US 12,475,478 B2
Computer-based systems involving machine learning associated with generation of recommended content and methods of use thereof
Jagdeep Kalra, Herndon, VA (US); Kamalesh Jayaraman, Fairfax, VA (US); and David Tobey, Brooklyn, NY (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Feb. 12, 2024, as Appl. No. 18/439,558.
Application 18/439,558 is a continuation of application No. 17/245,742, filed on Apr. 30, 2021, granted, now 11,900,407.
Prior Publication US 2024/0249307 A1, Jul. 25, 2024
Int. Cl. G06Q 30/0211 (2023.01); G06F 40/30 (2020.01); G06N 20/00 (2019.01)
CPC G06Q 30/0211 (2013.01) [G06F 40/30 (2020.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
receiving, by at least one processor, at least one first message from a remote computing device over a computer network;
automatically extracting, by the at least one processor, a first property by analyzing the at least one first message;
automatically mapping, by the at least one processor via an application programming interface (API), the first property to a content repository stored in a remote content engine to generate a suggested content;
automatically inputting, by the at least one processor, the at least one first message and the suggested content to a machine learning model to generate at least one first image;
wherein the machine learning model is configured to utilize encoded historical images to generate the at least one first image;
automatically modifying, by the at least one processor, at least one user interface to insert the at least one first image into a predetermined banner portion of the at least one user interface, wherein the at least one user interface with the at least one first image is configured to be displayed at the remote computing device;
automatically causing, by the at least one processor, the remote computing device to track at least one action performed to the at least one first image to generate tracking data;
receiving, by the at least one processor, the tracking data from the remote computing device;
updating, by the at least one processor, a dataset with the tracking data; and
providing, by the at least one processor, the updated dataset to re-train the machine learning model.