IP Library › Granted Patent US 12,737,271
Granted Patent B2
US 12,737,271 · App. 18/899,343 · Granted Sep 15, 2026

Safety compliance for maintenance and operations of critical systems

Inventors: Robert S. Milligan (Erlanger, KY); Amy Forsee (Ashland, MO); Deepika Murthy Nath (Cary, NC); Kelly Ann Washburn (Naugatuck, CT)
Assignee: Kyndryl, Inc.
G06F11/3072G06F11/3476
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 12,737,271
App. No.
18/899,343
Granted
Sep 15, 2026
Kind
B2
Abstract

A method may include receiving a set of inputs; transforming the set of inputs into a set of corresponding waveforms; generating from the set of corresponding waveforms, a composite wave spectrum, including identifying a waveform sub-set corresponding to a time interval of the composite wave spectrum; determining based on a comparison of the waveform sub-set to a pattern repository, an anomaly exists within the waveform sub-set in response to determining the composite wave spectrum is an operational-type spectrum; analyzing the anomaly to determine an associated risk; logging based on the anomaly and the associated risk, an incident record; determining based on the anomaly, an approved change control exists; and executing the approved change control.

Claims (89)

1 . A method, comprising:

receiving, by a computing device, a set of inputs;

transforming, by the computing device, the set of inputs into a set of corresponding waveforms;

generating, by the computing device, from the set of corresponding waveforms, a composite wave spectrum comprising identifying a waveform sub-set corresponding to a time interval of the composite wave spectrum;

determining, by the computing device, based on a comparison of the waveform sub-set to a pattern repository, an anomaly exists within the waveform sub-set in response to determining the composite wave spectrum is an operational-type spectrum;

analyzing, by the computing device, the anomaly to determine an associated risk;

logging, by the computing device, based on the anomaly and the associated risk, an incident record;

determining, by a computing device, based on the anomaly, an approved change control exists; and

executing, by the computing device, the approved change control,

wherein the transforming the set of inputs into the set of corresponding waveforms comprises:

sampling frames from the set of inputs;

pixelating the sampled frames from the set of inputs; and

converting the pixelated frames to a frequency spectrum.

2 . The method of claim 1 , further comprising:

updating, by a computing device, the pattern repository to include a pattern within the composite wave spectrum in response to determining the composite wave spectrum is a training type spectrum; and

generating a training-type alert corresponding to the updated pattern repository.

3 . The method of claim 1 , further comprising:

executing a predefined action based on the associated risk in response to determining the emergency bypass applies,

wherein the analyzing the anomaly to determine the associated risk automatically occurs in response to determining that the anomaly exists.

4 . The method of claim 1 , further comprising:

determining, by the computing device, no approved change control exists in response to determining the emergency bypass does not apply;

opening, based on the incident record, an update change control ticket;

executing a predefined action based on the associated risk; and

tagging the frequency spectrum with a training flag.

5 . The method of claim 4 , wherein the predefined action comprises automatically locking out unauthorized access to a data center by preventing network communication with the data center.

6 . The method of claim 1 , further comprising:

completing, by the computing device, a set of predefined mitigation actions in response to determining the composite wave spectrum includes a classified pattern; and

generating a classified pattern alert corresponding to the completed predefined mitigation actions.

7 . The method of claim 1 , wherein the determining an approved change control exists based on the anomaly occurs in response to not receiving a user-initiated emergency bypass.

8 . The method of claim 1 , further comprising:

generating, by the computing device, an operational-type alert corresponding to an executed approved change control.

9 . The method of claim 1 , further comprising:

requesting, by the computing device, user classification and risk assessment of the unclassified pattern in response to determining the composite wave spectrum includes an unclassified pattern;

receiving, by the computing device, user classification of the unclassified pattern;

creating, by the computing device, a newly classified pattern based on the received unclassified pattern; and

storing, by the computing device, the newly classified pattern in the pattern repository.

10 . The method of claim 9 , further comprising:

completing, by the computing device, a set of mitigation actions in response to receiving classification and risk assessment of the unclassified pattern.

11 . The method of claim 1 , wherein the computing device includes software provided as a service in a cloud environment.

12 . A computer program product comprising one or more computer readable storage media having program instructions collectively stored on the one or more computer readable storage media, the program instructions executable to:

receive a set of inputs;

transform the set of inputs into a set of corresponding waveforms;

generate from the set of corresponding waveforms, a composite wave spectrum comprising identifying a waveform sub-set corresponding to a time interval of the composite wave spectrum;

determine, based on a comparison of the waveform sub-set to a pattern repository, an anomaly exists within the waveform sub-set in response to determining the composite wave spectrum is an operational-type spectrum;

analyze the anomaly to determine an associated risk;

log, based on the anomaly and the associated risk, an incident record;

determine, based on the anomaly, an approved change control exists; and

execute the approved change control,

wherein the transforming the set of inputs into the set of corresponding waveforms comprises:

sampling frames from the set of inputs;

pixelating the sampled frames from the set of inputs; and

converting the pixelated frames to a frequency spectrum.

13 . The method of claim 12 , wherein the program instructions are executable to:

update the pattern repository to include a pattern within the composite wave spectrum in response to determining the composite wave spectrum is a training type spectrum; and

generate a training-type alert corresponding to the updated pattern repository.

14 . The method of claim 12 , wherein the program instructions are executable to:

execute a predefined action based on the associated risk in response to determining the emergency bypass applies,

wherein the analyzing the anomaly to determine the associated risk automatically occurs to optimize computing resources in response to determining that the anomaly exists.

15 . The method of claim 12 , wherein the program instructions are executable to:

determine that no approved change control exists in response to determining the emergency bypass does not apply;

open, based on the incident record, an update change control ticket;

execute a predefined action based on the associated risk; and

tag the frequency spectrum with a training flag.

16 . The method of claim 12 , further comprising:

complete a set of predefined mitigation actions in response to determining the composite wave spectrum includes a classified pattern; and

generate a classified pattern alert corresponding to the completed predefined mitigation actions.

17 . The method of claim 12 , wherein the determining an approved change control exists based on the anomaly occurs in response to not receiving a user-initiated emergency bypass.

18 . The method of claim 12 , wherein the program instructions are executable to:

generate an operational-type alert corresponding to an executed approved change control.

19 . The method of claim 12 , wherein the program instructions are executable to:

request user classification and risk assessment of the unclassified pattern in response to determining the composite wave spectrum includes an unclassified pattern;

receive user classification of the unclassified pattern;

create a newly classified pattern based on the received unclassified pattern; and

store a newly classified pattern in the pattern repository.

20 . A system comprising:

a processor, a computer readable memory, one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions executable to:

receive a set of inputs;

transform the set of inputs into a set of corresponding waveforms;

generate from the set of corresponding waveforms, a composite wave spectrum comprising identifying a waveform sub-set corresponding to a time interval of the composite wave spectrum;

determine, based on a comparison of the waveform sub-set to a pattern repository, an anomaly exists within the waveform sub-set in response to determining the composite wave spectrum is an operational-type spectrum;

analyze the anomaly to determine an associated risk;

log, based on the anomaly and the associated risk, an incident record;

determine, based on the anomaly, an approved change control exists; and

execute the approved change control,

wherein the transforming the set of inputs into the set of corresponding waveforms comprises:

sampling frames from the set of inputs;

pixelating the sampled frames from the set of inputs;

converting the pixelated frames to a frequency spectrum; and

tagging the frequency spectrum with a training flag.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 27, 2024
From: MILLIGAN, ROBERT S.; FORSEE, AMY; NATH, DEEPIKA MURTHY; WASHBURN, KELLY ANN
To: KYNDRYL, INC.
Reel/Frame 068723/0650 →
Continuity (1)
Related Publication 20260093590A1 · Apr 2, 2026
References Cited (22)
US 5859811A · Miller et al. · 1999 [cited by applicant]
US 7359810B2 · Letts et al. · 2008 [cited by applicant]
US 7409320B2 · Wegerich · 2008 [cited by applicant]
US 8365019B2 · Sailer et al. · 2013 [cited by applicant]
US 8887286B2 · Dupont et al. · 2014 [cited by applicant]
US 10692032B2 · Datta Ray · 2020 [cited by applicant]
US 11283748B2 · Snapir et al. · 2022 [cited by applicant]
US 20070094195A1 · Wang · 2007 [cited by applicant]
US 20090043522A1 · Liggiero, III et al. · 2009 [cited by applicant]
US 20160125068A1 · Dongieux · 2016 [cited by applicant]
US 20160327595A1 · Reinders · 2016 [cited by examiner]
US 20190050942A1 · Dalal et al. · 2019 [cited by applicant]
US 20200159934A1 · Yamaguchi et al. · 2020 [cited by applicant]
US 20210019211A1 · Sghiouer · 2021 [cited by examiner]
US 20210109497A1 · Man et al. · 2021 [cited by applicant]
US 20230153389A1 · Bickel · 2023 [cited by examiner]
US 20230195589A1 · Calabria · 2023 [cited by applicant]
US 20240178667A1 · Pankova · 2024 [cited by examiner]
US 20250190564A1 · Hassan · 2025 [cited by examiner]
CN 117896506 · 2024 [cited by applicant]
O. Rajabi Shishvan, D.-S. Zois and T. Soyata, “Machine Intelligence in Healthcare and Medical Cyber Physical Systems: A Survey,” in IEEE Access, vol. 6, pp. 46419-46494, 2018, doi: 10.1109/ACCESS.2018.2866049 (Year: 201… [cited by examiner]
Cheng et al., “Vision-based Monitoring Of Site Safety Compliance Based On Worker Re-identification And Personal Protective Equipment Classification”, Automation in Construction, vol. 139. https://www.sciencedirect.com/s… [cited by applicant]