17082580

申请日：2020-10-28

Applicant: Google LLC

Inventor： Keun Soo Yim ,  Kyung Yul Lim ,  Umesh Patil

IPC: G06F40/295 ,  G06F40/205 ,  G06F40/279 ,  G10L15/19

CPC classification number: G06F40/295 ,  G06F40/205 ,  G06F40/279 ,  G10L15/19

Abstract: In various implementations described herein, a partial free-form natural language input may be received from a user at an input component of a computing device. The partial free-form natural language input may identify an entity without identifying a responsive action and may be directed by the user to an automated assistant that operates at least in part on the computing device. The partial free-form natural language input may be analyzed to identify the entity. Based on the identified entity, a plurality or superset of candidate responsive actions may be identified, filtered, and/or ranked based on one or more signals. The automated assistant may then provide output that recommends one or more of the candidate responsive actions based on the ranking and/or filtering.

公开(公告)号：US11705121B2

公开(公告)日：2023-07-18

申请号：US16936972

申请日：2020-07-23

Applicant: Google LLC

Inventor： Gaurav Bhaya ,  Robert Stets ,  Umesh Patil

IPC: G10L15/00 ,  G10L15/22 ,  G06F3/16 ,  G06F40/279 ,  G10L15/18 ,  G10L15/08

CPC classification number: G10L15/22 ,  G06F3/167 ,  G06F40/279 ,  G10L15/1822 ,  G10L2015/088 ,  G10L2015/223

Abstract: A system of multi-modal transmission of packetized data in a voice activated data packet based computer network environment is provided. A natural language processor component can parse an input audio signal to identify a request and a trigger keyword. Based on the input audio signal, a direct action application programming interface can generate a first action data structure, and a content selector component can select a content item. An interface management component can identify first and second candidate interfaces, and respective resource utilization values. The interface management component can select, based on the resource utilization values, the first candidate interface to present the content item. The interface management component can provide the first action data structure to the client computing device for rendering as audio output, and can transmit the content item converted for a first modality to deliver the content item for rendering from the selected interface.

公开(公告)号：US10593329B2

公开(公告)日：2020-03-17

申请号：US16039204

申请日：2018-07-18

Applicant: Google LLC

Inventor： Gaurav Bhaya ,  Robert Stets ,  Umesh Patil

IPC: G10L15/00 ,  G10L15/22 ,  G06F3/16 ,  G06F17/27 ,  G10L15/18 ,  G10L15/08

Abstract: A system of multi-modal transmission of packetized data in a voice activated data packet based computer network environment is provided. A natural language processor component can parse an input audio signal to identify a request and a trigger keyword. Based on the input audio signal, a direct action application programming interface can generate a first action data structure, and a content selector component can select a content item. An interface management component can identify first and second candidate interfaces, and respective resource utilization values. The interface management component can select, based on the resource utilization values, the first candidate interface to present the content item. The interface management component can provide the first action data structure to the client computing device for rendering as audio output, and can transmit the content item converted for a first modality to deliver the content item for rendering from the selected interface.

公开(公告)号：US20220129631A1

公开(公告)日：2022-04-28

申请号：US17082580

申请日：2020-10-28

Applicant: Google LLC

Inventor： Keun Soo Yim ,  Kyung Yul Lim ,  Umesh Patil

IPC: G06F40/295 ,  G06F40/205

Abstract: Implementations are described herein for recommending actions based on entity or entity type. In various implementations, a partial free-form natural language input may be received from a user at an input component of a computing device. The partial free-form natural language input may identify an entity without identifying a responsive action and may be directed by the user to an automated assistant that operates at least in part on the computing device. The partial free-form natural language input may be analyzed to identify the entity. Based on the identified entity, a plurality or superset of candidate responsive actions may be identified, filtered, and/or ranked based on one or more signals. The automated assistant may then provide output that recommends one or more of the candidate responsive actions based on the ranking and/or filtering.

公开(公告)号：US20200066274A1

公开(公告)日：2020-02-27

申请号：US16666780

申请日：2019-10-29

Applicant: Google LLC

Inventor： Gaurav Bhaya ,  Robert Stets ,  Umesh Patil

IPC: G10L15/22 ,  G06F17/27 ,  G06F3/16

Abstract: A system of multi-modal transmission of packetized data in a voice activated data packet based computer network environment is provided. A natural language processor component can parse an input audio signal to identify a request and a trigger keyword. Based on the input audio signal, a direct action application programming interface can generate a first action data structure, and a content selector component can select a content item. An interface management component can identify first and second candidate interfaces, and respective resource utilization values. The interface management component can select, based on the resource utilization values, the first candidate interface to present the content item. The interface management component can provide the first action data structure to the client computing device for rendering as audio output, and can transmit the content item converted for a first modality to deliver the content item for rendering from the selected interface.