US 12,107,774 B2
System and method for autonomous conversion of a resource format using machine learning
Isabel Esther Baransky, New York, NY (US); and Daniel Rapheal Stanton, Sacramento, CA (US)
Assigned to BANK OF AMERICA CORPORATION, Charlotte, NC (US)
Filed by BANK OF AMERICA CORPORATION, Charlotte, NC (US)
Filed on Aug. 8, 2022, as Appl. No. 17/883,277.
Prior Publication US 2024/0048506 A1, Feb. 8, 2024
Int. Cl. G06F 15/173 (2006.01); H04L 47/722 (2022.01); H04L 47/765 (2022.01); H04L 47/78 (2022.01)
CPC H04L 47/788 (2013.01) [H04L 47/722 (2013.01); H04L 47/765 (2013.01)] 14 Claims
OG exemplary drawing
 
1. A system for autonomous resource format conversion, the system comprising:
at least one non-transitory storage device; and
at least one processing device coupled to the at least one non-transitory storage device, wherein the at least one processing device is configured to:
receive, from an originating user or entity, a data transmission, wherein the data transmission is a transmission of currency;
extract, from the data transmission, a destination identifier and a primary data format, wherein the destination identifier identifies comprises at least one account number and a destination zip code and the destination identifier associated with a beneficiary a secondary data format, wherein the secondary data format comprises a destination currency, and wherein the primary data format comprises an originating currency;
determine the destination identifier is an approved destination identifier, wherein determining the destination identifier is an approved destination identifier comprises querying a data repository of blocked destination identifiers and determining the destination identifier is not associated with any of the blocked destination identifiers;
compare the approved destination identifier to a plurality of reference patterns, wherein each reference pattern is associated with a set of known identifiers including exclusion values and inclusion values;
identify the destination identifier not matching at least one set of the inclusion values or the destination identifier matching at least one set of the exclusion values; and
convert, based on an output of a machine learning engine, the primary data format to the secondary data format, wherein the output of the machine learning engine further comprises identifying a match of the destination identifier to a downstream edge point from a plurality of known downstream edge points, wherein the downstream edge point comprises a country code and at least one destination identifier associated with the beneficiary.