US 12,487,811 B2
Natural language processing engine for component level data mapping and code revision impact analysis
Marcus Raphael Matos, Richardson, TX (US); Jack Lawson Bishop, III, Evanston, IL (US); Robert Cain Durbin, Jr., New Hope, PA (US); Daniel Joseph Serna, The Colony, TX (US); Benjamin Tweel, Romeoville, IL (US); and Jake Michael Yara, Mint Hill, NC (US)
Assigned to BANK OF AMERICA CORPORATION, Charlotte, NC (US)
Filed by BANK OF AMERICA CORPORATION, Charlotte, NC (US)
Filed on Jan. 3, 2023, as Appl. No. 18/092,520.
Prior Publication US 2024/0220229 A1, Jul. 4, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 9/44 (2018.01); G06F 8/65 (2018.01); G06F 9/445 (2018.01); G06F 9/455 (2018.01); H04L 41/0686 (2022.01)
CPC G06F 8/65 (2013.01) [H04L 41/0686 (2013.01)] 15 Claims
OG exemplary drawing
 
1. A system for code revision impact analysis, the system comprising:
at least one non-transitory storage device; and
at least one processor coupled to the at least one non-transitory storage device, wherein the at least one processor is configured to:
train a natural language processing engine to output a plurality of expected updates associated with a text file, wherein training the natural language processing engine comprises:
receiving, via a data acquisition engine, a training dataset comprising software code;
converting, via a data pre-processing engine, the training dataset from a non-standardized format to a standardized format;
processing, via the data pre-processing engine, the converted training dataset to generate an extracted feature set using a dimensionality reduction technique;
executing, using a machine learning model tuning engine, a plurality of testing cycles using the extracted feature set, wherein the machine learning model tuning engine is configured to vary one or more testing parameters for each testing cycle of the plurality of testing cycles; and
deploying the trained natural language processing engine into a production environment;
generate a system map of a distributed computing environment, wherein the system map comprises a plurality of nodes;
receive a data transmission comprising an image file associated with a software update;
convert the image file into a text file via an optical character recognition (OCR) process;
process the converted text file via the trained natural language processing engine, wherein an output of the trained natural language processing engine comprises the plurality of expected updates;
determine, based on the generated system map, at least one downstream effect of the plurality of expected updates, wherein the at least one downstream effect is associated with one or more nodes of the plurality of nodes;
calculate an impact score for the at least one downstream effect, wherein the impact score is based on the one or more nodes; and
perform a remedial action based on the impact score, wherein performing the remedial action comprises preventing a network device from installing the software update.