US 12,340,381 B2
Linking physical locations and online channels in a database
Allison Fenichel, Brooklyn, NY (US); Fan Feng, New York, NY (US); and Illiana Reed, San Francisco, CA (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on May 31, 2023, as Appl. No. 18/326,087.
Application 18/326,087 is a continuation of application No. 17/113,546, filed on Dec. 7, 2020, granted, now 11,687,954.
Prior Publication US 2023/0306450 A1, Sep. 28, 2023
Int. Cl. G06Q 30/0201 (2023.01); G06F 16/28 (2019.01); G06F 16/29 (2019.01); G06N 5/04 (2023.01); G06N 20/00 (2019.01); G06Q 20/34 (2012.01)
CPC G06Q 30/0201 (2013.01) [G06F 16/288 (2019.01); G06F 16/29 (2019.01); G06N 5/04 (2013.01); G06N 20/00 (2019.01); G06Q 20/34 (2013.01); G06Q 20/351 (2013.01); G06Q 20/348 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
performing, by a device, natural language processing to extract a set of features from unstructured data,
wherein the set of features is associated with information from a data set, and
wherein the information from the data set is associated with an online location;
iteratively training, by the device and based on the set of features, a machine learning model to generate a trained machine learning model,
wherein the machine learning model comprises at least one of a neural network or a support vector machine;
determining, by the device, that a score associated with an output of the trained machine learning model satisfies a threshold by applying the trained machine learning model to the information from the data set and inputting into the trained machine learning model a string similarity score determined between two or more features of the set of features,
wherein the score indicates a likelihood that the online location is associated with a brand; and
determining, based on the score, the brand associated with the online location;
adding information associated with the online location to a graph comprising links indicating that the online location and at least one physical location are associated with a same brand; and
generating, based on information associated with the links, one or more temporary credentials that are configured to enable completing one or more transactions at the online location and the at least one physical location,
wherein the one or more temporary credentials are used in completing one or more transactions at, at least one of the online location or the at least one physical location.