IP Library › Granted Patent US 11,914,457
Granted Patent B2
US 11,914,457 · App. 17/708,167 · Granted Feb 27, 2024

System for early detection of operational failure in component-level functions within a computing environment

Inventors: Ashok Kumar (Hyderabad, IN); Narsing Raj (Hyderabad, IN); Venkata Lakshmi Sai Siva Kumar Devulapalli (Hyderabad, IN)
Assignee: BANK OF AMERICA CORPORATION
G06F11/0751G06F11/0721G06F11/0787
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,914,457
App. No.
17/708,167
Granted
Feb 27, 2024
Kind
B2
Abstract

Systems, computer program products, and methods are described herein for early detection of operational failure in component-level functions within a computing environment. The present invention is configured to receive, from one or more source devices, log data; determine, using a trained machine learning model, a likelihood that a first subset of the log data is associated with an operational failure of one or more component-level functions; determine that the likelihood that the first subset of the log data is associated with the operational failure of one or more component-level functions is greater than a predetermined threshold; determine that the first subset of the log data reflects a current state of a first subset of source devices; generate a notification indicating that the first subset of source devices is likely to experience the operational failure of one or more component-level functions; and display the notification on an administrator device associated with the first subset of source devices.

Claims (75)

1. A system for early detection of operational failure in component-level functions within a computing environment, the system comprising:

at least one non-transitory storage device; and

at least one processor coupled to the at least one non-transitory storage device, wherein the at least one processor is configured to:

electronically receive, from one or more source devices, log data;

analyze, using a machine learning subsystem, the log data for indications of operational failure of one or more component-level functions associated with the one or more source devices, wherein analyzing further comprises:

determining, using a trained machine learning model, a likelihood that a first subset of the log data is associated with operational failure of one or more component-level functions; and

determining that the likelihood that the first subset of the log data is associated with the operational failure of one or more component-level functions is greater than a predetermined threshold;

determine that the first subset of the log data reflects a current state of a first subset of source devices;

determine that the first subset of source devices is likely to experience the operational failure of one or more component-level functions based on at least their current state;

determine a tier of the operational failure of the one or more component-level functions based on their overall effect on the computing environment;

generate a notification indicating that the first subset of source devices is likely to experience the operational failure of one or more component-level functions and the tier of the operational failure of the one or more component-level functions; and

transmit control signals configured to cause an administrator device associated with the first subset of source devices to display the notification.

2. The system of claim 1 , wherein the at least one processor is further configured to:

retrieve, from a first internal repository, one or more mitigation actions associated with the tier of the operational failure of one or more component-level functions; and

transmit control signals configured to cause the administrator device to display the one or more mitigation actions.

3. The system of claim 2 , wherein the one or more mitigation actions are preventative actions that are to be implemented before the first subset of source devices experience the operational failure of one or more component-level functions.

4. The system of claim 2 , wherein the one or more mitigation actions are remedial actions that are to be implemented after the first subset of source devices experience the operational failure of one or more component-level functions.

5. The system of claim 1 , wherein the at least one processor is further configured to:

continuously monitor component-level functions of one or more source devices within the computing environment;

determine a current state of the one or more source devices based on at least monitoring the component-level functions of the one or more source devices; and

electronically receive, from one or more source devices, the log data reflecting the current state of the one or more source devices.

6. The system of claim 1 , wherein the at least one processor is further configured to:

continuously monitor incidences of historical component-level functional failures associated with the one or more source devices;

retrieve historical log data corresponding to the historical component-level functional failures, wherein the historical log data reflects a state of the one or more source devices a predetermined period of time prior to the incidences of the historical component-level functional failures; and

store the historical log data and the corresponding historical component-level functional failures in a second internal repository.

7. The system of claim 6 , wherein the at least one processor is further configured to:

retrieve, from the second internal repository, the historical log data and the corresponding historical component-level functional failures; and

generate a training dataset using the historical log data and the corresponding historical component-level functional failures.

8. The system of claim 7 , wherein the at least one processor is further configured to:

train a machine learning model with the training dataset using a machine learning algorithm; and

generate the trained machine learning model.

9. A computer program product for early detection of operational failure in component-level functions within a computing environment, the computer program product comprising a non-transitory computer-readable medium comprising code causing a first apparatus to:

electronically receive, from one or more source devices, log data;

analyze, using a machine learning subsystem, the log data for indications of operational failure of one or more component-level functions associated with the one or more source devices, wherein analyzing further comprises:

determining, using a trained machine learning model, a likelihood that a first subset of the log data is associated with operational failure of one or more component-level functions; and

determining that the likelihood that the first subset of the log data is associated with the operational failure of one or more component-level functions is greater than a predetermined threshold;

determine that the first subset of the log data reflects a current state of a first subset of source devices;

determine that the first subset of source devices is likely to experience the operational failure of one or more component-level functions based on at least their current state;

determine a tier of the operational failure of the one or more component-level functions based on their overall effect on the computing environment;

generate a notification indicating that the first subset of source devices is likely to experience the operational failure of one or more component-level functions and the tier of the operational failure of the one or more component-level functions; and

transmit control signals configured to cause an administrator device associated with the first subset of source devices to display the notification.

10. The computer program product of claim 9 , wherein the first apparatus is further configured to:

retrieve, from a first internal repository, one or more mitigation actions associated with the tier of the operational failure of one or more component-level functions; and

transmit control signals configured to cause the administrator device to display the one or more mitigation actions.

11. The computer program product of claim 10 , wherein the one or more mitigation actions are preventative actions that are to be implemented before the first subset of source devices experience the operational failure of one or more component-level functions.

12. The computer program product of claim 10 , wherein the one or more mitigation actions are remedial actions that are to be implemented after the first subset of source devices experience the operational failure of one or more component-level functions.

13. The computer program product of claim 9 , wherein the first apparatus is further configured to:

continuously monitor component-level functions of one or more source devices within the computing environment;

determine a current state of the one or more source devices based on at least monitoring the component-level functions of the one or more source devices; and

electronically receive, from one or more source devices, the log data reflecting the current state of the one or more source devices.

14. The computer program product of claim 9 , wherein the first apparatus is further configured to:

continuously monitor incidences of historical component-level functional failures associated with the one or more source devices;

retrieve historical log data corresponding to the historical component-level functional failures, wherein the historical log data reflects a state of the one or more source devices a predetermined period of time prior to the incidences of the historical component-level functional failures; and

store the historical log data and the corresponding historical component-level functional failures in a second internal repository.

15. The computer program product of claim 14 , wherein the first apparatus is further configured to:

retrieve, from the second internal repository, the historical log data and the corresponding historical component-level functional failures; and

generate a training dataset using the historical log data and the corresponding historical component-level functional failures.

16. The computer program product of claim 15 , wherein the first apparatus is further configured to:

train a machine learning model with the training dataset using a machine learning algorithm; and

generate the trained machine learning model.

17. A method for early detection of operational failure in component-level functions within a computing environment, the method comprising:

electronically receiving, from one or more source devices, log data;

analyzing, using a machine learning subsystem, the log data for indications of operational failure of one or more component-level functions associated with the one or more source devices, wherein analyzing further comprises:

determining, using a trained machine learning model, a likelihood that a first subset of the log data is associated with operational failure of one or more component-level functions; and

determining that the likelihood that the first subset of the log data is associated with the operational failure of one or more component-level functions is greater than a predetermined threshold;

determining that the first subset of the log data reflects a current state of a first subset of source devices;

determining that the first subset of source devices is likely to experience the operational failure of one or more component-level functions based on at least their current state;

determining a tier of the operational failure of the one or more component-level functions based on their overall effect on the computing environment;

generating a notification indicating that the first subset of source devices is likely to experience the operational failure of one or more component-level functions and the tier of the operational failure of the one or more component-level functions; and

transmitting control signals configured to cause an administrator device associated with the first subset of source devices to display the notification.

18. The method of claim 17 , wherein the method further comprises:

retrieving, from a first internal repository, one or more mitigation actions associated with the tier of the operational failure of one or more component-level functions; and

transmitting control signals configured to cause the administrator device to display the one or more mitigation actions.

19. The method of claim 18 , wherein the one or more mitigation actions are preventative actions that are to be implemented before the first subset of source devices experience the operational failure of one or more component-level functions.

20. The method of claim 18 , wherein the one or more mitigation actions are remedial actions that are to be implemented after the first subset of source devices experience the operational failure of one or more component-level functions.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 30, 2022
From: KUMAR, ASHOK; RAJ, NARSING; DEVULAPALLI, VENKATA LAKSHMI SAI SIVA KUMAR
To: BANK OF AMERICA CORPORATION
Reel/Frame 059439/0385 →
Continuity (1)
Related Publication 20230315553A1 · Oct 5, 2023