US 12,437,111 B1
Token based communications for machine learning systems
Fredrick William Rodgers, Northlake, TX (US); and Michael P. Gout, San Antonio, TX (US)
Assigned to United Services Automobile Association (USAA), San Antonio, TX (US)
Filed by United Services Automobile Association (USAA), San Antonio, TX (US)
Filed on Nov. 8, 2023, as Appl. No. 18/504,466.
Application 18/504,466 is a continuation of application No. 16/129,310, filed on Sep. 12, 2018, granted, now 11,847,246.
Claims priority of provisional application 62/558,471, filed on Sep. 14, 2017.
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 30/00 (2023.01); G06F 18/214 (2023.01); G06F 21/62 (2013.01); G06N 5/04 (2023.01); G06N 20/00 (2019.01); H04L 9/32 (2006.01)
CPC G06F 21/6254 (2013.01) [G06F 18/214 (2023.01); G06N 5/04 (2013.01); G06N 20/00 (2019.01); H04L 9/3213 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A computer-implemented method performed by at least one processor, the method comprising:
generating, by at least one processor, for each of a plurality of events, a respective token that represents the event, wherein the respective token representing the event is encrypted using a private key associated with an organization and allows the organization to identify the event but does not allow a third party to identify the event;
for each event of the plurality of events:
identifying, by at least one processor, at least one entity associated with the event;
associating the respective token encrypted by the private key of the organization and representing the event with the at least one entity;
communicating, by at least one processor, the respective token and the at least one entity as label data for training of a machine learning system; and
associating the respective token encrypted by the private key and representing the event and the at least one entity with environmental data of the at least one entity to generate feature data for training of the machine learning system, wherein the environmental data indicates online activities taken by the at least one entity for a predetermined period of time before a date of the event;
combining the label data and the feature data to generate training data for training the machine learning system;
training the machine learning system on the training data comprising both (i) the label data and (ii) the feature data generated from the environmental data indicating online activities taken by the at least one entity; and
providing other environmental data indicating one or more other recent online activities of another entity as input to the trained machine learning system;
processing, using the trained machine learning system, the other environmental data indicating the one or more other recent online activities of another entity to generate an output that indicates that a particular event will likely occur within a predetermined time frame;
determining whether the particular event occurred based on subsequent observation data associated with the other entity;
providing feedback data to the machine learning system based on the determination, the feedback data comprising a positive example when the particular event occurred and a negative example when the particular event did not occur; and
retraining the machine learning system on the training data and the feedback data.