IP Library › Granted Patent US 12,438,720
Granted Patent B2
US 12,438,720 · App. 18/304,518 · Granted Oct 7, 2025

Authenticating a system maintenance via a cognitive and blockchain-based process

Inventors: Lamogha Chiazor (Eastleigh, GB); Paritosh Ranjan (Kolkata, IN)
Assignee: International Business Machines Corporation
H04L9/32G06F40/40G06V20/44
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 12,438,720
App. No.
18/304,518
Granted
Oct 7, 2025
Kind
B2
Abstract

Embodiments of the present invention provide an approach for dynamically authenticating a performance of a maintenance process via a cognitive and blockchain-based verification technique. Specifically, a person performs a set of maintenance steps as defined by textual summaries stored in a first blockchain. While the person performs the maintenance steps, a video of her performing the steps is recorded. A textual summary for each frame of the video is generated and stored in a second blockchain. A first set of event-entity relationships and the second set of event-entity relationships are extracted from the blockchains and compared to determine a compliance value. Based on the comparison, a determination is made whether the person performed the maintenance process correctly (i.e., as listed in the predefined maintenance steps).

Claims (40)

1. A method for dynamically authenticating a performance of a maintenance process, comprising:

obtaining, by a processor, a set of textual summaries stored in a first blockchain, wherein the textual summaries include predefined instructions on performing the maintenance process;

generating, by the processor, a generated set of textual summaries from a video illustrating a performance of the maintenance process wherein each frame of the video is associated with a textual summary;

storing, by the processor, the generated set of textual summaries from the video in a second blockchain;

extracting, by the processor, a first set of event-entity relationships from the set of textual summaries stored in the first blockchain and a second set of event-entity relationships from the generated set of textual summaries stored in the second blockchain;

wherein the event is a behavior and the entity is an object associated with the performance;

comparing, by the processor, the first set of event-entity relationships and the second set of event-entity relationships to determine a compliance value; and

generating, by the processor, a notification based on the compliance value exceeding a predefined threshold indicating the maintenance process is performed with surety and correctness.

2. The method of claim 1 , further comprising removing, by the processor, any duplicates within the set of textual summaries from the video prior to storing the textual summaries in the second blockchain.

3. The method of claim 1 , wherein the entity is a replacement part of a system being maintained and the event is an action performed on the entity.

4. The method of claim 1 , wherein the event-entity relationships are extracted using a natural language processing technique.

5. The method of claim 1 , further comprising iterating, by the processor, through each event-entity relationship in the second set to determine if each event-entity relationship in the second set exists in the first set.

6. The method of claim 5 , further comprising generating, by the processor, the notification when at least one event-entity relationship in the second set does not exist in the first set.

7. A computing system for dynamically authenticating a performance of a maintenance process, comprising:

a processor;

a memory device coupled to the processor; and

a computer readable storage device coupled to the processor, wherein the storage device contains program code executable by the processor via the memory device to implement a method, the method comprising:

obtaining, by a processor, a set of textual summaries stored in a first blockchain, wherein the textual summaries include predefined instructions on performing the maintenance process;

generating, by the processor, a generated set of textual summaries from a video illustrating a performance of the maintenance process wherein each frame of the video is associated with a textual summary;

storing, by the processor, the generated set of textual summaries from the video in a second blockchain;

extracting, by the processor, a first set of event-entity relationships from the set of textual summaries stored in the first blockchain and a second set of event-entity relationships from the generated set of textual summaries stored in the second blockchain;

wherein the event is a behavior and the entity is an object associated with the performance;

comparing, by the processor, the first set of event-entity relationships and the second set of event-entity relationships to determine a compliance value; and

generating, by the processor, a notification based on the compliance value exceeding a predefined threshold indicating the maintenance process is performed with surety and correctness.

8. The computing system of claim 7 , further comprising removing, by the processor, any duplicates within the set of textual summaries from the video prior to storing the textual summaries in the second blockchain.

9. The computing system of claim 7 , wherein the entity is a replacement part of a system being maintained and the event is an action performed on the entity.

10. The computing system of claim 7 , wherein the event-entity relationships are extracted using a natural language processing technique.

11. The computing system of claim 7 , further comprising iterating, by the processor, through each event-entity relationship in the second set to determine if each event-entity relationship in the second set exists in the first set.

12. The computing system of claim 11 , further comprising generating, by the processor, the notification when at least one event-entity relationship in the second set does not exist in the first set.

13. A computer program product dynamically authenticating a performance of a maintenance process, the computer program product comprising a computer readable storage device, and program instructions stored on the computer readable storage device, to:

obtain, by a processor, a set of textual summaries stored in a first blockchain, wherein the textual summaries include predefined instructions on performing the maintenance process;

generate, by the processor, a set of textual summaries from a video illustrating a performance of the maintenance process wherein each frame of the video is associated with a textual summary;

store, by the processor, the generated set of textual summaries from the video in a second blockchain;

extract, by the processor, a first set of event-entity relationships from the set of textual summaries stored in the first blockchain and a second set of event-entity relationships from the generated set of textual summaries stored in the second blockchain wherein the event is a behavior and the entity is an object associated with the performance;

compare, by the processor, the first set of event-entity relationships and the second set of event-entity relationships to determine a compliance value; and

generate, by the processor, a notification based on the compliance value exceeding a predefined threshold indicating the maintenance process is performed with surety and correctness.

14. The computer program product of claim 13 , further comprising program instructions stored on the computer readable storage device to remove, by the processor, any duplicates within the set of textual summaries from the video prior to storing the textual summaries in the second blockchain.

15. The computer program product of claim 13 , wherein the entity is a replacement part of a system being maintained and the event is an action performed on the entity.

16. The computer program product of claim 13 , wherein the event-entity relationships are extracted using a natural language processing technique.

17. The computer program product of claim 13 further comprising program instructions stored on the computer readable storage device to iterate, by the processor, through each event-entity relationship in the second set to determine if each event-entity relationship in the second set exists in the first set and generating the notification when at least one event-entity relationship in the second set does not exist in the first set.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 21, 2023
From: CHIAZOR, LAMOGHA; RANJAN, PARITOSH
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 063398/0405 →
Continuity (1)
Related Publication 20240356749A1 · Oct 24, 2024
References Cited (11)
US 11308108B2 · Ishii et al. · 2022 [cited by applicant]
US 20200184739A1 · Nathan · 2020 [cited by examiner]
US 20220271915A1 · Turner · 2022 [cited by examiner]
US 20230199236A1 · McGill · 2023 [cited by examiner]
US 20240184769A1 · Nomani · 2024 [cited by examiner]
CN 115034409A · 2022 [cited by applicant]
IPCOM000249447D, “Method and System for Verifying Distributed Processor Vital Product Data (VPD) and Maintenance Procedures via Blockchain Transactions”, Feb. 27, 2017, 3 pages. [cited by applicant]
Abhishek Yadav et al., “Real Time Video to Text Summarization using Neural Network”, International Research Journal of Engineering and Technology (IRJET), vol. 7, Issue 12, Dec. 2020, 9 pages. [cited by applicant]
Ada Mode, “Natural Language Processing for Maintenance Optimisation”, Machine Learning, Feb. 12, 2021, 10 pages. [cited by applicant]
AMA Research & Media LLP, “Text-based Intelligent Virtual Assistant Market to Get a New Boost | Google, Apple, Vodafone Group”, Nov. 15, 2022, https://www.openpr.com/news/2806924/text-based-intelligent-virtual-assistant… [cited by applicant]
Shridhar et al., “ALFWorld”, https://alfworld.github.io/, Nov. 1, 2020, 3 pgs. [cited by applicant]