IP Library › Granted Patent US 12,293,611
Granted Patent B2
US 12,293,611 · App. 17/394,022 · Granted May 6, 2025

Data extraction for machine learning systems and methods

Inventor: Nathan Thomas North (Seattle, WA)
Assignee: Transportation IP Holdings, LLC
G07C5/006G05B23/0243G06F30/27G07C5/008G07C5/0825G07C5/0833
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 12,293,611
App. No.
17/394,022
Filed
Aug 4, 2021
Granted
May 6, 2025
Kind
B2
Art Unit
3747
USPC
701/31.4
Abstract

A system (e.g., a maintenance system) includes a maintenance task input unit and one or more processors. The maintenance task input unit is configured to generate plural input data groups corresponding to a maintenance task. Each of the input data groups is in a corresponding one of plural formats. The one or more processors are coupled to the maintenance task input unit and configured to obtain the plural input data groups from the maintenance task input unit. The one or more processors are configured to identify a particular format of the formats for each input data group, and to prepare an intermediate representation of the input representation based on the particular format that is identified. Also the one or more processors are configured to modify the intermediate representation to provide a model input having a common format. The one or more processors are configured to modify intermediate representations corresponding to each of the input data groups to the common format, and to provide the model input to a maintenance system artificial intelligence modeler that is configured to use the model input to at least one of develop or use a model using the model input for vehicle maintenance.

Claims (42)

1. A system comprising:

a maintenance task input unit configured to generate a plurality of input data groups, wherein the plurality of input data groups correspond to a maintenance task performed on a component of a vehicle, wherein each of the plurality of input data groups corresponds to a different format of a plurality of formats, and wherein the maintenance task input unit comprises one or more of a keyboard, a manual input peripheral device, a camera, a microphone, or any combination thereof; and

one or more processors communicably coupled to the maintenance task input unit, the one or more processors are configured to:

obtain the plurality of input data groups from the maintenance task input unit;

identify a particular format of the plurality of formats for each of the plurality of input data groups;

generate a plurality of intermediate representations corresponding to each of the plurality of input data groups, wherein the plurality of intermediate representations are based on the particular format for each of the plurality of input data groups;

modify the plurality of intermediate representations corresponding to each of the plurality of input data groups to provide a plurality of model inputs, wherein each of the plurality of model inputs are modified to have a common format; and

evaluate the plurality of model inputs with a maintenance system artificial intelligence modeler, wherein the maintenance system artificial intelligence modeler compares the plurality of model inputs to a completed maintenance task; and

determine a sufficiency assessment of the maintenance task.

2. The system of claim 1 , wherein the one or more processors are configured to prepare the plurality of intermediate representations by generating an n-dimensional array having an n-dimensional array format corresponding to the particular format for each of the plurality of input data groups.

3. The system of claim 2 , wherein the common format defines a common n-dimensional array format.

4. The system of claim 1 , wherein the plurality of formats include at least one of an image format, a text format, a video format, or an audio format.

5. The system of claim 1 , wherein the one or more processors are configured to modify the plurality of intermediate representations to generate the plurality of model inputs by altering at least one of a size or a shape of an n-dimensional array of the plurality of intermediate representations.

6. The system of claim 1 , wherein the maintenance task input unit is configured to generate the plurality of input data groups by at least one of acquiring image information or acquiring audio information corresponding to the maintenance task performed on the component of the vehicle.

7. The system of claim 1 , wherein the one or more processors are further configured to perform a responsive task based on the sufficiency assessment of the maintenance task.

8. The system of claim 1 , wherein the sufficiency assessment of the maintenance task comprises completed satisfactory, completed unsatisfactory, or incomplete.

9. A method comprising:

obtaining a plurality of input data groups of input information corresponding to a maintenance task performed on a component of a vehicle, wherein each of the plurality of input data groups corresponds to a different format of a plurality of formats;

identifying a particular format of the plurality of formats for each of the plurality of input data groups;

generating a plurality of intermediate representations of the plurality of input data groups based on the particular format that is identified for each of the plurality of input data groups;

modifying the plurality of intermediate representations corresponding to the plurality of input data groups to provide a plurality of model inputs, wherein each of the plurality of model inputs are modified to have a common format;

evaluating the plurality of model inputs with a maintenance system artificial intelligence modeler, wherein the maintenance system artificial intelligence modeler compares the plurality of model inputs to a maintenance task; and

determining a sufficiency assessment of the maintenance task.

10. The method of claim 9 , wherein preparing the plurality of intermediate representations comprises generating an n-dimensional array having an n-dimensional array format corresponding to the particular format for each of the plurality of input data groups.

11. The method of claim 10 , wherein the common format defines a common n-dimensional array format.

12. The method of claim 9 , wherein the plurality of formats include at least one of an image format, a text format, a video format, or an audio format.

13. The method of claim 9 , wherein modifying the plurality of intermediate representations to provide generate the plurality of model inputs by altering at least one of a size or a shape of an n-dimensional array of the plurality of intermediate representations.

14. The method of claim 9 , wherein obtaining the plurality of input data groups comprises at least one of acquiring an image file or acquiring an audio file corresponding to the maintenance task performed on the component of the vehicle.

15. The method of claim 9 , further comprising:

performing a responsive task based on the sufficiency assessment of the maintenance task, wherein the sufficiency assessment is completed unsatisfactory or incomplete.

16. A method comprising:

obtaining maintenance task data for a maintenance task on a component of a vehicle;

generating an input data including input information corresponding to the maintenance task data;

obtaining, by one or more processors, the input data of the input information, wherein the input data corresponds to a plurality of formats;

identifying a particular format of the plurality of formats for the input data;

generating an intermediate representation of the input data based on the particular format that is identified;

modifying the intermediate representation to provide a model input having a common format;

evaluating the model input with a maintenance system artificial intelligence modeler, wherein the maintenance system artificial intelligence modeler compares the model input to a maintenance task; and

determining a sufficiency assessment of the maintenance task.

17. The method of claim 16 , wherein obtaining the input data comprises at least one of acquiring an image file or acquiring an audio file corresponding to the maintenance task.

18. The method of claim 16 , further comprising:

performing a responsive task based on the sufficiency assessment of the maintenance task, wherein the sufficiency assessment is completed unsatisfactory or incomplete.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 4, 2021
From: NORTH, NATHAN THOMAS
To: TRANSPORTATION IP HOLDINGS, LLC
Reel/Frame 057081/0893 →
Continuity (2)
Provisional Application 63062438 · Aug 6, 2020
Related Publication 20220044494A1 · Feb 10, 2022
References Cited (34)
US 8674993B1 · Fleming · 2014 [cited by examiner]
US 10048995B1 · Dikhit · 2018 [cited by examiner]
US 11244233B2 · Sturtivant · 2022 [cited by examiner]
US 20020169735A1 · Kil · 2002 [cited by examiner]
US 20070094181A1 · Tayebnejad · 2007 [cited by examiner]
US 20080114474A1 · Campbell · 2008 [cited by examiner]
US 20130124465A1 · Pingel · 2013 [cited by examiner]
US 20130212420A1 · Lawson · 2013 [cited by examiner]
US 20140047107A1 · Maturana · 2014 [cited by examiner]
US 20140222522A1 · Chait · 2014 [cited by examiner]
US 20140335480A1 · Asenjo · 2014 [cited by examiner]
US 20140337000A1 · Asenjo · 2014 [cited by examiner]
US 20140337429A1 · Asenjo · 2014 [cited by examiner]
US 20150105968A1 · Ho · 2015 [cited by examiner]
US 20150120009A1 · Killian · 2015 [cited by examiner]
US 20150277406A1 · Maturana · 2015 [cited by examiner]
US 20150281356A1 · Maturana · 2015 [cited by examiner]
US 20160179599A1 · Deshpande · 2016 [cited by examiner]
US 20160299999A1 · James · 2016 [cited by examiner]
US 20170308802A1 · Ramsøy · 2017 [cited by examiner]
US 20170351241A1 · Bowers · 2017 [cited by examiner]
US 20170358204A1 · Modica · 2017 [cited by examiner]
US 20180349433A1 · Baines · 2018 [cited by examiner]
US 20180356800A1 · Chao · 2018 [cited by examiner]
US 20200151611A1 · McGavran · 2020 [cited by examiner]
US 20200167643A1 · Bivens · 2020 [cited by examiner]
US 20200327371A1 · Sharma · 2020 [cited by examiner]
US 20210094561A1 · Jiang · 2021 [cited by examiner]
CN 103077163A · 2013 [cited by applicant]
Examination report No. 1 for corresponding Australian Patent Application 2021212073 mailed Jul. 7, 2022. [cited by applicant]
Second Examination Report mailed Oct. 24, 2022 for corresponding Australian Patent Application No. 2021212073 (4 pages). [cited by applicant]
Office Action for Japanese Patent Application No. 2021-129210 dated Oct. 31, 2022 (and English Translation). [cited by applicant]
Extended European Search Report mailed Jan. 5, 2022 for corresponding European Patent Application No. 21189870.5 (10 pages). [cited by applicant]
Office Action mailed Oct. 24, 2022 for corresponding European Patent Application No. 21 189 870.5 (4 pages). [cited by applicant]