US 12,147,422 B2
System and method for transpilation of machine interpretable languages
Maharaj Mukherjee, Poughkeepsie, NY (US); Carl M. Benda, Charlotte, NC (US); Elvis Nyamwange, Little Elm, TX (US); Suman Roy Choudhury, Jersey City, NJ (US); and Utkarsh Raj, Charlotte, NC (US)
Assigned to Bank of America Corporation, Charlotte, NC (US)
Filed by Bank of America Corporation, Charlotte, NC (US)
Filed on Dec. 21, 2021, as Appl. No. 17/557,208.
Claims priority of provisional application 63/272,263, filed on Oct. 27, 2021.
Prior Publication US 2023/0129994 A1, Apr. 27, 2023
Int. Cl. G06F 16/24 (2019.01); G06F 16/21 (2019.01); G06F 16/242 (2019.01); G06F 16/2452 (2019.01); G06F 16/2453 (2019.01); G06F 16/248 (2019.01); G06F 16/25 (2019.01); G06F 40/205 (2020.01)
CPC G06F 16/2452 (2019.01) [G06F 16/214 (2019.01); G06F 16/2425 (2019.01); G06F 16/2433 (2019.01); G06F 16/2448 (2019.01); G06F 16/24534 (2019.01); G06F 16/248 (2019.01); G06F 16/258 (2019.01); G06F 40/205 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A computing platform comprising:
at least one processor;
a communication interface communicatively coupled to the at least one processor; and
memory storing computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
train a machine learning model using one or more source syntax trees, one or more target dialect syntax trees, and relationships between the one or more source syntax trees and the one or more target dialect syntax trees, wherein training the machine learning model comprises configuring the machine learning model to output source dialect keys and their corresponding target dialect queries;
execute the corresponding target dialect queries to identify whether the corresponding target dialect queries result in valid execution or result in error;
for a first target dialect query resulting in valid execution, store the first target dialect query and first source dialect keys corresponding to the first target dialect query in a query library lookup table;
for a second target dialect query resulting in error:
identify a cause of the error;
automatically generate, based on the identified cause of the error, a transliteration rule to correct the error; and
store, in the query library lookup table, the second target dialect query, second source dialect keys corresponding to the second target dialect query, and the transliteration rule;
receive, from a client application, a first source query formatted in the source dialect;
translate, using the transliteration rule, the first source query to the target dialect to produce a translated query;
execute the translated query on a target database to produce a query result; and
send, to the client application, the query result.