IP Library › Granted Patent US 12,620,206
Granted Patent B2
US 12,620,206 · App. 18/692,076 · Granted May 5, 2026

Training data synthesis for machine learning

Inventors: Atul Laxman Katole (Houston, TX); Purnaprajna Raghavendra Mangsuli (Pune, IN); Hiren Maniar (Houston, TX)
Assignee: SCHLUMBERGER TECHNOLOGY CORPORATION
G06V10/774G06V10/72G06V10/82G06F16/24522
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 12,620,206
App. No.
18/692,076
Granted
May 5, 2026
Kind
B2
Abstract

A method can include generating a plurality of synthetic objects and associated labels using a trained first machine learning system that is trained to generate a synthetic object based at least in part on a feature of a labeled object, an assigned label that represents the feature, and stochastic variation input; training a second machine learning model to predict labels for features of objects based at least in part on the plurality of synthetic objects and associated labels; and predicting a label for an unlabeled feature of an object using the second machine learning model.

Claims (59)

1 . A method comprising:

generating a plurality of synthetic objects and associated labels using a trained first machine learning system that is trained to generate a synthetic object based at least in part on a feature of a labeled object, an assigned label that represents the feature, and stochastic variation input, wherein the synthetic objects include a stochastic variation output, wherein the stochastic variation input comprises single channel images including uncorrelated Gaussian noise, and wherein the stochastic variation output comprises one or more of:

erased or partially erased gridlines;

width and intensity variations in the gridlines;

noise on the gridlines;

intensity variation in curves; and

width variation in the curves;

training a second machine learning model to predict labels for features of objects based at least in part on the plurality of synthetic objects and associated labels; and

predicting a label for an unlabeled feature of an object using the second machine learning model.

2 . The method of claim 1 , further comprising:

determining an uncertainty associated with labeling the unlabeled feature in the object using the trained second machine learning model;

determining that the uncertainty is greater than a predetermined value;

in response to determining that the uncertainty is greater than the predetermined value, soliciting an input of one or more training pairs of objects having the unlabeled feature of the object and an assigned label associated therewith;

generating a new plurality of synthetic objects and associated labels using the trained first machine learning system and the one or more training pairs of objects; and

training the second machine learning model to predict labels for features of objects based at least in part on the plurality of new synthetic objects and associated labels.

3 . The method of claim 1 , wherein the labeled object comprises a well log, wherein the feature comprises one or more of a header section, a depth track, and a plot segment, and wherein training the first machine learning model comprises training the first machine learning model to generate synthetic objects having variations of the one or more of the header section, the depth track, and the plot segment based on the labeled object.

4 . The method of claim 3 , wherein the variations include different relative locations for one or more of the header section, the depth track, and the plot segment in the individual synthetic objects.

5 . The method of claim 1 , wherein the labeled object comprises a plot of a well log or a seismic survey log, wherein the feature comprises one or more of a curve shape, a number of curves, a range of values, and a line style, and wherein training the first machine learning model comprises training the first machine learning model to generate synthetic objects having variations of the one or more of the curve shape, the number of curves, the range of values, and the line style.

6 . The method of claim 1 , wherein the labeled object comprises a header section of a well log, wherein the feature comprises a line style, units, or a scale in the header section, and wherein training the first machine learning model comprises training the first machine learning model to generate synthetic objects having variations of the one or more of the line style, the units, or the scale.

7 . The method of claim 6 , wherein the variations include different relative locations for display of the line style, the units, or the scale in the individual synthetic objects.

8 . The method of claim 1 , wherein the labeled object comprises a natural language search query, wherein the feature comprises one or more of a country, a state, an operator identity, and a field need, and wherein training the first machine learning model comprises training the first machine learning model to generate synthetic objects having variations of the one or more of the country, the state, the operator, and the field need, and wherein training the second machine learning model comprises training the second machine learning model to label natural language search queries as database-specific language search queries.

9 . The method of claim 1 , wherein the first machine learning system comprises a generative adversarial network.

10 . The method of claim 9 , wherein the generative adversarial network comprises a generator and a discriminator.

11 . A non-transitory, computer-readable medium storing instructions that, when executed by at least one processor of a computing system, cause the computing system to perform operations, the operations comprising:

generating a plurality of synthetic objects and associated labels using a trained first machine learning system that is trained to generate a synthetic object based at least in part on a feature of a labeled object, an assigned label that represents the feature, and stochastic variation input, wherein the synthetic objects include a stochastic variation output, wherein the stochastic variation input comprises single channel images including uncorrelated Gaussian noise, and wherein the stochastic variation output comprises one or more of:

erased or partially erased gridlines;

width and intensity variations in the gridlines;

noise on the gridlines;

intensity variation in curves; and

width variation in the curves;

training a second machine learning model to predict labels for features of objects based at least in part on the plurality of synthetic objects and associated labels; and

predicting a label for an unlabeled feature of an object using the second machine learning model.

12 . The medium of claim 11 , wherein the operations further comprise:

determining an uncertainty associated with labeling the unlabeled feature in the object using the trained second machine learning model;

determining that the uncertainty is greater than a predetermined value;

in response to determining that the uncertainty is greater than the predetermined value, soliciting an input of one or more training pairs of objects having the feature of the unlabeled object and an assigned label associated therewith;

generating a new plurality of synthetic objects and associated labels using the trained first machine learning system and the one or more training pairs of objects; and

training the second machine learning model to predict labels for features of objects based at least in part on the plurality of new synthetic objects and associated labels.

13 . The medium of claim 11 , wherein the labeled object comprises a well log, wherein the feature comprises one or more of a header section, a depth track, and a plot segment, and wherein training the first machine learning model comprises training the first machine learning model to generate synthetic objects having variations of the one or more of the header section, the depth track, and the plot segment based on the labeled object.

14 . The medium of claim 11 , wherein the labeled object comprises a plot of a well log or a seismic survey log, wherein the feature comprises one or more of a curve shape, a number of curves, a range of values, and a line style, and wherein training the first machine learning model comprises training the first machine learning model to generate synthetic objects having variations of the one or more of the curve shape, the number of curves, the range of values, and the line style.

15 . The medium of claim 11 , wherein the labeled object comprises a header section of a well log, wherein the feature comprises a line style, units, or a scale in the header section, wherein training the first machine learning model comprises training the first machine learning model to generate synthetic objects having variations of the one or more of the line style, the units, and the scale, and wherein the variations include different relative locations for display of the line style, the units, and the scale in the individual synthetic objects.

16 . The medium of claim 11 , wherein the labeled object comprises a natural language search query, wherein the feature comprises one or more of a country, a state, an operator identity, and a field need, and wherein training the first machine learning model comprises training the first machine learning model to generate synthetic objects having variations of the one or more of the country, the state, the operator, and the field need, and wherein training the second machine learning model comprises training the second machine learning model to label natural language search queries as database-specific language search queries.

17 . A computing system, comprising:

one or more processors; and

a memory system including one or more non-transitory computer-readable media storing instructions that, when executed by at least one of the one or more processors, cause the computing system to perform operations, the operations comprising:

generating a plurality of synthetic objects and associated labels using a trained first machine learning system that is trained to generate a synthetic object based at least in part on a feature of a labeled object, an assigned label that represents the feature, and stochastic variation input, wherein the synthetic objects include a stochastic variation output, wherein the stochastic variation input comprises single channel images including uncorrelated Gaussian noise, and wherein the stochastic variation output comprises one or more of:

erased or partially erased gridlines;

width and intensity variations in the gridlines;

noise on the gridlines;

intensity variation in curves; and

width variation in the curves;

training a second machine learning model to predict labels for features of objects based at least in part on the plurality of synthetic objects and associated labels; and

predicting a label for an unlabeled feature of an object using the second machine learning model.

18 . The computing system of claim 17 , wherein the operations further comprise:

determining an uncertainty associated with labeling the unlabeled feature in the object using the trained second machine learning model;

determining that the uncertainty is greater than a predetermined value;

in response to determining that the uncertainty is greater than the predetermined value, soliciting an input of one or more training pairs of objects having the unlabeled feature of the object and an assigned label associated therewith;

generating a new plurality of synthetic objects and associated labels using the trained first machine learning system and the one or more training pairs of objects; and

training the second machine learning model to predict labels for features of objects based at least in part on the plurality of new synthetic objects and associated labels.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 25, 2024
From: KATOLE, ATUL LAXMAN; MANGSULI, PURNAPRAJNA RAGHAVENDRA; MANIAR, HIREN
To: SCHLUMBERGER TECHNOLOGY CORPORATION
Reel/Frame 066886/0054 →
Continuity (2)
Provisional Application 63261156 · Sep 14, 2021
Related Publication 20240355100A1 · Oct 24, 2024
References Cited (38)
US 9911210B1 · Witte · 2018 [cited by examiner]
US 10095984B1 · Venter · 2018 [cited by applicant]
US 20170371856A1 · Can et al. · 2017 [cited by applicant]
US 20180033147A1 · Becker et al. · 2018 [cited by applicant]
US 20180253873A1 · Witte · 2018 [cited by applicant]
US 20190043172A1 · Chui et al. · 2019 [cited by applicant]
US 20190180115A1 · Zou · 2019 [cited by applicant]
US 20190197358A1 · Madani et al. · 2019 [cited by applicant]
US 20190302290A1 · Alwon · 2019 [cited by examiner]
US 20200335086A1 · Paraskevopoulos et al. · 2020 [cited by applicant]
US 20210097371A1 · Puscas · 2021 [cited by examiner]
US 20210158104A1 · Wu · 2021 [cited by examiner]
US 20210165938A1 · Bailey · 2021 [cited by applicant]
US 20210174131A1 · Schwartz · 2021 [cited by examiner]
US 20220067737A1 · Wittenbach · 2022 [cited by examiner]
US 20230128933A1 · Laxman et al. · 2023 [cited by applicant]
CN 110148088A · 2019 [cited by applicant]
WO 2018148492A1 · 2018 [cited by applicant]
H. Xiong and R. Sun, “Transferable Natural Language Interface to Structured Queries Aided by Adversarial Generation,” 2019 IEEE 13th International Conference on Semantic Computing (ICSC), Newport Beach, CA, USA, 2019, p… [cited by examiner]
Lu et al., “Automated analysis of images in documents for intelligent document search”, International Journal on Document Analysis and Recognition (IJDAR), 12.2, pp. 65-81, 2009. [cited by applicant]
Svendsen, “Chart detection and recognition in graphics intensive business documents”, Dissertation, 2015, 166 pages. [cited by applicant]
Liu et al., “Review of chart recognition in document images”, Visualization and Data Analysis 2013, vol. 8654, International Society for Optics and Photonics, 2013, 8 pages. [cited by applicant]
International Search Report of International Patent Application No. PCT/US2021/020480 on Apr. 28, 2021, 6 pages. [cited by applicant]
Written Opinion of International Patent Application No. PCT/US2021/020480 on Apr. 28, 2021, 5 pages. [cited by applicant]
International Preliminary Report on Patentability of International Patent Application No. PCT/US2021/020480 dated Sep. 15, 2022, 8 pages. [cited by applicant]
Rafkind et al., “Exploring Text and Image Features to Classify Images in Bioscience Literature”, Proceedings of the BioNLP Workshop on Linking Natural Language Processing and Biology at HLT-NAACL 06, pp. 73-80, 2006. [cited by applicant]
Savva et al., “Revision: Automated classification, analysis and redesign of chart images”, Proceedings of the 24th annual ACM symposium on User interface software and technology, 11 pages, 2011. [cited by applicant]
Huang et al., “Chart Image Classification Using Multiple-Instance Learning”, 2007 IEEE Workshop on Applications of Computer Vision (WACV07), IEEE, 6 pages, 2007. [cited by applicant]
Kollem et al., “A review of image denoising and segmentation methods based on medical images”, International Journal of Machine Learning and Computing, vol. 9, No. 3, pp. 288-295, 2019. [cited by applicant]
Xing et al., “Deep CNN for removal of salt and pepper noise”, IET Image Processing, 13.9, pp. 1550-1560, 2019. [cited by applicant]
Huang et al., “a scalable deep learning platform for identifying geologic features from seismic attributes”, The Leading Edge, vol. 36, issue 3, pp. 249-256, 2017. [cited by applicant]
Wu et al., “Convolutional neural networks for fault interpretation in seismic images”, SEG Technical Program Exanded Abstracts 2018, Society of Exploration Geophysicists, pp. 1946-1950, 2018. [cited by applicant]
Extended Search Report issued in European Patent Application No. 21764087.9 dated Dec. 18, 2023, 6 pages. [cited by applicant]
International Search Report and Written Opinion of the PCT Application No. PCT/US2022/043485 dated Nov. 1, 2022, 9 pages. [cited by applicant]
Notice of Allowance issued in U.S. Appl. No. 17/908,633 dated Apr. 9, 2025, 32 pages. [cited by applicant]
Extended Search Report issued in European Patent Application No. 22870616.4 dated Apr. 30, 2025, 10 pages. [cited by applicant]
Xiong, H. et al., “Transferable Natural Language Interface to Strucured Queries aided by Adversarial Generation”, 2019 IEEE 13th International Conference on Semantic Computing, 2019, pp. 255-262. [cited by applicant]
Office Action issued in U.S. Appl. No. 17/908,633 dated Dec. 13, 2024, 16 pages. [cited by applicant]