| CPC G16H 20/70 (2018.01) [G06N 3/044 (2023.01); G06N 3/08 (2013.01)] | 19 Claims |
|
1. A method of analyzing user feedback in response to a cognition training program, the method comprising:
training, by a processor, at least one machine learning algorithm with a predefined dataset to predict a training success rate of a particular user, wherein the predefined dataset comprises previously received user feedback for users with known characteristics, said feedback representing a user response to a displayed scenario;
receiving, by the processor, new user feedback representing a new user response to the displayed scenario;
determining, by the processor, a prediction of a training success rate of the new user with the at least one machine learning algorithm based on the received new user feedback;
modifying, by the processor, the cognition training program in accordance with the predicted training success rate of the new user;
iteratively retraining the at least one machine learning algorithm with the received new user feedback to improve prediction of the training success rate, using reinforcement learning;
determining, by the processor, a behavior pattern of the new user in response to the modified cognition training program;
determining, by the processor, reduction of the training success rate, based on the determined behavior pattern; and
issuing an alert indicating cognitive decline, when the reduction of the training success rate exceeds a predefined threshold.
|