US 11,921,692 B1
Computer-based systems configured for automatically updating a database based on an initiation of a dynamic machine-learning verification and methods of use thereof
Shabnam Kousha, Washington, DC (US); Joshua Edwards, Philadelphia, PA (US); Lin Ni Lisa Cheng, Great Neck, NY (US); Tyler Maiman, Melville, NY (US); and Asher Smith-Rose, Midlothian, VA (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Sep. 16, 2022, as Appl. No. 17/946,926.
Int. Cl. G06F 16/23 (2019.01); G06F 16/2455 (2019.01)
CPC G06F 16/23 (2019.01) [G06F 16/2455 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving, by at least one processor, input data from at least one external data aggregator at a predetermined interval of time associated with a collection of input data, wherein the input data is telecommunication data;
utilizing, by the at least one processor, at least one trained machine learning algorithm to generate a database of known queries associated with a plurality of users based on an analysis of the input data received from the at least one external data aggregator, wherein the analysis of the input data provides additional information associated with a plurality of indicative markers;
receiving, by the at least one processor, subsequent input data from the at least one external aggregator at a later interval of time;
automatically updating, by the at least one processor, the database of known queries associated with the plurality of users based on the subsequent input data;
utilizing, by the at least one processor, the at least one trained machine learning algorithm to perform a cross-reference analysis to determine a presence of at least one data record within the database of known queries, wherein the at least one data record is at least one data point shared between the input data and the subsequent input data;
dynamically removing, by the at least one processor, the at least one data record from the database of known queries based on the cross-reference analysis;
utilizing, by the at least one processor, the trained machine learning algorithm to predict a trigger associated with the presence of the at least one data record comprising the at least one data point, wherein the at least one trigger is a data correctness confidence value associated with the at least one external data aggregator; and
instructing, by at least one processor, at least one graphic user interface (GUI) having at least one programmable GUI element within a computing device to initiate a verification of the presence of the at least one data record, comprising the at least one data point, based on the plurality of indicative markers.