US 12,008,092 B2
Supervised and unsupervised techniques for motion classification
Lucas Allen Budman, Denver, CO (US); Amitabh Agrawal, Superior, CO (US); and Andrew Weber Spott, Boulder, CO (US)
Assigned to TruU, Inc., Palo Alto, CA (US)
Filed by TruU, Inc., Palo Alto, CA (US)
Filed on Aug. 9, 2022, as Appl. No. 17/884,456.
Application 17/884,456 is a continuation of application No. 16/858,543, filed on Apr. 24, 2020, granted, now 11,455,383.
Claims priority of provisional application 62/840,876, filed on Apr. 30, 2019.
Prior Publication US 2022/0382845 A1, Dec. 1, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 21/32 (2013.01); G06F 18/23213 (2023.01); G06N 20/00 (2019.01); G06T 17/00 (2006.01); G06V 10/764 (2022.01); G06V 40/10 (2022.01); G06V 40/20 (2022.01)
CPC G06F 21/32 (2013.01) [G06F 18/23213 (2023.01); G06N 20/00 (2019.01); G06T 17/00 (2013.01); G06V 10/764 (2022.01); G06V 40/10 (2022.01); G06V 40/20 (2022.01); G06V 40/23 (2022.01)] 22 Claims
OG exemplary drawing
 
1. A non-transitory computer-readable medium comprising stored computer-readable instructions, the instructions when executed by a processor, cause the processor to:
receive, from at least one sensor, a sequence of motion data characterizing movements performed by a target user, the sequence of motion data encoded as a feature vector representation of the motion data;
input the feature vector representation of the motion data into a machine-learned model trained based on manually labeled groups of entries of a training set of motion data, each labeled group of the training set representative of a mapping from the entries in the labeled group to a movement;
identify, by the machine-learned model, a movement represented by the feature vector representation of the motion data, the identification determining a label to the feature vector describing the movement represented by the feature vector; and
generate a labeled representation of the sequence of motion data comprising the label describing the movement represented by the feature vector representation of the motion data and identifying a portion of the sequence of motion data corresponding to the identified movement.