US 12,293,269 B2
Curation and provision of digital content
Patrick Soon-Shiong, Los Angeles, CA (US)
Assigned to Nant Holdings IP, LLC, Culver City, CA (US)
Filed by Nant Holdings IP, LLC, Culver City, CA (US)
Filed on Jun. 24, 2024, as Appl. No. 18/751,969.
Application 18/751,969 is a continuation of application No. 18/221,573, filed on Jul. 13, 2023, granted, now 12,061,653.
Application 18/221,573 is a continuation of application No. 16/678,212, filed on Nov. 8, 2019, granted, now 11,748,417, issued on Sep. 5, 2023.
Claims priority of provisional application 62/759,954, filed on Nov. 12, 2018.
Prior Publication US 2024/0346085 A1, Oct. 17, 2024
Int. Cl. G06N 20/00 (2019.01); G06F 17/00 (2019.01); G06F 18/24 (2023.01); G06N 5/048 (2023.01)
CPC G06N 20/00 (2019.01) [G06F 17/00 (2013.01); G06F 18/24 (2023.01); G06N 5/048 (2013.01)] 22 Claims
OG exemplary drawing
 
1. A computer-based curation system comprising:
a wearable heart rate sensor configured to obtain heart rate data corresponding to a person;
at least one non-transitory computer readable memory storing software instructions; and
at least one processor coupled with the at least one non-transitory computer readable memory and that performs the following operations upon execution of the software instructions:
accessing electrocardiogram structured content comprising attributes adhering to a namespace, wherein the electrocardiogram structured content includes heart rate data obtained via the wearable heart rate sensor and corresponding to the person;
accessing event data comprising attributes adhering to the namespace, the event data characterizing an event associated with the person;
identifying curated content comprising an alert related to the electrocardiogram structured content and related to a doctor, wherein each of the electrocardiogram structured content, the event data and the curated content comprise one or more digital data structures stored in the at least one non-transitory computer readable memory;
predicting, via a trained prediction model, from the electrocardiogram structured content attributes and the event data attributes, a point-in-time when the alert would be relevant, wherein the predicted relevant point-in-time is prior to occurrence of the event associated with the person, the trained prediction model comprises a machine learning model trained to map the electrocardiogram structured content attributes to the event data attributes to generate a relevancy metric for the electrocardiogram structured content attributes; and
causing the alert to be rendered on a device related to the doctor near or at the point-in-time, prior to occurrence of the event associated with the person.