US 11,869,200 B2
ML model arrangement and method for evaluating motion patterns
Konstantin Mehl, Munich (DE); and Maximilian Strobel, Munich (DE)
Assigned to KAIA HEALTH SOFTWARE GMBH, Munich (DE)
Filed by Kaia Health Software GmbH, Munich (DE)
Filed on Aug. 26, 2022, as Appl. No. 17/896,924.
Application 17/896,924 is a continuation of application No. 16/735,132, filed on Jan. 6, 2020, granted, now 11,482,047.
Prior Publication US 2022/0415091 A1, Dec. 29, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06K 9/00 (2022.01); G06T 7/246 (2017.01); G06T 7/20 (2017.01); G06T 7/70 (2017.01); G06N 3/04 (2023.01); G06V 40/20 (2022.01); G06F 18/24 (2023.01); G06N 5/01 (2023.01); G06V 10/46 (2022.01); G06V 10/42 (2022.01)
CPC G06T 7/246 (2017.01) [G06F 18/24 (2023.01); G06N 3/04 (2013.01); G06N 5/01 (2023.01); G06T 7/20 (2013.01); G06T 7/70 (2017.01); G06V 10/42 (2022.01); G06V 10/462 (2022.01); G06V 40/23 (2022.01); G06T 2207/20084 (2013.01)] 24 Claims
OG exemplary drawing
 
1. A machine learning (ML) model arrangement configured for evaluating in a sequence of image data structures motion patterns of a physical exercise among a plurality of physical exercises, the evaluation being based on a set of key data elements for each image data structure of the sequence of image data structures, a key data element indicating a respective position of a landmark in the image data structure, the ML model arrangement comprising:
for each physical exercise among the plurality of physical exercises a second ML model dedicated to the physical exercise, each second ML model being a ML model configured for evaluating a corresponding specific motion pattern, each second ML model being configured for determining, based on input data comprising at least one of the key data elements for at least one image data structure or data derived therefrom, class labels for each image data structure, said class labels identifying at least one of: at least one motion phase of the specific motion pattern, at least one evaluation point of the specific motion pattern, wherein said evaluation point is a point in time.