US-12627562-B2 - Method and system for expanding client networks while improving and protecting robustness of the client networks

Abstract

A client network expansion system that: converts at least one from among a first rule and a first trend into a first set of code; stores the first set of code within a first repository of strategies; receives a first request that is associated with a new set of client details; based on the first repository of strategies, transforms a new set of client details into at least one new quantification of a first set of client attributes; determines whether the at least one new quantification meets a first set of criteria for a first client network; and adds a new client to the first client network when the determination is made that the at least one new quantification meets the first set of criteria.

Inventors

• Krishna Rao VEERAMACHANENI
• Sudhir GORRIPATI

Assignees

• JPMORGAN CHASE BANK, N.A.

Dates

Publication Date

20260512

Application Date

20240501

Priority Date

20240319

Claims (20)

1. 1 . A method for implementing a client network expansion tool, the method comprising: converting at least one from among a first rule and a first trend into a first set of code that comprises at least a first corresponding programmatic client network strategy; storing the first corresponding programmatic client network strategy within a first repository of strategies for a first client network that receives a first set of services from a first set of servers, wherein the first client network includes at least one client device; receiving, from a new client, a first request to join the first client network, wherein the first request is associated with a new set of client details that correspond to the new client; deploying at least one first application programming interface (API) of at least one first artificial intelligence and machine learning (AI/ML) model; based on the first repository of strategies, utilizing, via the at least one first API, the at least one first AI/ML model to transform the new set of client details into at least one new quantification of a first set of client attributes; utilizing, via the at least one first API, the at least one first AI/ML model to determine whether the at least one new quantification meets a first set of criteria for the first client network; and when a determination is made that the at least one new quantification meets the first set of criteria, adding the new client to the first client network.
2. 2 . The method of claim 1 , after the adding the new client to the first client network, the method further comprises: permitting, by the adding, the first set of servers to provide the first set of services to the new client; and improving, by the adding, a robustness of the first client network.
3. 3 . The method of claim 1 , wherein when a determination is made that at least one new quantification does not meet the first set of criteria, the method further comprises: rejecting the first request; preventing, by the rejecting, the first set of servers from providing the first set of services to the new client; and protecting, by the rejecting, a robustness of the first client network from being diminished.
4. 4 . The method of claim 1 , further comprising: searching a set of databases for at least one from among at least one attribute value of the new client and at least one parameter value of the new client; obtaining, from the set of databases, results of the searching, wherein the new set of client details comprises the results of the searching; and associating the new set of client details with the new client.
5. 5 . The method of claim 4 , wherein the set of databases comprises at least one from among a government database and a database of an external agency.
6. 6 . The method of claim 1 , wherein the transforming comprises utilizing an algorithm to transform the new set of client details into the at least one new quantification.
7. 7 . The method of claim 1 , further comprising: receiving a second request, wherein the second request is associated with a second set of client details, wherein the second request comprises a request to join a second client network that receives a second set of services from a second set of servers; based on a second repository of strategies, transforming the second set of client details into at least one second quantification, wherein the at least one second quantification comprises at least one quantification of a second set of client attributes; determining whether the at least one second quantification meets a second set of criteria for the second client network; and when a determination is made that the at least one second quantification meets the second set of criteria, granting the second request.
8. 8 . The method of claim 1 , wherein the at least one first AI/ML model comprises at least one from among at least one explainable AI/ML model and at least one distance metric learning AI/ML model.
9. 9 . The method of claim 8 , wherein the at least one explainable AI/ML model identifies a first set of contributing factors that cause the at least one first AI/ML model to transform the new set of client details into the at least one new quantification.
10. 10 . The method of claim 8 , wherein the at least one distance metric learning AI/ML model is based on at least one from among a large margin nearest neighbor metric learning (LMNN) algorithm and a neighborhood components analysis (NCA) algorithm.
11. 11 . A system for implementing a client network expansion tool, the system comprising: a processor; and memory storing instructions that, when executed by the processor, cause the processor to perform operations comprising: converting at least one from among a first rule and a first trend into a first set of code that comprises at least a first corresponding programmatic client network strategy; storing the first corresponding programmatic client network strategy within a first repository of strategies for a first client network that receives a first set of services from a first set of servers, wherein the first client network includes at least one client device; receiving, from a new client, a first request to join the first client network, wherein the first request is associated with a new set of client details that correspond to the new client; deploying at least one first application programming interface (API) of at least one first artificial intelligence and machine learning (AI/ML) model; based on the first repository of strategies, utilizing, via the at least one first API, the at least one first AI/ML model to transform the new set of client details into at least one new quantification of a first set of client attributes; utilizing, via the at least one first API, the at least one first AI/ML model to determine whether the at least one new quantification meets a first set of criteria for the first client network; and when a determination is made that the at least one new quantification meets the first set of criteria, adding the new client to the first client network.
12. 12 . The system of claim 11 , after the adding the new client to the first client network, the instructions may cause the processor to perform further operations comprising: permitting, by the adding, the first set of servers to provide the first set of services to the new client; and improving, by the adding, a robustness of the first client network.
13. 13 . The system of claim 11 , wherein when a determination is made that at least one new quantification does not meet the first set of criteria, the instructions cause the processor to perform further operations comprising: rejecting the first request; preventing, by the rejecting, the first set of servers from providing the first set of services to the new client; and protecting, by the rejecting, a robustness of the first client network from being diminished.
14. 14 . The system of claim 11 , wherein when executed, the instructions cause the processor to perform further operations comprising: searching a set of databases for at least one from among at least one attribute value of the new client and at least one parameter value of the new client; obtaining, from the set of databases, results of the searching, wherein the new set of client details comprises the results of the searching; and associating the new set of client details with the new client.
15. 15 . The system of claim 11 , wherein when executed by the processor, the at least one first AI/ML model comprises at least one from among a distance metric learning AI/ML model and an explainable AI/ML model that identifies a first set of contributing factors that cause the at least one first AI/ML model to transform the new set of client details into the at least one new quantification, and wherein the at least one distance metric learning AI/ML model is based on at least one from among a large margin nearest neighbor metric learning (LMNN) algorithm and a neighborhood components analysis (NCA) algorithm.
16. 16 . A non-transitory computer-readable medium for implementing a client network expansion tool, the computer-readable medium stores instructions that, when executed by a processor, cause the processor to perform operations comprising: converting at least one from among a first rule and a first trend into a first set of code that comprises at least a first corresponding programmatic client network strategy; storing the first corresponding programmatic client network strategy within a first repository of strategies for a first client network that receives a first set of services from a first set of servers, wherein the first client network includes at least one client device; receiving, from a new client, a first request to join the first client network, wherein the first request is associated with a new set of client details that correspond to the new client; deploying at least one first application programming interface (API) of at least one first artificial intelligence and machine learning (AI/ML) model; based on the first repository of strategies, utilizing, via the at least one first API, the at least one first AI/ML model to transform the new set of client details into at least one new quantification of a first set of client attributes; utilizing, via the at least one first API, the at least one first AI/ML model to determine whether the at least one new quantification meets a first set of criteria for the first client network; and when a determination is made that the at least one new quantification meets the first set of criteria, adding the new client to the first client network.
17. 17 . The computer-readable medium of claim 16 , after the adding the new client to the first client network, the instructions cause the processor to perform further operations that comprise: permitting, by the adding, the first set of servers to provide the first set of services to the new client; and improving, by the adding, a robustness of the first client network.
18. 18 . The computer-readable medium of claim 16 , wherein when a determination is made that at least one new quantification does not meet the first set of criteria, the instructions cause the processor to perform further operations comprising: rejecting the first request; preventing, by the rejecting, the first set of servers from providing the first set of services to the new client; and protecting, by the rejecting, a robustness of the first client network from being diminished.
19. 19 . The computer-readable medium of claim 16 , wherein when executed by the processor, the instructions cause the transforming and the determining to be performed by at least one first artificial intelligence and machine learning (AI/ML) model that comprises at least one from among a distance metric learning AI/ML model and an explainable AI/ML model that identifies a first set of contributing factors that cause the at least one first AI/ML model to transform the new set of client details into the at least one new quantification.
20. 20 . The computer-readable medium of claim 19 , wherein when executed by the processor, the instructions cause the at least one distance metric learning AI/ML model to be based on at least one from among a large margin nearest neighbor metric learning (LMNN) algorithm and a neighborhood components analysis (NCA) algorithm.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority benefit from Indian Application No. 202411020403, filed Mar. 19, 2024, which is hereby incorporated by reference in its entirety. BACKGROUND 1. Field of the Invention The field of the invention disclosed herein generally relates to a client network expansion tool and, more particularly, to a method, system, and computer-readable medium for implementing technology that expands at least one client network, improves the at least one client network's robustness, and simultaneously protects that robustness from being diminished. 2. Background of the Invention Currently, there is a need for technology that can identify strategies for reliably expanding a client network and can also identify factors impacting the client network's robustness. As part of initiatives to expand the clientele of a resource network, such as a distributed resource network that provides services via the Internet, it is necessary to identify dynamic business strategies and any attributes that impact the network's strength, especially when that network's strength depends on the integrity of its clients. However, there is currently no technology available for identifying dynamic business strategies or attributes that impact a network's strength. Therefore, conventional resource network clientele expansion initiatives are prone to inconsistencies and other types of errors due to an absence of relevant resources to this end. Accordingly, there is a need in the field of the herein-disclosed invention for a technical solution to the foregoing absence of technology for identifying dynamic business strategies and attributes that impact a network's strength. SUMMARY The present disclosure, through one or more of its various aspects, embodiments, and/or specific features or sub-component, provides, inter alia, various systems, servers, devices, methods, media, programs and platforms for implementing a client network expansion tool that expands at least one client network and improves the at least one client network's robustness while simultaneously protecting that robustness from being diminished. According to an aspect of the present disclosure, a method is provided for implementing a client network expansion tool. The method may comprise: converting at least one from among a first rule and a first trend into a first set of code that comprises at least a first corresponding programmatic client network strategy; storing the first corresponding programmatic strategy within a first repository of strategies for a first client network that receives a first set of services from a first set of servers; receiving, from a new client, a first request to join the first client network; based on the first repository of strategies, transforming a new set of client details that correspond to the new client, into at least one new quantification of a first set of client attributes; determining whether the at least one new quantification meets a first set of criteria for the first client network; and adding the new client to the first client network when a determination is made that the at least one new quantification meets the first set of criteria. The first client network may include at least one client device, and the first request may be associated with the new set of client details. In the method, after the adding the new client to the first client network, the method may further comprise: permitting, by the adding, the first set of servers to provide the first set of services to the new client; and improving, by the adding, a robustness of the first client network. In the method, when a determination is made that at least one new quantification does not meet the first set of criteria, the method may further comprise: rejecting the first request; preventing, by the rejecting, the first set of servers from providing the first set of services to the new client; and protecting, by the rejecting, a robustness of the first client network from being diminished. The method may further comprise: searching a set of databases for at least one from among at least one attribute value of the new client and at least one parameter value of the new client; and obtaining, from the set of databases, results of the searching; and associating the new set of client details with the new client. The new set of client details may comprise the results of the searching. In the method, the set of databases may comprise at least one from among a government database and a database of an external agency. In the method, the transforming may comprise utilizing an algorithm to transform the new set of client details into the at least one new quantification. The method may further comprise: receiving a second request; based on a second repository of strategies, transforming a second set of client details into at least one second quantification; determining whether the at least one second quantification meets a second set