US 11,714,915 B2
Data aggregation based on disparate local processing of requests
Jack Stockert, Los Altos, CA (US); and Charles Aunger, Hayward, CA (US)
Assigned to Health2047, Inc., Menlo Park, CA (US)
Filed by Health2047, Inc., Menlo Park, CA (US)
Filed on Jan. 31, 2020, as Appl. No. 16/779,367.
Claims priority of provisional application 62/800,209, filed on Feb. 1, 2019.
Prior Publication US 2020/0250336 A1, Aug. 6, 2020
Int. Cl. G16H 50/20 (2018.01); G06F 21/62 (2013.01); G16H 50/70 (2018.01); G06N 3/08 (2023.01); G16H 15/00 (2018.01); G16H 10/60 (2018.01)
CPC G06F 21/6245 (2013.01) [G06N 3/08 (2013.01); G16H 10/60 (2018.01); G16H 15/00 (2018.01); G16H 50/70 (2018.01)] 28 Claims
OG exemplary drawing
 
1. A computer system comprising one or more computer processors configured to execute software code to perform operations comprising:
receiving a request associated with analyzing medical data, the request specifying one or more constraints and information defining one or more machine learning models to be trained;
accessing index information, and identifying one or more medical providers storing medical data responsive to the request, wherein the computer system does not have access to the medical data;
instructing, for each medical provider, compute systems controlled by the one or more medical providers to perform the request, wherein the information defining the one or more machine models is transmitted to the one or more medical providers;
receiving, from the medical providers, parameters associated with training the machine learning model, the parameters including at least trained weights and biases associated with layers forming the machine learning model; and
providing the parameters in response to the request.