公开(公告)号：US11763236B1

公开(公告)日：2023-09-19

申请号：US18190602

申请日：2023-03-27

申请人： Citibank, N.A.

发明人： Maneet Sharma ,  Flora Sah ,  Adar Kiran Danait ,  Ashima Gupta ,  James Iacona ,  Crystal Lynn Magruder ,  Tracy L. Yager

IPC分类号： G06Q10/0635 ,  G06F40/44

CPC分类号： G06Q10/0635 ,  G06F40/44

摘要： Systems and methods are described for a three-tiered artificial intelligence architecture that synchronizes processing statement deployment across diverse computer networks. The system may receive, at a user interface, a first request for a first recommendation. The first recommendation includes a set of standardized processing statements for implementing on a function. The system may input the first request into a first network component. The first network component includes first, second, and third models. The first model is trained to generate a library of standardized processing statements. The second model is trained to generate a plurality of standardized processing characteristic values for each standardized processing statement in the library. The third model is trained to generate recommendations of sets of standardized processing statements to functions. The system receives an output from the first network component and generates for display the first recommendation based on the output.

公开(公告)号：US12131280B2

公开(公告)日：2024-10-29

申请号：US18361250

申请日：2023-07-28

申请人： Citibank, N.A.

发明人： Maneet Sharma ,  Flora Sah ,  Adar Kiran Danait ,  Ashima Gupta ,  James Iacona ,  Crystal Lynn Magruder ,  Tracy L. Yager

IPC分类号： G06Q10/0635 ,  G06F40/44

CPC分类号： G06Q10/0635 ,  G06F40/44

摘要： Systems and methods are described for a three-tiered artificial intelligence architecture that synchronizes processing statement deployment across diverse computer networks. The system may receive, at a user interface, a first request for a first recommendation. The first recommendation includes a set of standardized processing statements for implementing on a function. The system may input the first request into a first network component. The first network component includes first, second, and third models. The first model is trained to generate a library of standardized processing statements. The second model is trained to generate a plurality of standardized processing characteristic values for each standardized processing statement in the library. The third model is trained to generate recommendations of sets of standardized processing statements to functions. The system receives an output from the first network component and generates for display the first recommendation based on the output.