US 11,727,019 B2
Scalable dynamic acronym decoder
Erik Silk, Reston, VA (US); Basim Partovi, Derwood, MD (US); and Ahmad Hassan Ibrahim, Centerville, VA (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Jun. 4, 2021, as Appl. No. 17/338,789.
Application 17/338,789 is a continuation of application No. 16/416,719, filed on May 20, 2019.
Application 16/416,719 is a continuation of application No. 16/151,844, filed on Oct. 4, 2018, granted, now 10,339,150, issued on Jul. 2, 2019.
Prior Publication US 2021/0294812 A1, Sep. 23, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/2457 (2019.01); H04L 9/40 (2022.01); G06F 9/455 (2018.01); G06F 9/54 (2006.01); G06N 20/00 (2019.01); G06F 16/248 (2019.01); G06F 16/9535 (2019.01); G06F 9/451 (2018.01)
CPC G06F 16/24578 (2019.01) [G06F 9/451 (2018.02); G06F 9/45558 (2013.01); G06F 9/54 (2013.01); G06F 16/248 (2019.01); G06F 16/9535 (2019.01); G06N 20/00 (2019.01); H04L 63/08 (2013.01); H04L 63/105 (2013.01); G06F 2009/4557 (2013.01); G06F 2009/45591 (2013.01); G06F 2009/45595 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system, comprising:
a computer processor; and
a memory storing instructions which when executed by the processor to cause the processor to:
receive, from a user interface, a query specifying an acronym, the query associated with an account;
process, by a database management system (DBMS), the query against a database to generate a result set, the query processed based at least in part on elements of a context vector of the account and a plurality of content tags applied to each of a plurality of entries in the database;
return, by the DBMS, results of the result set as responsive to the query, each result in the result set comprising a respective definition for the acronym;
receive classification data comprising a subset of the plurality of content tags;
receive learning data describing use of a plurality of user interfaces including the user interface;
generate at least one new content tag for at least one of the plurality of entries in the database by a machine learning (ML) algorithm based on the classification data, the learning data, and a ML model;
apply the generated at least one new content tag to the at least one of the plurality of entries in the database; and
process another query based at least in part on the at least one new content tag, the another query comprising another acronym.