US 12,213,796 B2
Aroma training using virtual reality
Derrick Anthony Martin, II, Brooklyn, NY (US); Alex M. Kass, Palo Alto, CA (US); Marc Carrel-Billiard, Vence (FR); and Alexandria Emily Pabst, Merced, CA (US)
Assigned to Accenture Global Solutions Limited, Dublin (IE)
Filed by Accenture Global Solutions Limited, Dublin (IE)
Filed on Jun. 17, 2022, as Appl. No. 17/843,442.
Claims priority of provisional application 63/286,744, filed on Dec. 7, 2021.
Prior Publication US 2023/0172524 A1, Jun. 8, 2023
Int. Cl. A61B 5/00 (2006.01); G06F 3/01 (2006.01); G06F 3/04842 (2022.01)
CPC A61B 5/4011 (2013.01) [G06F 3/015 (2013.01); G06F 3/04842 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A computer-implemented method for aroma training, comprising:
generating training data sets for training a machine learning model to identify one of a plurality of objects to present after initially presenting another one of the plurality of objects to incrementally trigger increased user perception of aromas by users that are suffering from olfactory disfunction, the training data sets each including data indicating (i) another one of the plurality of objects that was initially presented to one of the users, (ii) one of the plurality of objects that were presented to the one of the users after initially presenting the another one of the plurality of objects, (iii) and electrical brain activity data of the one of the users that reflects an extent to which presentation of the aromas of the one of the plurality of objects and the another one of the plurality of objects created fluctuations in electrical activity of a brain of the one of the users when the one of the plurality of objects and the another one of the plurality of object were presented;
training the machine learning model in such a way that the aromas of the another one of the plurality of objects is followed in sequence by the aromas of the one of the plurality of objects, to predict objects from a plurality of objects based on the aromas;
transmitting, to a client device, a first data indicating a first object from the plurality of objects and instructions to disperse a first aroma associated with the first object for presentation to a user of the client device;
receiving, from the client device, a user response that was provided by the user in response to the presentation of the first object and the first aroma, the user response comprising electrical brain activity data of the user that reflects an extent to which an aroma of the first object was perceived;
storing the user response in a database as an instance of a training dataset for the user;
identifying, based on the user response, a second object from the plurality of objects using the trained machine learning model;
determining the aroma of the second object based on the electrical brain activity data of the one of the users; and
transmitting, to the client device, the second data indicating the second object and instructions to disperse the second aroma for presentation to the user of the client device.