US 12,266,449 B2
System and method for text-based conversation with a user, using machine learning
Mark McInnis, Bedford, MA (US)
Filed by RETAIN HEALTH, INC, Bedford, MA (US)
Filed on Mar. 8, 2022, as Appl. No. 17/689,136.
Application 17/689,136 is a continuation in part of application No. 17/319,138, filed on May 13, 2021, granted, now 11,275,903.
Prior Publication US 2022/0367061 A1, Nov. 17, 2022
Int. Cl. G16H 50/30 (2018.01); G16H 40/67 (2018.01); G16H 50/20 (2018.01); G16H 80/00 (2018.01)
CPC G16H 50/30 (2018.01) [G16H 40/67 (2018.01); G16H 50/20 (2018.01); G16H 80/00 (2018.01)] 16 Claims
OG exemplary drawing
 
1. A method of risk score comparison and analysis using wearable devices, the method comprising:
receiving, at a computing device, user data associated with a first user from a wearable device, wherein the wearable device comprises a sensor that extracts the user data from the first user;
generating, using the computing device, a first risk score as a function of the user data;
matching with a trained classifier, using the computing device, the first user to a second user having a second risk score as a function of user data associated with the second user, wherein the trained classifier is trained as a function of a machine learning algorithm and training data comprising examples user data correlated to examples of risk score data, wherein matching the users comprises:
extracting, from the first risk score, a plurality of first risk score content elements;
extracting, from the second risk score, a plurality of second risk score content elements; and
matching the plurality of first risk score content elements to the plurality of second risk score content elements; and
receiving, using the computing device, at least a feature associated with a user's condition;
classifying, using the computing device, at least an intervention class, wherein the at least an intervention class is classified using probabilistic outputs of a machine learning model based on the received feature;
optimizing, using the computing device, the classified at least an intervention class, wherein the classified at least an intervention class is optimized to best address the user's condition, wherein the optimization employs a greedy algorithm to determine a selection of the at least an intervention class such that a first risk score associated with the selection is optimized;
interfacing, using the computing device and the wearable device, conversationally with first user, wherein interfacing conversationally with the user comprises:
generating text as a function of the first risk score being matched to the second risk score and the optimized at least an intervention class; and
communicating the text to the first user via the wearable device.