The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Sep. 23, 2025

Filed:

Jan. 22, 2024
Applicant:

Bank of America Corporation, Charlotte, NC (US);

Inventors:

Anurajam Rajagopalan, Medavakkam, IN (US);

Sathyanarayana Rajendran, Chennai, IN (US);

Sunil Kumar Sriperambudur, Peerancheru, IN;

Assignee:

Bank of America Corporation, Charlotte, NC (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06F 15/173 (2006.01); G06F 9/50 (2006.01); H04L 45/302 (2022.01); H04L 67/1008 (2022.01); H04L 67/63 (2022.01);
U.S. Cl.
CPC ...
H04L 67/1008 (2013.01); G06F 9/5027 (2013.01); H04L 45/302 (2013.01); H04L 67/63 (2022.05);
Abstract

A message queue routing system may be implemented into a message queue gateway to route data to Software component designed and deployed into MQ Gateway to route the data to the MQ cluster. A central processing unit (CPU) node analyzer reads real time health statistics of each of a plurality of MQ cluster processing nodes. Based the computation, the CPU node analyzer routes the message to a specified node of the cluster having a minimum of CPU load at that time. The CPU node analyzer analyzes information comprising at least CPU performance information and system idleness information. Each processing node enables dynamic message routing computations utilizing an artificial intelligence/machine learning framework and a plurality of trained predictive models. The predictive model is trained using a trained data set using text classification. Message information is extracted from the message via natural language processing and is processed via the trained model to identify characteristic information of the message. The characteristic information is used to select a subset of filters associated with message functionality. The message is routed to a target application based on filtering performed using the subset of filters.


Find Patent Forward Citations

Loading…