US 12,293,271 B1
Experimental content generation learning model for rapid machine learning in a data-constrained environment
Anthony Chong, San Francisco, CA (US); Corne Nagel, Agoura Hills, CA (US); and Samuel Owen, St. Louis, MO (US)
Assigned to StatSketch Inc., San Francisco, CA (US)
Filed by StatSketch Inc., San Francisco, CA (US)
Filed on Nov. 1, 2024, as Appl. No. 18/934,779.
Application 18/934,779 is a continuation of application No. 18/665,210, filed on May 15, 2024, granted, now 12,165,027.
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 20/00 (2019.01)
CPC G06N 20/00 (2019.01) 21 Claims
OG exemplary drawing
 
21. A computer program product comprising at least one non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising an executable portion configured to:
select a first rated content data object associated with a first experimental classification group for at least a first target client, wherein the first rated content data object is generated by a content generation model;
select a second rated content data object associated with a second experimental classification group for at least a second target client, wherein the second rated content data object is generated by the content generation model;
cause transmission of a first renderable content data object to the first target client,
wherein the first renderable content data object is based on the first rated content data object generated by the content generation model;
cause transmission of a second renderable content data object to the second target client,
wherein the second renderable content data object is based on the second rated content data object generated by the content generation model;
receive a first interaction data signal indicative of a first responsive action associated with the first target client and a second interaction data signal indicative of a second responsive action associated with the second target client; and
generate an updated content generation model based at least in part on a content generation learning model state, the content generation learning model state being based on the first responsive action and the second responsive action,
wherein the content generation learning model state comprises at least the first interaction data signal and second interaction data signal indicative of the respective responsive actions associated with the first target client and the second target client.