US 12,283,129 B2
Movement prediction machine learning models
Jon Kevin Muse, Thompsons Station, TN (US); Rama S. Ravindranathan, Edison, NJ (US); Marilyn L. Gordon, Cherry Hill, NJ (US); and Gregory J. Boss, Saginaw, MI (US)
Assigned to UnitedHealth Group Incorporated, Minnetonka, MN (US)
Filed by UnitedHealth Group Incorporated, Minnetonka, MN (US)
Filed on Nov. 1, 2021, as Appl. No. 17/453,059.
Prior Publication US 2023/0133858 A1, May 4, 2023
Int. Cl. G06V 40/20 (2022.01); G06F 1/16 (2006.01); G06N 20/00 (2019.01)
CPC G06V 40/25 (2022.01) [G06F 1/163 (2013.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
identifying, by one or more processors and based at least in part on an event data object that comprises sensor data describing user movement information associated with at least one foot of a user, one or more movement characteristics associated with the user;
determining, by the one or more processors, based at least in part on the one or more movement characteristics and using a movement prediction machine learning model, a movement prediction profile that comprises a plurality of movement feature sets associated with the at least one foot of the user, wherein:
(i) each movement feature set of the plurality of movement feature sets is associated with a respective stimulation protocol of a plurality of stimulation protocols, and
(ii) each stimulation protocol of the plurality of stimulation protocols is associated with one or more target stimulation zones; and
initiating, by the one or more processors, stimulation output to one or more electroactive polymers associated with the one or more target stimulation zones based at least in part on one or more stimulation protocols of the plurality of stimulation protocols for the one or more target stimulation zones as indicated by the movement prediction profile provided by the movement prediction machine learning model.