US 12,153,605 B2
Synthetic data generation
Aadarsh Pratik, Maharashtra (IN); Mrugesh S. Kulkarni, New Jersey, NJ (US); Tarun Bhatnagar, Edison, NJ (US); Shrikant Khaire, Charlotte, NC (US); Ramachandhran Subrahmanian, East Windsor, NJ (US); and Indira Korrapati, Waxhaw, NC (US)
Assigned to Wells Fargo Bank, N.A., San Francisco, CA (US)
Filed by Wells Fargo Bank, N.A., San Francisco, CA (US)
Filed on May 3, 2023, as Appl. No. 18/311,714.
Application 18/311,714 is a continuation of application No. 17/354,285, filed on Jun. 22, 2021, granted, now 11,675,817.
Prior Publication US 2023/0409607 A1, Dec. 21, 2023
Int. Cl. G06F 7/00 (2006.01); G06F 16/28 (2019.01); G06F 21/62 (2013.01); G06N 20/00 (2019.01)
CPC G06F 16/285 (2019.01) [G06F 21/6245 (2013.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method for synthetic data generation, the method comprising:
receiving a request for synthetic data generation, the request for synthetic data generation comprising one or more configuration data parameters;
determining a match level, wherein the match level describes a percent match between the one or more configuration data parameters and one or more base datasets;
selecting a processing model from amongst a plurality of processing models based upon the determined match level, wherein selection of the processing model based on the determined match level comprises selecting a machine learning generation model in an instance in which the match level exceeds a predefined threshold percentage and selecting a rules-based generation model in an instance in which the match level does not exceed the predefined threshold percentage;
generating one or more synthetic datasets comprising one or more synthetic data values via the selected processing model; and
providing, to a user via a user interface, the one or more generated synthetic datasets.