US 11,949,733 B2
Audio-based data structure generation
Gaurav Bhaya, Sunnyvale, CA (US); and Robert James Stets, Jr., Mountain View, CA (US)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on Feb. 4, 2021, as Appl. No. 17/167,720.
Application 17/167,720 is a continuation of application No. 15/395,689, filed on Dec. 30, 2016, granted, now 10,972,530.
Prior Publication US 2021/0160308 A1, May 27, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. H04L 67/10 (2022.01); G06F 40/174 (2020.01); G06F 40/186 (2020.01); G10L 15/18 (2013.01); G10L 15/22 (2006.01); H04L 67/53 (2022.01); G06Q 30/0242 (2023.01); G10L 15/08 (2006.01); G10L 15/30 (2013.01); H04L 67/01 (2022.01)
CPC H04L 67/10 (2013.01) [G06F 40/174 (2020.01); G06F 40/186 (2020.01); G10L 15/1822 (2013.01); G10L 15/22 (2013.01); H04L 67/53 (2022.05); G06Q 30/0242 (2013.01); G10L 2015/088 (2013.01); G10L 2015/223 (2013.01); G10L 15/30 (2013.01); H04L 67/01 (2022.05)] 20 Claims
OG exemplary drawing
 
1. A system, comprising:
a data processing system comprising memory and one or more processors to:
receive, via an interface of the data processing system, data packets comprising an input audio signal detected by a sensor of a client device that is remote from the data processing system;
parse the input audio signal to identify a request and a keyword;
identify a third-party provider based on the keyword;
select, from a database, a template based on the third-party provider;
populate a field in the template with a value received from the client device;
generate, based on the value, the keyword, the template, and responsive to the request, an action data structure for a service provided by the third-party provider remote from the data processing system and the client device;
select, based on the keyword and via a real-time content selection process, a content item provided by a second third-party provider different from the third-party provider, wherein the second third-party provider provides content selection criteria comprising a bid for the content item that is used by the real-time content selection process to select the content item;
transmit, to the client device, the content item for presentation by the client device via an output signal; and
transmit the action data structure to the third-party provider to cause the third-party provider to execute the action data structure to perform the service or invoke a conversational application programming interface to establish a communication session with the client device.