US 11,704,592 B2
Machine-learning based gesture recognition
Keith P. Avery, Seattle, WA (US); Jamil Dhanani, San Francisco, CA (US); Harveen Kaur, Santa Clara, CA (US); Varun Maudgalya, Sunnyvale, CA (US); Timothy S. Paek, Mercer Island, WA (US); Dmytro Rudchenko, Bellevue, WA (US); Brandt M. Westing, Seattle, WA (US); and Minwoo Jeong, Sammamish, WA (US)
Assigned to Apple Inc., Cupertino, CA (US)
Filed by Apple Inc., Cupertino, CA (US)
Filed on Jul. 23, 2020, as Appl. No. 16/937,479.
Claims priority of provisional application 62/878,695, filed on Jul. 25, 2019.
Prior Publication US 2021/0027199 A1, Jan. 28, 2021
Int. Cl. G06F 3/0488 (2022.01); G06F 3/01 (2006.01); G06F 3/0481 (2022.01); G06N 20/00 (2019.01); G06F 3/04883 (2022.01); H04R 3/04 (2006.01); G06N 3/08 (2023.01)
CPC G06N 20/00 (2019.01) [G06F 3/011 (2013.01); G06F 3/017 (2013.01); G06F 3/04883 (2013.01); H04R 3/04 (2013.01); G06N 3/08 (2013.01); H04R 2430/01 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, from a first non-touch sensor of a device, first sensor output of a first type;
receiving, from a second non-touch sensor of the device, second sensor output of a second type that differs from the first type;
providing the first sensor output and the second sensor output as concurrent inputs to a machine learning model, the machine learning model having been previously trained to output a predicted gesture based on both sensor output of the first type and sensor output of the second type;
providing a predicted gesture on a surface of the device based on an output from the machine learning model, the output generated in response to the providing of both the first sensor output and the second sensor output as concurrent inputs to the machine learning model; and
adjusting an audio output level of the device based on the predicted gesture on the surface of the device, wherein the device comprises an audio output device.