Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
DETAILED ACTION
This action is responsive to the Application filed on 03/16/2026
Claims 1-26 are pending in the case. Claims 1, 19-20 are independent claims. Claims 1, 19-20 have been currently amended. Claims 25-25 have been newly added.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
The term “approximately” in claim(s) 1 and 19–20 is a relative term which renders the claim indefinite. The term “approximately” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1, 11, 15 and 19-20 are rejected 35 U.S.C. 103 as being unpatentable over OSYPOV
et al. (US Pub No.: 20180106917 A1), hereinafter referred to as OSYPOV in view of “A Weakly-Supervised Approach to Seismic Structure Labeling”, Yazeed, 2017 and further in view of Aslan et al. (US Pub No.: 20170132528 A1), hereinafter referred to as Aslan.
With respect to claim 1, OSYPOV discloses:
A method, comprising: receiving a first trained machine model trained via unsupervised learning using unlabeled seismic image data (In paragraph [0026], OSYPOV disclose using the unsupervised machine learning model to receive/analyze seismic data. In paragraph [0033], the seismic data includes unlabeled data, the remaining portion of the seismic dataset.)
generating processed seismic image data by applying new seismic image data for [[a]] the geologic region to the first trained machine model (In paragraph [0036], OSYPOV disclose adding more information about the rock types, connections, and flow properties of seismic facies using a machine learning model (e.g., can be unsupervised learning model))
the second trained model predicting stratigraphy of a geologic region from seismic image data of the geologic region (In paragraph [0033], OSYPOV disclose a supervised machine learning for seismic facies interpretation, where a classifier learns from labeled seismic data (training set) to predict facies for unlabeled data, resulting in a precisely labeled facies distribution map.)
operating equipment associated with a well based on the predicted stratigraphy of the second trained machine model (In paragraph [0033], OSYPOV disclose the seismic dataset and set of facies labels are input to a supervised machine learning at operation 24. The labeled training dataset is first used to “train” a classifier; the classifier (learns from labeled seismic data (training set) to predict facies for unlabeled data) is then applied to the unlabeled input data in order to produce a facies distribution that is now specifically labeled.)
With respect to claim 1, OSYPOV do not specifically disclose:
receiving sparsely-labeled seismic image data comprising a plurality of labels acquired via an interactive interpretation process with a human expert interpreter, the sparsely-labeled seismic image data corresponding to a portion of a geologic region that is volumetrically less than approximately 1 percent of the geologic region as seismically imaged
building, as initialized from the first trained machine model, a second trained machine model via supervised learning, using only the processed seismic data from the unsupervised learning of the first trained machine model and the received plurality of labels without direct input of the new seismic image data to the second trained machine model
However, Yazeed is known to disclose:
Receiving sparsely-labeled seismic image data comprising a plurality of labels acquired via an interactive interpretation process with a human expert interpreter, the sparsely-labeled seismic image data corresponding to a portion of a geologic region that is volumetrically less than approximately 1 percent of the geologic region as seismically imaged (On page 1, (OBTAINING WEAK LABELS FOR SEISMIC IMAGES), Yazeed disclose obtaining one image-level label compared to potentially hundreds of thousands of pixel labels inherently corresponds to a very small fraction of the total data volume. )
OSYPOV and Yazeed are analogous pieces of art because both references concern seismic data via machine learning. Accordingly, it would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify OSYPOV, by identifying facies from seismic data via machine learning as taught by OSYPOV, with generating labeled data for applying machine learning techniques to computational seismic interpretation tasks as taught by Yazeed. The motivation for doing so would have been to use strong computer power to find patterns in data that people might miss, resulting in better classification of facies (See [0024] of OSYPOV.)
With respect to claim 1, OSYPOV and Yazeed does not disclose:
Building, as initialized from the first trained machine model, a second trained machine model via supervised learning, using only the processed seismic data from the unsupervised learning of the first trained machine model and the received plurality of labels without direct input of the new seismic image data to the second trained machine model
However, Aslan is known to disclose:
Building, as initialized from the first trained machine model, a second trained machine model via supervised learning, using only the processed seismic data from the unsupervised learning of the first trained machine model and the received plurality of labels without direct input of the new seismic image data to the second trained machine model, the second trained machine model predicting stratigraphy of the geologic region (In paragraph [0039], Aslan disclose passing output data from a first machine-learning model to the second machine learning model. The second machine learning model does not see the original labels of the training data. Even though Aslan does not disclose output data being “seismic data”, but OSYPOV discloses having seismic data.)
OSYPOV in view of Yazeed and Aslan are analogous pieces of art because both references concern machine learning. Accordingly, it would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, by creating a second machine learning model based on the first machine learning model as taught by Aslan. The motivation for doing so would have been to effectively generate high-quality pixel-level labels using only "rough" image-level labels (See (Page 3, Conclusion ) of Yazeed).
Regarding claim 11, OSYPOV in view of Yazeed and Aslan disclose elements of claim 1. In addition, OSYPOV disclose:
The method of claim 1, wherein the interactive interpretation process comprises receiving input via a graphical user interface rendered to a display (In paragraph [0039], OSYPOV disclose the seismic facies identification system 500 includes one or more processing units (CPUs) 502, one or more network interfaces 508 and/or other communications interfaces 503, memory 506, and one or more communication buses 504 for interconnecting these and various other components. The seismic facies identification system 500 also includes a user interface 505 (e.g., a display 505-1 and an input device 505-2). )
Regarding claim 15, OSYPOV in view of Yazeed and Aslan disclose elements of claim 11. In addition, OSYPOV disclose:
The method of claim 11, wherein the input comprises trace-wise markings (In FIG. 5 & paragraph [0037], OSYPOV disclose the input facies labels are shown as the red line 51, green rectangle 53, and purple rectangle and line 54).
With respect to claim 19, OSYPOV discloses:
A system, comprising: a processor; memory operatively coupled to the processor; and processor-executable instructions stored in the memory to instruct the system to: receive a first trained machine model trained via unsupervised learning using unlabeled seismic image data (In paragraph [0026], OSYPOV disclose using the unsupervised machine learning model to receive/analyze seismic data. In paragraph [0033], the seismic data includes unlabeled data, the remaining portion of the seismic dataset. In paragraph [0039], OSYPOV disclose a processor and memory.)
generating processed seismic image data by applying new seismic image data for [[a]] the geologic region to the first trained machine model (In paragraph [0036], OSYPOV disclose adding more information about the rock types, connections, and flow properties of seismic facies using a machine learning model (e.g., can be unsupervised learning model))
the second trained model predicting stratigraphy of a geologic region from seismic image data of the geologic region (In paragraph [0033], OSYPOV disclose a supervised machine learning for seismic facies interpretation, where a classifier learns from labeled seismic data (training set) to predict facies for unlabeled data, resulting in a precisely labeled facies distribution map.)
manage operation of equipment associated with a well based on the predicted stratigraphy of the second trained machine model (In paragraph [0033], OSYPOV disclose the seismic dataset and set of facies labels are input to a supervised machine learning at operation 24. The labeled training dataset is first used to “train” a classifier; the classifier (learns from labeled seismic data (training set) to predict facies for unlabeled data) is then applied to the unlabeled input data in order to produce a facies distribution that is now specifically labeled.)
With respect to claim 19, OSYPOV do not specifically disclose:
receiving sparsely-labeled seismic image data comprising a plurality of labels acquired via an interactive interpretation process with a human expert interpreter, the sparsely-labeled seismic image data corresponding to a portion of a geologic region that is volumetrically less than approximately 1 percent of the geologic region as seismically imaged
building, as initialized from the first trained machine model, a second trained machine model via supervised learning, using only the processed seismic data from the unsupervised learning of the first trained machine model and the received plurality of labels without direct input of the new seismic image data to the second trained machine model
However, Yazeed is known to disclose:
Receiving sparsely-labeled seismic image data comprising a plurality of labels acquired via an interactive interpretation process with a human expert interpreter, the sparsely-labeled seismic image data corresponding to a portion of a geologic region that is volumetrically less than approximately 1 percent of the geologic region as seismically imaged (On page 1, (OBTAINING WEAK LABELS FOR SEISMIC IMAGES), Yazeed disclose obtaining one image-level label compared to potentially hundreds of thousands of pixel labels inherently corresponds to a very small fraction of the total data volume. )
OSYPOV and Yazeed are analogous pieces of art because both references concern seismic data via machine learning. Accordingly, it would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify OSYPOV, by identifying facies from seismic data via machine learning as taught by OSYPOV, with generating labeled data for applying machine learning techniques to computational seismic interpretation tasks as taught by Yazeed. The motivation for doing so would have been to use strong computer power to find patterns in data that people might miss, resulting in better classification of facies (See [0024] of OSYPOV.)
With respect to claim 19, OSYPOV and Yazeed does not disclose:
Building, as initialized from the first trained machine model, a second trained machine model via supervised learning, using only the processed seismic data from the unsupervised learning of the first trained machine model and the received plurality of labels without direct input of the new seismic image data to the second trained machine model
However, Aslan is known to disclose:
Building, as initialized from the first trained machine model, a second trained machine model via supervised learning, using only the processed seismic data from the unsupervised learning of the first trained machine model and the received plurality of labels without direct input of the new seismic image data to the second trained machine model, the second trained machine model predicting stratigraphy of the geologic region (In paragraph [0039], Aslan disclose passing output data from a first machine-learning model to the second machine learning model. The second machine learning model does not see the original labels of the training data. Even though Aslan does not disclose output data being “seismic data”, but OSYPOV discloses having seismic data.)
OSYPOV in view of Yazeed and Aslan are analogous pieces of art because both references concern machine learning. Accordingly, it would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, by creating a second machine learning model based on the first machine learning model as taught by Aslan. The motivation for doing so would have been to effectively generate high-quality pixel-level labels using only "rough" image-level labels (See (Page 3, Conclusion ) of Yazeed).
With respect to claim 20, OSYPOV discloses:
One or more computer-readable storage media comprising computer-executable instructions executable to instruct a computing system to: receive a first trained machine model trained via unsupervised learning using unlabeled seismic image data (In paragraph [0026], OSYPOV disclose using the unsupervised machine learning model to receive/analyze seismic data. . In paragraph [0033], the seismic data includes unlabeled data, the remaining portion of the seismic dataset.)
generating processed seismic image data by applying new seismic image data for [[a]] the geologic region to the first trained machine model (In paragraph [0036], OSYPOV disclose adding more information about the rock types, connections, and flow properties of seismic facies using a machine learning model (e.g., can be unsupervised learning model))
the second trained model predicting stratigraphy of a geologic region from seismic image data of the geologic region (In paragraph [0033], OSYPOV disclose a supervised machine learning for seismic facies interpretation, where a classifier learns from labeled seismic data (training set) to predict facies for unlabeled data, resulting in a precisely labeled facies distribution map.)
manage operation of equipment associated with a well based on the predicted stratigraphy of the second trained machine model (In paragraph [0033], OSYPOV disclose the seismic dataset and set of facies labels are input to a supervised machine learning at operation 24. The labeled training dataset is first used to “train” a classifier; the classifier (learns from labeled seismic data (training set) to predict facies for unlabeled data) is then applied to the unlabeled input data in order to produce a facies distribution that is now specifically labeled.)
With respect to claim 20, OSYPOV do not specifically disclose:
receiving sparsely-labeled seismic image data comprising a plurality of labels acquired via an interactive interpretation process with a human expert interpreter, the sparsely-labeled seismic image data corresponding to a portion of a geologic region that is volumetrically less than approximately 1 percent of the geologic region as seismically imaged
building, as initialized from the first trained machine model, a second trained machine model via supervised learning, using only the processed seismic data from the unsupervised learning of the first trained machine model and the received plurality of labels without direct input of the new seismic image data to the second trained machine model
However, Yazeed is known to disclose:
Receiving sparsely-labeled seismic image data comprising a plurality of labels acquired via an interactive interpretation process with a human expert interpreter, the sparsely-labeled seismic image data corresponding to a portion of a geologic region that is volumetrically less than approximately 1 percent of the geologic region as seismically imaged (On page 1, (OBTAINING WEAK LABELS FOR SEISMIC IMAGES), Yazeed disclose obtaining one image-level label compared to potentially hundreds of thousands of pixel labels inherently corresponds to a very small fraction of the total data volume. )
OSYPOV and Yazeed are analogous pieces of art because both references concern seismic data via machine learning. Accordingly, it would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify OSYPOV, by identifying facies from seismic data via machine learning as taught by OSYPOV, with generating labeled data for applying machine learning techniques to computational seismic interpretation tasks as taught by Yazeed. The motivation for doing so would have been to use strong computer power to find patterns in data that people might miss, resulting in better classification of facies (See [0024] of OSYPOV.)
With respect to claim 20, OSYPOV and Yazeed does not disclose:
Building, as initialized from the first trained machine model, a second trained machine model via supervised learning, using only the processed seismic data from the unsupervised learning of the first trained machine model and the received plurality of labels without direct input of the new seismic image data to the second trained machine model
However, Aslan is known to disclose:
Building, as initialized from the first trained machine model, a second trained machine model via supervised learning, using only the processed seismic data from the unsupervised learning of the first trained machine model and the received plurality of labels without direct input of the new seismic image data to the second trained machine model, the second trained machine model predicting stratigraphy of the geologic region (In paragraph [0039], Aslan disclose passing output data from a first machine-learning model to the second machine learning model. The second machine learning model does not see the original labels of the training data. Even though Aslan does not disclose output data being “seismic data”, but OSYPOV discloses having seismic data.)
OSYPOV in view of Yazeed and Aslan are analogous pieces of art because both references concern machine learning. Accordingly, it would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, by creating a second machine learning model based on the first machine learning model as taught by Aslan. The motivation for doing so would have been to effectively generate high-quality pixel-level labels using only "rough" image-level labels (See (Page 3, Conclusion ) of Yazeed).
Regarding claim 26, OSYPOV in view of Yazeed and Aslan disclose elements of claim 1. In addition, OSYPOV disclose:
The method of claim 1, wherein the interactive interpretation process is performed via a graphical user interface that: dynamically determines a minimum selectable labeling area based on at least one of: a type of user input device; and a resolution of the seismic image data; and constrains user labeling inputs in the interactive process to satisfy the determined minimum selectable labeling area (Examiners selects a type of user input device: In paragraph [0039], OSYPOV The seismic facies identification system 500 also includes a user interface 505 (e.g., a display 505-1 and an input device 505-2).)
Claims 2-6, 16 and 23 are rejected 35 U.S.C. 103 as being unpatentable over OSYPOV in view of Yazeed, Aslan and further in view of TANAKA et al. (US Pub No.: 20180101770 A1), hereinafter referred to as TANAKA
Regarding claim 2, OSYPOV in view of Yazeed and Aslan disclose elements of claim 1. OSYPOV in view of Yazeed and Aslan do not explicitly disclose:
The method of claim 1, wherein the first trained machine model comprises a convolution neural network
However, TANAKA disclose the limitation (In paragraph [0042] TANAKA disclose the first generative model is a deep convolutional generative adversarial networks (DCGAN).
Accordingly, it would have been obvious to a person having ordinary skills in the art before the effective filling date of the claimed invention, having the teaching of OSYPOV in view of Yazeed and Aslan before them to include TANAKA, with generating data similar to train data included in the data set as taught by TANAKA. The motivation for doing so would have been to improve the accuracy of both first generative model and second generative model (See [0045] & [0054] of TANAKA.)
Regarding claim 3, OSYPOV in view of Yazeed and Aslan disclose elements of claim 1. OSYPOV in view of Yazeed and Aslan do not explicitly disclose:
The method of claim 1, wherein the second trained machine model comprises a convolution neural network
However, TANAKA disclose the limitation (In paragraph [0040], TANAKA disclose both first and second generative models use a Deep Convolutional GAN (DCGAN).)
Accordingly, it would have been obvious to a person having ordinary skills in the art before the effective filling date of the claimed invention, having the teaching of OSYPOV in view of Yazeed and Aslan before them to include TANAKA, with generating data similar to train data included in the data set as taught by TANAKA. The motivation for doing so would have been to improve the accuracy of both first generative model and second generative model (See [0045] & [0054] of TANAKA.)
Regarding claim 4, OSYPOV in view of Yazeed and Aslan disclose elements of claim 1. OSYPOV in view of Yazeed and Aslan do not explicitly disclose:
The method of claim 3, wherein the second trained machine model comprises a U-Net architecture
However, TANAKA disclose the limitation (In paragraph [0040], TANAKA disclose the second generative model, comprise a Deep Convolutional GAN (using a Convolutional Neural Network).)
Accordingly, it would have been obvious to a person having ordinary skills in the art before the effective filling date of the claimed invention, having the teaching of OSYPOV in view of Yazeed and Aslan before them to include TANAKA, with generating data similar to train data included in the data set as taught by TANAKA. The motivation for doing so would have been to improve the accuracy of both first generative model and second generative model (See [0045] & [0054] of TANAKA.)
Regarding claim 5, OSYPOV in view of Yazeed and Aslan disclose elements of claim 1. OSYPOV in view of Yazeed and Aslan do not explicitly disclose:
The method of claim 1, further comprising building the first trained machine model
However, TANAKA disclose the limitation (In paragraph [0029], TANAKA disclose training the first unsupervised model, learning on the basis of some or all of the train data included in the data set.)
Accordingly, it would have been obvious to a person having ordinary skills in the art before the effective filling date of the claimed invention, having the teaching of OSYPOV in view of Yazeed and Aslan before them to include TANAKA, with generating data similar to train data included in the data set as taught by TANAKA. The motivation for doing so would have been to improve the accuracy of both first generative model and second generative model (See [0045] & [0054] of TANAKA.)
Regarding claim 6, OSYPOV in view of Yazeed and Aslan disclose elements of claim 5. OSYPOV in view of Yazeed and Aslan do not explicitly disclose:
The method of claim 5, wherein the unlabeled seismic image data comprises unlabeled augmented seismic image data (In paragraph [0033], OSYPOV discloses training the unlabeled input data in order to produce a seismic dataset and an optional set of facies, training data may be obtained from synthetic well logs.)
Regarding claim 16, OSYPOV in view of Yazeed and Aslan disclose elements of claim 1. OSYPOV in view of Yazeed and Aslan do not explicitly disclose:
The method of claim 1, wherein the initialization from the first trained machine model improves convergence during the building of the second trained machine model
However, TANAKA disclose the limitation (In paragraph [0105- 0106], TANAKA discloses the generator of the second generative model has the same structure as the generator of the first generative model. Thus, discrimination accuracy of the discriminator of the second generative model can be improved.)
Accordingly, it would have been obvious to a person having ordinary skills in the art before the effective filling date of the claimed invention, having the teaching of OSYPOV in view of Yazeed and Aslan before them to include TANAKA, with generating data similar to train data included in the data set as taught by TANAKA. The motivation for doing so would have been to improve the accuracy of both first generative model and second generative model (See [0045] & [0054] of TANAKA.)
Regarding claim 23, OSYPOV in view of Yazeed and Aslan disclose elements of claim 16. In addition, Aslan disclose:
The method of claim 16, wherein the improved convergence comprises reducing a number of supervised training iterations used to build the second trained machine model (In paragraph [0122, Aslan disclose a reduced size (in terms of storage footprint), allowing for more flexible use of the second type of machine learning model in implementations where storage space and/or computational power is at a premium without significant loss in accuracy of the second model's output.)
Claims 7-10 and 21 are rejected 35 U.S.C. 103 as being unpatentable over OSYPOV in view of Yazeed, Aslan and further in view of Mallet et al. (US Patent No. 8,743,115 B1), hereinafter referred to as Mallet.
Regarding claim 7, OSYPOV in view of Yazeed and Aslan disclose elements of claim 1. OSYPOV in view of Yazeed and Aslan do not explicitly disclose:
The method of claim 1, wherein the second trained machine model predicts stratigraphy of a geologic region as sequences of a layers of material in the geologic region
However, Mallet disclose the limitation (In Col. 44, lines 50-55, Mallet disclose a second model representing the same physical geological structures, where the physical geological structures were originally deposited in the past. Seismic data (e.g., stored with seismic cubes) and/or geologic data (e.g., well markers along well paths) may be accepted.)
Accordingly, it would have been obvious to a person having ordinary skills in the art before the effective filling date of the claimed invention, having the teaching of OSYPOV in view of Yazeed and Aslan before them to include Mallet, with generating a first present day model representing stratified terrains and generating a second corresponding depositional model representing the stratified terrains at the geological-time at which they were originally deposited within the Earth. The motivation for doing so would have been to generate an accurate geological-time model (see Col. 15, lines 20-29, of Mallet)
Regarding claim 8, OSYPOV in view of Yazeed and Aslan disclose elements of claim 1. OSYPOV in view of Yazeed and Aslan do not explicitly disclose:
The method of claim 1, wherein the second trained machine model predicts geologic history of a geologic region
However, Mallet disclose the limitation (In Col. 44, lines 50-55, Mallet disclose a second model representing the same physical geological structures, where the physical geological structures were originally deposited in the past. Seismic data (e.g., stored with seismic cubes) and/or geologic data (e.g., well markers along well paths) may be accepted.)
Accordingly, it would have been obvious to a person having ordinary skills in the art before the effective filling date of the claimed invention, having the teaching of OSYPOV in view of Yazeed and Aslan before them to include Mallet, with generating a first present day model representing stratified terrains and generating a second corresponding depositional model representing the stratified terrains at the geological-time at which they were originally deposited within the Earth. The motivation for doing so would have been to generate an accurate geological-time model (see Col. 15, lines 20-29, of Mallet)
Regarding claim 9, OSYPOV in view of Yazeed and Aslan disclose elements of claim 1. OSYPOV in view of Yazeed and Aslan do not explicitly disclose:
The method of claim 1, wherein the second trained machine model predicts a stratigraphic Earth model of the geologic region
However, Mallet disclose the limitation (In Col. 44, lines 50-55, Mallet disclose a second model representing the same physical geological structures, where the physical geological structures were originally deposited in the past. Seismic data (e.g., stored with seismic cubes) and/or geologic data (e.g., well markers along well paths) may be accepted.)
Accordingly, it would have been obvious to a person having ordinary skills in the art before the effective filling date of the claimed invention, having the teaching of OSYPOV in view of Yazeed and Aslan before them to include Mallet, with generating a first present day model representing stratified terrains and generating a second corresponding depositional model representing the stratified terrains at the geological-time at which they were originally deposited within the Earth. The motivation for doing so would have been to generate an accurate geological-time model (see Col. 15, lines 20-29, of Mallet)
Regarding claim 10, OSYPOV in view of Yazeed and Aslan disclose elements of claim 1. OSYPOV in view of Yazeed and Aslan do not explicitly disclose:
The method of claim 1, further comprising, via the second trained machine model, predicting stratigraphy of a geologic region from seismic image data of the geologic region
However, Mallet disclose the limitation (In Col. 44, lines 50-55, Mallet disclose a second model representing the same physical geological structures, where the physical geological structures were originally deposited in the past. Seismic data (e.g., stored with seismic cubes) and/or geologic data (e.g., well markers along well paths) may be accepted.)
Accordingly, it would have been obvious to a person having ordinary skills in the art before the effective filling date of the claimed invention, having the teaching of OSYPOV in view of Yazeed and Aslan before them to include Mallet, with generating a first present day model representing stratified terrains and generating a second corresponding depositional model representing the stratified terrains at the geological-time at which they were originally deposited within the Earth. The motivation for doing so would have been to generate an accurate geological-time model (see Col. 15, lines 20-29, of Mallet)
Claims 12-13 are rejected 35 U.S.C. 103 as being unpatentable over OSYPOV in view of Yazeed and Aslan and further in view of Li et al. (US Pub No.: 20070219724 A1), hereinafter referred to as Li.
Regarding claim 12, OSYPOV in view of Yazeed and Aslan disclose elements of claim 11. OSYPOV in view of Yazeed and Aslan do not explicitly disclose:
The method of claim 11, wherein the input comprises strokes that comprise at least one vertical stroke having a vertical dimension that exceeds a horizontal dimension
However, Li disclose the limitation (In paragraph [0044], Li disclose vertical grid surfaces (lines) are created to divide the subsurface volume into "columns" of limited lateral extent. Now referring to numeral 23, horizontal or lateral grid surfaces (lines), which may be substantially or relatively horizontal, are created to correspond with surfaces of geologic time associated with the original deposition of the sediments that fill the subsurface volume.)
Accordingly, it would have been obvious to a person having ordinary skills in the art before the effective filling date of the claimed invention, having the teaching of OSYPOV in view of Yazeed and Aslan before them to include Li, generate an acoustic signal that propagates into the earth and is at least partially reflected by subsurface seismic reflectors. The motivation for doing so would have been to accurately characterize in a geologic model and preserved during upscaling for reservoir performance simulation (See [0020] of Li.)
Regarding claim 13, OSYPOV in view of Yazeed and Aslan disclose elements of claim 11. OSYPOV in view of Yazeed and Aslan do not explicitly disclose:
The method of claim 11, wherein the input comprises graphical symbols that comprise at least one closed-boundary symbol
However, Li disclose the limitation (In paragraph [0050], Li disclose some lines created in the simulation may not match the actual lines seen in seismic data, well logs, or other geological information. If this happens, the lines can be changed by hand, or the simulation settings can be adjusted until the simulated lines better match the actual ones.)
Accordingly, it would have been obvious to a person having ordinary skills in the art before the effective filling date of the claimed invention, having the teaching of OSYPOV in view of Yazeed and Aslan before them to include Li, generate an acoustic signal that propagates into the earth and is at least partially reflected by subsurface seismic reflectors. The motivation for doing so would have been to accurately characterize in a geologic model and preserved during upscaling for reservoir performance simulation (See [0020] of Li.)
Claims 14, 21-22 and 25 are rejected 35 U.S.C. 103 as being unpatentable over OSYPOV in view of Yazzeed and Aslan and further in view of LIU et al. (US Pub No.: 20200183032 A1),hereinafter referred to as LIU.
Regarding claim 14, OSYPOV in view of Yazeed and Aslan disclose elements of claim 11. OSYPOV in view of Yazeed and Aslan do not explicitly disclose:
The method of claim 11, wherein the input comprises markings that comprise at least one positive marking and at least one negative marking
However, LIU disclose the limitation (In FIGS. 3A-3D & paragraph [0035], LIU discloses histograms including false negative and false positive markings.)
Accordingly, it would have been obvious to a person having ordinary skills in the art before the effective filling date of the claimed invention, having the teaching of OSYPOV in view of Yazeed and Aslan before them to include LIU with automated seismic interpretation to improve the quality of the seismic interpretation by incorporating geologic priors in the training as taught by LIU. The motivation for doing so would have been to improve the quality of the seismic interpretation by incorporating geologic priors in the training (See [0030] of LIU.)
Regarding claim 21, OSYPOV in view of Yazeed and Aslan disclose elements of claim 1. OSYPOV in view of Yazeed and Aslan do not explicitly disclose:
The method of claim 1, wherein the building the second trained machine model further comprises: receiving, via the interactive interpretation process, labels corresponding to a plurality of marked regions comprising both positively marked regions and negatively marked regions, each negatively marked region being associated with a corresponding positively marked region, wherein the plurality of marked regions do not overlap
However, LIU disclose the limitation (In paragraph [0042], LIU disclose producing a large area of uncertainty between the resulting positive and negative samples. Such instances may then be subject to labor-intensive post-processing (e.g., a human interpreter may apply differentiating thresholds).)
Accordingly, it would have been obvious to a person having ordinary skills in the art before the effective filling date of the claimed invention, having the teaching of OSYPOV in view of Yazeed and Aslan before them to include LIU with automated seismic interpretation to improve the quality of the seismic interpretation by incorporating geologic priors in the training as taught by LIU. The motivation for doing so would have been to improve the quality of the seismic interpretation by incorporating geologic priors in the training (See [0030] of LIU.)
Regarding claim 22, OSYPOV in view of Yazeed and Aslan disclose elements of claim 1. OSYPOV in view of Yazeed and Aslan do not explicitly disclose:
The method of claim 11, wherein the graphical user interface is configured to receive, during the interactive interpretation process, at least two of: a stroke, a graphical symbol, a set of positive and negative markings, or a trace-wise marking
However, LIU disclose the limitation ( In paragraph [0042], LIU disclose false-positive or false-negative marks)
Accordingly, it would have been obvious to a person having ordinary skills in the art before the effective filling date of the claimed invention, having the teaching of OSYPOV in view of Yazeed and Aslan before them to include LIU with automated seismic interpretation to improve the quality of the seismic interpretation by incorporating geologic priors in the training as taught by LIU. The motivation for doing so would have been to improve the quality of the seismic interpretation by incorporating geologic priors in the training (See [0030] of LIU.)
Regarding claim 25, OSYPOV in view of Yazeed and Aslan disclose elements of claim 11. OSYPOV in view of Yazeed and Aslan do not explicitly disclose:
The method of claim 1, wherein the plurality of labels comprises labels corresponding to a plurality of positively marked regions and negatively marked regions, each negatively marked region being associated with a corresponding positively marked region, such that the plurality of positively marked regions and negatively marked regions do not overlap
However, LIU disclose the limitation ( In paragraph [0029], LIU disclose interpreting seismic images, over and above pixel-wise and/or area/volume-wise comparisons that do not adequately take into account geological context (noting that where a “pixel-wise” comparison is referenced herein, the analogous 3-D “voxel-wise” comparison is also contemplated, unless context expressly indicates otherwise).)
Accordingly, it would have been obvious to a person having ordinary skills in the art before the effective filling date of the claimed invention, having the teaching of OSYPOV in view of Yazeed and Aslan before them to include LIU with automated seismic interpretation to improve the quality of the seismic interpretation by incorporating geologic priors in the training as taught by LIU. The motivation for doing so would have been to improve the quality of the seismic interpretation by incorporating geologic priors in the training (See [0030] of LIU.)
Claim 17 and 24 are rejected 35 U.S.C. 103 as being unpatentable over OSYPOV in view of Yazeed and Aslan and further in view of Tonellot et al. (US Pub No.: 20100004870 A1),hereinafter referred to as Tonellot.
Regarding claim 17, OSYPOV in view of Yazeed and Aslan disclose elements of claim 1. OSYPOV in view of Yazeed and Aslan do not explicitly disclose:
The method of claim 1, wherein the initialization from the first trained machine model reduces demand for labeled seismic image data for convergence during the building of the second trained machine model
However, Tonelloe disclose the limitation (In paragraph [0124], Tonelloe disclose a first model from the seismic data and a second model from the seismic data wherein a cost function using the scale factor is minimized is carried out so as to evaluate a difference between the synthetic data and the seismic data)
Accordingly, it would have been obvious to a person having ordinary skills in art before the effective filling date of the claimed invention, having the teaching of OSYPOV in view of Yazeed and Aslan before them to include Tonellot, with a seismic data stratigraphic inversion method for obtaining images representative of a heterogeneous as taught by Tonelloe. The motivation for doing so would have been to improve the estimation of the seismic attribute variations linked with the production parameters (See [0122] of Tonelloe.)
Regarding claim 24, OSYPOV in view of Yazeed and Aslan disclose elements of claim 17. In addition, OSYPOV disclose:
The method of claim 17, wherein the reduced demand for labeled seismic image data comprises using fewer interpreter-provided labels to achieve convergence during the building of the second trained machine model (In paragraph [0034], OSYPOV disclose a classifier based on limited labels provided by an interpreter.)
Claim 18 is rejected 35 U.S.C. 103 as being unpatentable over OSYPOV in view of Yazeed and Aslan and further in view of Mao et al. (US Pub No.: 20200064507 A1),hereinafter referred to as Mao.
Regarding claim 18, OSYPOV in view of Yazeed and Aslan disclose elements of claim 1. OSYPOV in view of Yazeed and Aslan do not explicitly disclose:
The method of claim 1, wherein the received labeled seismic image data comprises coded labels that are coded based on one or more interpreter criteria
In paragraph [0078], Mao disclose the program code will: get a seismic dataset, which comes from signals of seismic sensors that pick up waves from inside the ground; identify possible breaks in the ground based on the seismic dataset; use a neural network to label some of these possible breaks, marking them as either a target break or a nontarget break; and then find the location of the geological feature in the ground that is linked to at least one target break based on the labeled possible breaks
Accordingly, it would have been obvious to a person having ordinary skills in art before the effective filling date of the claimed invention, having the teaching of OSYPOV in view of Yazeed and Aslan before them to include Mao, with generating an interpreted seismic dataset. The motivation for doing so would have been to improve the reduced dimensional vector for labeling indicators of target discontinuities (See [0043] of Mao.)
Examiners Note
It should be noted that the Examiners expressed how claim 1, the disconnect from what information the second trained machine learning model is actually allowed receiving versus what the information is used to create its training data. The claim separates the raw seismic data from the processed seismic data.
Response to Arguments
Applicant's arguments filed 03/16/2026 in part have been fully considered.
Pertaining to the rejection under 101
Rejections for claims 1-26 are withdrawn under 35 USC § 101
Pertaining to Rejection under 103
Applicant’s arguments with respect to claim(s) 1, 19 and 20 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to EVEL HONORE whose telephone number is (703)756-1179. The examiner can normally be reached Monday-Friday 8 a.m. -5:30 p.m.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Mariela D Reyes can be reached at (571) 270-1006. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
EVEL HONORE
Examiner
Art Unit 2142
/Mariela Reyes/Supervisory Patent Examiner, Art Unit 2142
Prosecution Insights