US 12,086,807 B2
User authentication based on account transaction information in text field
Tyler Maiman, Melville, NY (US); David Septimus, New York, NY (US); Samuel Rapowitz, Roswell, GA (US); Jenny Melendez, Falls Church, VA (US); Viraj Chaudhary, Katy, TX (US); and Joshua Edwards, Philadelphia, PA (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Aug. 31, 2023, as Appl. No. 18/240,736.
Application 18/240,736 is a continuation of application No. 17/387,683, filed on Jul. 28, 2021, granted, now 11,775,973.
Prior Publication US 2024/0062211 A1, Feb. 22, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 20/40 (2012.01); G06F 18/214 (2023.01); G06N 20/20 (2019.01)
CPC G06Q 20/4015 (2020.05) [G06F 18/214 (2023.01); G06N 20/20 (2019.01); G06Q 20/4012 (2013.01); G06Q 20/405 (2013.01); G06Q 20/4097 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
determining based on a geographical location associated with a user device, training data indicating a plurality of merchants and popularity of each of the plurality of merchants in the geographical location:
generating, based on the training data, a trained machine learning model by training a machine learning model implemented using an artificial neural network comprising a plurality of nodes to predict a guessability of an input merchant, wherein the training the machine learning model comprises adjusting, based on the training data, one or more weights corresponding to one or more of the plurality of nodes of the artificial neural network;
receiving transaction data associated with an account, wherein the transaction data indicates a plurality of transactions, and wherein each transaction of the plurality of transactions is associated with a merchant;
identifying at least one merchant by processing text data of a user response to an authentication question; and
based on determining that at least one transaction of the plurality of transactions is associated with the at least one merchant:
providing, to the trained machine learning model, input data indicating the at least one merchant;
receiving, from the trained machine learning model and in response to the input data, output data indicating a guessability of the at least one merchant;
generating, based on the output data, an authentication score; and
providing, to the user device and based on the authentication score, access to the account.