US 12,131,280 B2
Systems and methods for synchronizing processing statement deployment across diverse computer networks using a three-tiered artificial intelligence architecture
Maneet Sharma, Irving, TX (US); Flora Sah, Natick, MA (US); Adar Kiran Danait, Flower Mound, TX (US); Ashima Gupta, Coppell, TX (US); James Iacona, Yardley, PA (US); Crystal Lynn Magruder, Eolia, MO (US); and Tracy L. Yager, Wright City, MO (US)
Assigned to Citibank, N.A., New York, NY (US)
Filed by Citibank, N.A., New York, NY (US)
Filed on Jul. 28, 2023, as Appl. No. 18/361,250.
Application 18/361,250 is a continuation of application No. 18/190,602, filed on Mar. 27, 2023, granted, now 11,763,236.
Prior Publication US 2024/0330818 A1, Oct. 3, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 10/0635 (2023.01); G06F 40/44 (2020.01)
CPC G06Q 10/0635 (2013.01) [G06F 40/44 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A system for synchronizing processing statement deployment in Activity, Risk, Control, and Monitoring (“ARCM”) tools using a three-tiered artificial intelligence architecture, the system comprising:
one or more processors; and
a non-transitory, computer-readable medium, comprising instructions that, when executed by the one or more processors, cause operations comprising:
receiving, at a user interface, a first request for a first recommendation, wherein the first recommendation comprises a first set of standardized processing statements for implementing on a first function of a plurality of functions for a network;
inputting the first request into a first network component, wherein the first network component comprises a plurality of models, wherein one or more of the plurality of models is trained to:
generate a library of standardized processing statements for the plurality of functions based on cosine similarities of text of non-standardized processing characteristics in non-standardized descriptions of non-standardized processing statements;
generate a plurality of standardized processing characteristic values for each standardized processing statement in the library, wherein the one or more of the plurality of models comprises a transformer-based model and a natural language processing model; and
generate recommendations of sets of standardized processing statements applied to one or more of the plurality of functions, wherein the one or more of the plurality of models comprises a classification model; and
receiving a first output from the one or more of the plurality of models, wherein the first output comprises the first set of standardized processing statements for implementing on the first function of the plurality of functions for the network.