US 12,406,661 B2
Digital assistant control of applications
Kurt W. Piersol, San Jose, CA (US); Cedric Bray, Sunnyvale, CA (US); Keith S. Brisson, Sandy, UT (US); Helmut Garstenauer, Ternberg (AT); Timothy R. Oriol, San Jose, CA (US); Jessica J. Peck, Morgan Hill, CA (US); Lewis N. Perkins, Cambridge, MA (US); Luca Simonelli, Cambridge (GB); and Nathan D. Taylor, Scotts Valley, CA (US)
Assigned to Apple Inc., Cupertino, CA (US)
Filed by Apple Inc., Cupertino, CA (US)
Filed on Feb. 27, 2023, as Appl. No. 18/114,877.
Application 18/114,877 is a continuation of application No. PCT/US2021/048036, filed on Aug. 27, 2021.
Claims priority of provisional application 63/113,032, filed on Nov. 12, 2020.
Claims priority of provisional application 63/071,087, filed on Aug. 27, 2020.
Prior Publication US 2023/0206912 A1, Jun. 29, 2023
Int. Cl. G10L 15/22 (2006.01); G06F 3/16 (2006.01); G10L 15/06 (2013.01); G10L 15/18 (2013.01)
CPC G10L 15/1822 (2013.01) [G06F 3/167 (2013.01); G10L 15/063 (2013.01); G10L 15/22 (2013.01); G10L 2015/223 (2013.01)] 45 Claims
OG exemplary drawing
 
1. A first electronic device comprising:
one or more processors;
a memory; and
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for:
receiving an utterance from a user;
determining one or more representations of the utterance using a speech recognition model at least partially trained with data representing an application;
providing the one or more representations of the utterance to a plurality of natural language models, wherein a lightweight natural language model of the plurality of natural language models is associated with the application and a complex natural language model of the plurality of natural language models, wherein the complex natural language model is associated with the application and integrated with a digital assistant, and wherein the lightweight natural language model is registered when data representing the application is received from a second electronic device; and
determining a user intent of the utterance based on the at least one of the plurality of natural language models and a database including a plurality of actions and objects associated with the application.