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：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：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.