US 11,918,883 B2
Electronic device for providing feedback for specific movement using machine learning model and operating method thereof
Jong Min Kim, Seoul (KR)
Assigned to IdeaLink Inc., Seoul (KR)
Filed by IdeaLink Inc., Seoul (KR)
Filed on Oct. 19, 2021, as Appl. No. 17/505,108.
Claims priority of application No. 10-2020-0138146 (KR), filed on Oct. 23, 2020.
Prior Publication US 2022/0126190 A1, Apr. 28, 2022
Int. Cl. A63B 71/06 (2006.01); A63B 24/00 (2006.01); A63B 69/36 (2006.01); G06F 18/214 (2023.01); G06N 20/00 (2019.01); G06T 7/73 (2017.01); G06T 13/40 (2011.01); G06V 10/40 (2022.01); G06V 40/20 (2022.01)
CPC A63B 71/0622 (2013.01) [A63B 24/0003 (2013.01); A63B 69/3623 (2013.01); G06F 18/214 (2023.01); G06N 20/00 (2019.01); G06T 7/73 (2017.01); G06T 13/40 (2013.01); G06V 10/40 (2022.01); G06V 40/23 (2022.01); A63B 2071/0636 (2013.01); A63B 2220/05 (2013.01); A63B 2220/44 (2013.01); A63B 2220/807 (2013.01); G06T 2200/24 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/30196 (2013.01); G06T 2207/30221 (2013.01); G06T 2207/30241 (2013.01)] 5 Claims
OG exemplary drawing
 
1. An operating method of an electronic device, comprising:
receiving a program including a machine learning model generated by performing machine learning using, as training data, information on a plurality of skeletons associated with a specific motion of an expert and/or a professional athlete associated with a specific sport, information on a plurality of angular velocities associated with the specific motion, and/or a plurality of pieces of evaluated information associated with the specific motion, which are accumulated in a server, from the server, the plurality of pieces of evaluated information including information on evaluation levels for a plurality of respective features associated with the specific motion, and the machine learning model being set to output first evaluation levels for the plurality of features associated with the specific motion in response to input of at least one of information on a first skeleton or information on first angular velocity;
executing the program and receiving information on second angular velocity for the specific motion of a user of the electronic device from a swing practice device based on execution of the program;
photographing the specific motion of the user based on execution of the program and acquiring information on a second joint during the specific motion of the user based on a plurality of images acquired based on the photographing;
displaying a 3D graphical user interface (GUI) including a 3D animation object based on the information on the second angular velocity and/or the information on the second joint; and
displaying information on second evaluation levels on the plurality of features associated with the specific motion output from the machine learning model on the 3D GUI in response to input of the information on the second angular velocity and/or the information on the second joint to the machine learning model,
wherein the plurality of features includes at least one of a grip type, address back swing cocking, top, down swing, impact, follow swing, or follow top when the specific motion is a golf swing, and
wherein information on second evaluation levels on the plurality of features represents one of three or more levels for each of the plurality of features.