IP Library › Granted Patent US 12,475,387
Granted Patent B2
US 12,475,387 · App. 18/651,233 · Granted Nov 18, 2025

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
G06N5/025G06F16/36G06F18/214G06F18/23G06N20/00
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 12,475,387
App. No.
18/651,233
Granted
Nov 18, 2025
Kind
B2
Abstract

One embodiment provides a method for generating a digital standard utilizing a trained machine-learning model, the method including: training at least one machine-learning model to generate digital standards from underlying standards utilizing a schema, wherein the training includes: receiving, for unstructured information within the underlying standards, a plurality of annotated underlying standards including a set of underlying standards having annotations identifying a classification of conceptual units within the set of underlying standards and corresponding to the schema; and teaching, for structured information within the underlying standards, the at least one machine-learning model patterns delineating information as belonging to conceptual units within the schema; and deploying the at least one trained machine-learning model to convert a second set of underlying standards to the digital standards, wherein the second set of underlying standards is different than the set of underlying standards. Other aspects are described and claimed.

Claims (35)

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

training at least one machine-learning model to generate digital standards from underlying standards utilizing a schema that identifies a format of a digital standard and provides a functionality to the digital standard, wherein the training comprises:

receiving, for unstructured information within the underlying standards, a plurality of annotated underlying standards comprising a set of underlying standards having annotations identifying a classification of conceptual units within the set of underlying standards and corresponding to the schema; and

teaching, for structured information within the underlying standards, the at least one machine-learning model patterns delineating information as belonging to conceptual units within the schema; and

deploying the at least one trained machine-learning model to convert a second set of underlying standards to the digital standards, wherein the second set of underlying standards is different than the set of underlying standards.

2 . The method of claim 1 , wherein the schema identifies a format of the digital standard and provides a functionality to the digital standard.

3 . The method of claim 1 , wherein the conceptual units comprise a unit of information contained within the set of underlying standard.

4 . The method of claim 1 , wherein the training comprises training the machine-learning model to recognize contextual information surrounding a conceptual unit.

5 . The method of claim 1 , wherein the receiving a plurality of annotated underlying standards comprises extracting, using the at least one machine-learning model and during the training, conceptual units from the plurality of annotated underlying standards and accessing an annotation corresponding to each of the extracted conceptual units.

6 . The method of claim 1 , wherein the teaching comprises extracting, using the at least one machine-learning model and during the training, information within the structured information and accessing a classification corresponding to the information.

7 . The method of claim 1 , wherein the training comprises training the at least one machine-learning model utilizing regular expression patterns.

8 . The method of claim 1 , comprising classifying, utilizing the at least one trained machine-learning model, extracted conceptual units from the second set of underlying standards based upon the schema and storing the classifying conceptual units into a data repository as defined by the schema.

9 . The method of claim 1 , comprising displaying a digital standard corresponding to a selected of the second set of underlying standard in a digital standard user interface.

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:

train at least one machine-learning model to generate digital standards from underlying standards utilizing a schema that identifies a format of a digital standard and provides a functionality to the digital standard, wherein the training comprises:

receiving, for unstructured information within the underlying standards, a plurality of annotated underlying standards comprising a set of underlying standards having annotations identifying a classification of conceptual units within the set of underlying standards and corresponding to the schema; and

teaching, for structured information within the underlying standards, the at least one machine-learning model patterns delineating information as belonging to conceptual units within the schema; and

deploy the at least one trained machine-learning model to convert a second set of underlying standards to the digital standards, wherein the second set of underlying standards is different than the set of underlying standards.

12 . The system of claim 11 , wherein the schema identifies a format of the digital standard and provides a functionality to the digital standard.

13 . The system of claim 11 , wherein the conceptual units comprise a unit of information contained within the set of underlying standard.

14 . The system of claim 11 , wherein the training comprises training the machine-learning model to recognize contextual information surrounding a conceptual unit.

15 . The system of claim 11 , wherein the receiving a plurality of annotated underlying standards comprises extracting, using the at least one machine-learning model and during the training, conceptual units from the plurality of annotated underlying standards and accessing an annotation corresponding to each of the extracted conceptual units.

16 . The system of claim 11 , wherein the teaching comprises extracting, using the at least one machine-learning model and during the training, information within the structured information and accessing a classification corresponding to the information.

17 . The system of claim 11 , wherein the training comprises training the at least one machine-learning model utilizing regular expression patterns.

18 . The system of claim 11 , comprising displaying a digital standard corresponding to a selected of the second set of underlying standard in a digital standard user interface.

19 . The system of claim 11 , comprising refining the at least one trained machine-learning model utilizing subsequently classified extracted conceptual units.

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 trains at least one machine-learning model to generate digital standards from underlying standards utilizing a schema that identifies a format of a digital standard and provides a functionality to the digital standard, wherein the training comprises:

receiving, for unstructured information within the underlying standards, a plurality of annotated underlying standards comprising a set of underlying standards having annotations identifying a classification of conceptual units within the set of underlying standards and corresponding to the schema; and

teaching, for structured information within the underlying standards, the at least one machine-learning model patterns delineating information as belonging to conceptual units within the schema; and

code that deploys the at least one trained machine-learning model to convert a second set of underlying standards to the digital standards, wherein the second set of underlying standards is different than the set of underlying standards.

Assignments (3)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 1, 2024
From: ZIEGENFUSS, AUDRA
To: SAE INTERNATIONAL
Reel/Frame 067280/0076 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 1, 2024
From: GAUR, DIVYESH; DORRONSORO, UXUE ZURUTUZA; BELOVA, ANNA; BHAVE, ROSHAN
To: COGNISTIC LLC
Reel/Frame 067280/0237 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 1, 2024
From: COGNISTIC LLC
To: SAE INTERNATIONAL
Reel/Frame 067280/0613 →
Continuity (3)
Continuation 18193147 · Mar 30, 2023
Continuation 16905559 · Jun 18, 2020
Related Publication 20240281675A1 · Aug 22, 2024
References Cited (20)
US 11328025B1 · Cobb et al. · 2022 [cited by applicant]
US 11393024B1 · Kodihalli · 2022 [cited by applicant]
US 11481906B1 · Narayanan · 2022 [cited by examiner]
US 11556579B1 · Bhatia et al. · 2023 [cited by applicant]
US 12204506B1 · Aliamiri · 2025 [cited by examiner]
US 20140074760A1 · Boldyrev et al. · 2014 [cited by applicant]
US 20170169103A1 · Juneja et al. · 2017 [cited by applicant]
US 20180137107A1 · Buccapatnam Tirumala et al. · 2018 [cited by applicant]
US 20200050949A1 · Sundararaman et al. · 2020 [cited by applicant]
US 20200053175A1 · Bodman et al. · 2020 [cited by applicant]
US 20200142856A1 · Neelamana · 2020 [cited by applicant]
US 20200151392A1 · Crabtree et al. · 2020 [cited by applicant]
US 20200202997A1 · Hadad · 2020 [cited by examiner]
US 20200218719A1 · Eifert · 2020 [cited by examiner]
US 20200251091A1 · Zhao · 2020 [cited by applicant]
US 20210279562A1 · Cmielowski · 2021 [cited by examiner]
US 20210303638A1 · Zhong · 2021 [cited by examiner]
US 20210334275A1 · Smart · 2021 [cited by examiner]
US 20220180066A1 · Wu · 2022 [cited by applicant]
Hackelbusch, Richard, International Search Report for PCT/US2021/037858, Oct. 1, 2021, 3 pages. [cited by applicant]