US 12,147,767 B2
Recommending action(s) based on entity or entity type
Keun Soo Yim, San Jose, CA (US); Kyung Yul Lim, Santa Clara, CA (US); and Umesh Patil, Cupertino, CA (US)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by GOOGLE LLC, Mountain View, CA (US)
Filed on May 8, 2023, as Appl. No. 18/144,707.
Application 18/144,707 is a continuation of application No. 17/082,580, filed on Oct. 28, 2020, granted, now 11,790,173.
Claims priority of provisional application 63/104,400, filed on Oct. 22, 2020.
Prior Publication US 2023/0274090 A1, Aug. 31, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 40/295 (2020.01); G06F 40/205 (2020.01); G06F 40/279 (2020.01); G10L 15/19 (2013.01)
CPC G06F 40/295 (2020.01) [G06F 40/205 (2020.01); G06F 40/279 (2020.01); G10L 15/19 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method using one or more processors, comprising:
receiving a partial free-form natural language input from a user at an input component of a computing device, wherein the partial free-form natural language input identifies an entity without identifying a responsive action and is directed by the user to an automated assistant that operates at least in part on the computing device;
performing named entity recognition on the partial free-form natural language input to identify an entity type of the entity;
based on the identified entity type, identifying a plurality of candidate responsive actions;
based on a state of a given application executing at least in part on the computing device, automatically filtering, from consideration, one or more of the plurality of candidate responsive actions, wherein the one or more filtered candidate responsive actions include the given application or another application of a same application type as the given application;
causing the automated assistant to provide output that recommends one or more of the candidate responsive actions that remain after the filtering; and
in response to user input at the computing device selecting one of the recommended one or more candidate applications, causing the computing device to execute the selected one of the recommended one or more candidate applications.