US 11,893,324 B2
Ear-wearable device shell modeling
Tao Zhang, Eden Prairie, MN (US)
Assigned to Starkey Laboratories, Inc., Eden Prairie, MN (US)
Filed by Starkey Laboratories, Inc., Eden Prairie, MN (US)
Filed on Aug. 31, 2022, as Appl. No. 17/823,568.
Application 17/823,568 is a continuation of application No. 16/685,745, filed on Nov. 15, 2019, granted, now 11,481,530.
Claims priority of provisional application 62/768,208, filed on Nov. 16, 2018.
Prior Publication US 2022/0414292 A1, Dec. 29, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 30/20 (2020.01); G06N 20/00 (2019.01); H04R 1/10 (2006.01); G06F 119/18 (2020.01); G06N 3/084 (2023.01)
CPC G06F 30/20 (2020.01) [G06N 3/084 (2013.01); G06N 20/00 (2019.01); H04R 1/1058 (2013.01); G06F 2119/18 (2020.01); H04R 2201/105 (2013.01)] 23 Claims
OG exemplary drawing
 
1. A method comprising:
training a machine learning (ML) model to generate a representation of an ear-wearable device for a target ear canal, wherein training the ML model comprises:
receiving a data set that includes a representation of a historic ear impression and a corresponding target representation of an ear-wearable device;
providing the historic ear impression to the ML model, wherein the ML model is configured to output a generated representation of the ear-wearable device;
applying a cost function to the output of the ML model to determine a cost, wherein the cost function includes a weighted mean square error of deviations of the generated representation of the ear-wearable device and the target representation of the ear-wearable device; and
updating model parameters of the ML model based on the cost;
receiving, by at least one processor, a representation of a target ear canal of a patient; and
applying, by the at least one processor, the ML model to generate a representation of an ear-wearable device for the target ear canal, wherein input to the ML model includes the representation of the target ear canal of the patient.