US 12,346,783 B1
Techniques for automated image labeling
Beth Borghese, Columbus, OH (US); and Alireza Khakpour, Columbus, OH (US)
Assigned to The Huntington National Bank, Columbus, OH (US)
Filed by THE HUNTINGTON NATIONAL BANK, Columbus, OH (US)
Filed on Jan. 6, 2025, as Appl. No. 19/010,545.
Application 19/010,545 is a continuation of application No. 19/009,280, filed on Jan. 3, 2025.
Int. Cl. G06V 10/764 (2022.01); G06N 20/00 (2019.01); G06Q 40/12 (2023.01); G06V 10/774 (2022.01)
CPC G06N 20/00 (2019.01) [G06Q 40/12 (2013.12); G06V 10/764 (2022.01); G06V 10/774 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
detecting, by a computer system, a repository value change for an account;
receiving, by the computer system, image information representing an image from a computing device that is associated with the account, wherein the image includes a depiction of media of exchange;
generating, by the computer system, a feature vector for the image, wherein the feature vector is generated based at least in part on the image information, and wherein the feature vector comprises numeric properties of the image;
associating, by the computer system, the feature vector and the repository value change, thereby generating a labeled training datum;
adding, by the computer system, the labeled training datum to a set of labeled training data; and
using, by the computer system, the set of labeled training data to train a machine learning model, wherein the machine learning model is configured to receive as input the image information and output a quantity that corresponds to the media of exchange.