IP Library › Granted Patent US 12,737,163
Granted Patent B2
US 12,737,163 · App. 18/508,359 · Granted Sep 15, 2026

System and method for intelligent automatic resolution of inactive computer code in a multi cloud environment

Inventors: Priyanka Nair (Sambalpur, IN); Sudarshan Veeramreddy (Hyderabad, IN); Swathi Bussa (Hyderabad, IN); Shyam K Dhanraj (Chennai, IN); Greeshma Susan Skariah (Pathanamthitta, IN); Vishakha Pandey (Sagar, IN)
Assignee: BANK OF AMERICA CORPORATION
G06F8/4435G06N3/0464
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 12,737,163
App. No.
18/508,359
Granted
Sep 15, 2026
Kind
B2
Abstract

A system is provided for intelligent automatic resolution of inactive computer code in a multi cloud environment. In particular, the system may comprise an artificial intelligence powered apparatus that may use one or more machine learning models and/or neural networks to analyze data from a cloud computing environment, such as system logs, memory dumps, real-time status queries, and/or the like. Based on analyzing the data, the system may identify inactive, unused, and/or redundant code within the cloud computing environment. The system may then compute a confidence level associated with the identification of the inactive code. Upon detecting that the confidence level has exceeded a defined threshold, the system may automatically initiate one or more remediation processes, such as deletion or modification of the inactive code. In this way, the system may provide a way to automatically remove inactive code from the cloud computing environment.

Claims (53)

1 . A system for intelligent automatic resolution of inactive computer code in a multi cloud environment, the system comprising:

a processing device;

a non-transitory storage device containing instructions when executed by the processing device, causes the processing device to perform the steps of:

accessing cloud data within a cloud computing environment, the cloud data comprising log files, memory dumps, and real-time status queries;

processing the cloud data using an artificial intelligence (“AI”) analyzer, wherein processing the cloud data comprises identifying one or more instances of inactive code by parsing the cloud data and perform feature extraction to the cloud data to identify numerical features, wherein the AI analyzer uses a deep convolutional neural network trained to correlate container orchestration metrics, dependency analysis data, and runtime code coverage data from the numerical features to identify the one or more instances of inactive code;

computing a confidence level for each of the one or more instances of inactive code;

determining whether the confidence level exceeds a defined threshold; and

based on determining whether the confidence level exceeds the defined threshold, executing one or more remediation processes for each of the one or more instances of inactive code, where the one or more remediation processes further comprises:

generating, using the AI analyzer, replacement code by automatically building a new code set modified from code within a live production environment of the cloud computing environment, wherein the replacement code removes the one or more instances of inactive code from the cloud computing environment;

testing the replacement code within a virtualized testing environment; and

based on testing the replacement code within the testing environment, deploying the replacement code into the cloud computing environment through a container orchestrator of the cloud computing environment.

2 . The system of claim 1 , wherein determining whether the confidence level exceeds the defined threshold comprises:

detecting that the confidence level exceeds the defined threshold; and

executing an automated resolution process on the one or more instances of inactive code.

3 . The system of claim 1 , wherein determining whether the confidence level exceeds the defined threshold comprises:

detecting that the confidence level falls below the defined threshold; and

transmitting a notification to a user computing device associated with the one or more instances of inactive code, wherein the notification comprises a report generated by the AI analyzer regarding the one or more instances of inactive code.

4 . The system of claim 3 , wherein the report comprises the confidence level.

5 . The system of claim 1 , wherein processing the cloud data using the AI analyzer comprises using one or more deep learning based processes to analyze the log files based on the numerical features.

6 . A computer program product for intelligent automatic resolution of inactive computer code in a multi cloud environment, the computer program product comprising a non-transitory computer-readable medium comprising code causing an apparatus to perform the steps of:

accessing cloud data within a cloud computing environment, the cloud data comprising log files, memory dumps, and real-time status queries;

processing the cloud data using an artificial intelligence (“AI”) analyzer, wherein processing the cloud data comprises identifying one or more instances of inactive code by parsing the cloud data and perform feature extraction to the cloud data to identify numerical features, wherein the AI analyzer uses a deep convolutional neural network trained to correlate container orchestration metrics, dependency analysis data, and runtime code coverage data from the numerical features to identify the one or more instances of inactive code;

computing a confidence level for each of the one or more instances of inactive code;

determining whether the confidence level exceeds a defined threshold; and

based on determining whether the confidence level exceeds the defined threshold, executing one or more remediation processes for each of the one or more instances of inactive code, where the one or more remediation processes further comprises:

generating, using the AI analyzer, replacement code by automatically building a new code set modified from code within a live production environment of the cloud computing environment, wherein the replacement code removes the one or more instances of inactive code from the cloud computing environment;

testing the replacement code within a virtualized testing environment; and

based on testing the replacement code within the testing environment, deploying the replacement code into the cloud computing environment through a container orchestrator of the cloud computing environment.

7 . The computer program product of claim 6 , wherein determining whether the confidence level exceeds the defined threshold comprises:

detecting that the confidence level exceeds the defined threshold; and

executing an automated resolution process on the one or more instances of inactive code.

8 . The computer program product of claim 6 , wherein determining whether the confidence level exceeds the defined threshold comprises:

detecting that the confidence level falls below the defined threshold; and

transmitting a notification to a user computing device associated with the one or more instances of inactive code, wherein the notification comprises a report generated by the AI analyzer regarding the one or more instances of inactive code.

9 . The computer program product of claim 8 , wherein the report comprises the confidence level.

10 . The computer program product of claim 6 , wherein processing the cloud data using the AI analyzer comprises using one or more deep learning based processes to analyze the log files based on the numerical features.

11 . A computer-implemented method for intelligent automatic resolution of inactive computer code in a multi cloud environment, the computer-implemented method comprising:

accessing cloud data within a cloud computing environment, the cloud data comprising log files, memory dumps, and real-time status queries;

processing the cloud data using an artificial intelligence (“AI”) analyzer, wherein processing the cloud data comprises identifying one or more instances of inactive code by parsing the cloud data and perform feature extraction to the cloud data to identify numerical features, wherein the AI analyzer uses a deep convolutional neural network trained to correlate container orchestration metrics, dependency analysis data, and runtime code coverage data from the numerical features to identify the one or more instances of inactive code;

computing a confidence level for each of the one or more instances of inactive code;

determining whether the confidence level exceeds a defined threshold; and

based on determining whether the confidence level exceeds the defined threshold, executing one or more remediation processes for each of the one or more instances of inactive code, where the one or more remediation processes further comprises:

generating, using the AI analyzer, replacement code by automatically building a new code set modified from code within a live production environment of the cloud computing environment, wherein the replacement code removes the one or more instances of inactive code from the cloud computing environment;

testing the replacement code within a virtualized testing environment; and

based on testing the replacement code within the testing environment, deploying the replacement code into the cloud computing environment through a container orchestrator of the cloud computing environment.

12 . The computer-implemented method of claim 11 , wherein determining whether the confidence level exceeds the defined threshold comprises:

detecting that the confidence level exceeds the defined threshold; and

executing an automated resolution process on the one or more instances of inactive code.

13 . The computer-implemented method of claim 11 , wherein determining whether the confidence level exceeds the defined threshold comprises:

detecting that the confidence level falls below the defined threshold; and

transmitting a notification to a user computing device associated with the one or more instances of inactive code, wherein the notification comprises a report generated by the AI analyzer regarding the one or more instances of inactive code.

14 . The computer-implemented method of claim 13 , wherein the report comprises the confidence level.

15 . The computer-implemented method of claim 11 , wherein processing the cloud data using the AI analyzer comprises using one or more deep learning based processes to analyze the log files based on the numerical features.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 14, 2023
From: NAIR, PRIYANKA; VEERAMREDDY, SUDARSHAN; BUSSA, SWATHI; DHANRAJ, SHYAM K; SKARIAH, GREESHMA SUSAN; PANDEY, VISHAKHA
To: BANK OF AMERICA CORPORATION
Reel/Frame 065552/0519 →
Continuity (1)
Related Publication 20250156163A1 · May 15, 2025
References Cited (27)
US 5999737A · Srivastava · 1999 [cited by applicant]
US 7543284B2 · Bolton · 2009 [cited by applicant]
US 9319425B2 · Giokas · 2016 [cited by applicant]
US 9679454B2 · Mishra · 2017 [cited by applicant]
US 9787800B2 · e Costa · 2017 [cited by applicant]
US 9813512B2 · Wilbur · 2017 [cited by applicant]
US 9818127B2 · Iyoob · 2017 [cited by applicant]
US 9832205B2 · Santhi · 2017 [cited by applicant]
US 9860368B2 · Aggarwal · 2018 [cited by applicant]
US 10542031B2 · Petry · 2020 [cited by applicant]
US 10853733B2 · Fadell · 2020 [cited by applicant]
US 10896195B2 · Sato · 2021 [cited by applicant]
US 10924548B1 · Karumbunathan · 2021 [cited by applicant]
US 11063821B2 · Cabral · 2021 [cited by applicant]
US 11252664B2 · Lee · 2022 [cited by applicant]
US 11546925B2 · Kang · 2023 [cited by applicant]
US 11563766B2 · Petry · 2023 [cited by applicant]
US 20090138847A1 · Beckwith · 2009 [cited by examiner]
US 20170124487A1 · Szeto · 2017 [cited by examiner]
US 20180143058A1 · Galron · 2018 [cited by applicant]
US 20200344185A1 · Singaraju · 2020 [cited by applicant]
US 20210081432A1 · Grunwald · 2021 [cited by applicant]
US 20210144517A1 · Guim Bernat · 2021 [cited by applicant]
US 20220019419A1 · Jonna · 2022 [cited by examiner]
US 20220187841A1 · Ebrahimi Afrouzi · 2022 [cited by applicant]
US 20220188098A1 · Hicks · 2022 [cited by examiner]
US 20250061089A1 · Seck · 2025 [cited by examiner]