IP Library Granted Patent US 11,645,550
Granted Patent B2
US 11,645,550 · App. 16/905,559 · Granted May 9, 2023

Generation of digital standards using machine-learning model

Inventors: Divyesh Gaur (Pittsburgh, PA); Uxue Zurutuza Dorronsoro (Pittsburgh, PA); Anna Belova (Pittsburgh, PA); Audra Ziegenfuss (Baden, PA); Roshan Bhave (Pittsburgh, PA)
Assignee: SAE International
G06N5/025G06K9/6218G06K9/6256G06N20/00
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 11,645,550
App. No.
16/905,559
Granted
May 9, 2023
Kind
B2
Abstract

One embodiment provides a method for generating a digital standard utilizing a trained machine-learning model, the method including: receiving an underlying standard; extracting conceptual units from the underlying standard; classifying, using at least one trained machine-learning model, at least a portion of the extracted conceptual units into one of a plurality of classification groups, wherein each of the classification groups identifies a function of the extracted conceptual units, included within a given classification group, within the underlying standard; wherein the classifying comprises classifying conceptual units from the underlying standard based upon sections of a schema corresponding to a digital standard; and storing the classified extracted conceptual units into a data repository based upon the schema. Other aspects are described and claimed.

Claims (38)

1. A method for generating a digital standard utilizing a trained machine-learning model, the method comprising:

receiving an underlying standard identifying requirements and data of an object or service and being issued by a governing body associated with the underlying standard;

extracting conceptual units from the underlying standard, wherein a conceptual unit comprises a unit of information contained within the underlying standard;

classifying, using at least one trained machine-learning model, at least a portion of the extracted conceptual units into one of a plurality of classification groups, wherein each of the classification groups identifies a function of the extracted conceptual units, included within a given classification group, within the underlying standard;

wherein the classifying comprises classifying conceptual units from the underlying standard based upon sections of a schema corresponding to a digital standard, wherein the schema identifies a format of the digital standard and provides a functionality to the digital standard; and

storing the classified extracted conceptual units into a data repository based upon the schema.

2. The method of claim 1 , comprising displaying a digital standard corresponding to the underlying standard in a digital standard user interface, wherein the displaying comprises accessing the classified extracted conceptual units from the data repository and displaying the classified extracted conceptual units in a user interface format based upon the schema.

3. The method of claim 1 , wherein the machine-learning model is trained utilizing annotated underlying standards.

4. The method of claim 1 , comprising labeling, using the at least one trained machine-learning model, the extracted conceptual units with a sub-type of the function corresponding to a given extracted conceptual units.

5. The method of claim 1 , wherein the conceptual units comprise at least one of sentences and table components.

6. The method of claim 1 , wherein the classifying is based upon a context of a given extracted conceptual unit within the underlying standard.

7. The method of claim 1 , wherein the classifying comprises identifying, utilizing expression patterns, attributes of extracted conceptual unit.

8. The method of claim 1 , wherein the machine-learning model is trained utilizing patterns.

9. The method of claim 1 , wherein the classifying comprises identifying, utilizing aliasing, extracted conceptual units representing information having similar attributes.

10. The method of claim 1 , comprising refining the at least one trained machine-learning model utilizing subsequently classified extracted conceptual units.

11. A system for generating a digital standard utilizing a trained machine-learning model, the system comprising:

one or more processors;

a memory device that stores instructions executable by the processor to:

receive an underlying standard identifying requirements and data of an object or service and being issued by a governing body associated with the underlying standard;

extract conceptual units from the underlying standard, wherein a conceptual unit comprises a unit of information contained within the underlying standard;

classify, using at least one trained machine-learning model, at least a portion of the extracted conceptual units into one of a plurality of classification groups, wherein each of the classification groups identifies a function of the extracted conceptual units, included within a given classification group, within the underlying standard;

wherein the classifying comprises classifying conceptual units from the underlying standard based upon sections of a schema corresponding to a digital standard, wherein the schema identifies a format of the digital standard and provides a functionality to the digital standard; and

store the classified extracted conceptual units into a data repository based upon the schema.

12. The system of claim 11 , comprising displaying a digital standard corresponding to the underlying standard in a digital standard user interface, wherein the displaying comprises accessing the classified extracted conceptual units from the data repository and displaying the classified extracted conceptual units in a user interface format based upon the schema.

13. The system of claim 11 , wherein the machine-learning model is trained utilizing annotated underlying standards.

14. The system of claim 11 , comprising labeling, using the at least one trained machine-learning model, the extracted conceptual units with a sub-type of the function corresponding to a given extracted conceptual units.

15. The system of claim 11 , wherein the conceptual units comprise at least one of sentences and table components.

16. The system of claim 11 , wherein the classifying is based upon a context of a given extracted conceptual unit within the underlying standard.

17. The system of claim 11 , wherein the classifying comprises identifying, utilizing expression patterns, attributes of extracted conceptual unit.

18. The system of claim 11 , wherein the machine-learning model is trained utilizing patterns.

19. The system of claim 11 , wherein the classifying comprises identifying, utilizing aliasing, extracted conceptual units representing information having similar attributes.

20. A product for generating a digital standard utilizing a trained machine-learning model, the product comprising:

a storage device that stores code, the code being executable by one or more processors and comprising:

code that receives an underlying standard identifying requirements and data of an object or service and being issued by a governing body associated with the underlying standard;

code that extracts conceptual units from the underlying standard, wherein a conceptual unit comprises a unit of information contained within the underlying standard;

code that classifies, using at least one trained machine-learning model, at least a portion of the extracted conceptual units into one of a plurality of classification groups, wherein each of the classification groups identifies a function of the extracted conceptual units, included within a given classification group, within the underlying standard;

wherein the classifying comprises classifying conceptual units from the underlying standard based upon sections of a schema corresponding to a digital standard, wherein the schema identifies a format of the digital standard and provides a functionality to the digital standard; and

code that stores the classified extracted conceptual units into a data repository based upon the schema.

Assignments (3)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 3, 2022
From: COGNISTIC LLC
To: SAE INTERNATIONAL
Reel/Frame 061642/0427 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 24, 2021
From: ZIEGENFUSS, AUDRA
To: SAE INTERNATIONAL
Reel/Frame 056327/0682 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 24, 2021
From: GAUR, DIVYESH; ZURUTUZA DORRONSORO, UXUE; BELOVA, ANNA; BHAVE, ROSHAN
To: COGNISTIC LLC
Reel/Frame 056327/0854 →
Continuity (1)
Related Publication 20210397979A1 · Dec 23, 2021
Cited By (1)
US 1,107,057