| CPC G10L 15/1822 (2013.01) [G06F 3/167 (2013.01); G06F 16/3322 (2019.01); G06F 16/3323 (2019.01); G10L 15/26 (2013.01); G10L 2015/223 (2013.01)] | 20 Claims |

|
1. A method implemented by one or more processors, the method comprising:
identifying content based on the content being recently visible on a computing device;
generating, based on the content and based on a first application being installed on the computing device, a first voice-based action query that can be spoken to initiate performance, by a first application, of a first computer-based action that is particularized to the content;
generating, based on a second application being installed on the computing device, a second voice-based action query that can be spoken to initiate performance, by a second application, of a second computer-based action that is particularized to the content;
determining that an input to initiate providing of a voice-based action query has been provided via the computing device, wherein the input to initiate providing of a voice-based query is a selection of a voice query interface element, a spoken phrase, or performing a gesture in view of a camera of the computing device;
in response to determining that the input to initiate providing of a voice-based action query has been provided via the computing device:
causing the first voice-based action query to be visually presented at the computing device, and
causing the second voice-based action query to be visually presented at the computing device along with the first voice-based action query; and
in response to the user speaking the provided first voice-based action query:
causing the first application to perform the first computer-based action.
|