DETAILED ACTION
Claims 1-20 are pending and have been examined.
--
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 .
Information Disclosure Statement
The information disclosure statements (IDS) submitted on 05/09/2024 and 06/12/2026 are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statements are being considered by the examiner.
Claim Objections
Claims 1-9 and 15-16 are objected to because of the following informalities:
In claim 1, “A computer-implemented method for predicting gas rate… estimating, using the at least one hardware processor, gas rates…” should be “A computer-implemented method for predicting gas rates… estimating, using the at least one hardware processor, gas rates…” (inconsistent terms: “gas rate” vs. “gas rates”)
In claims 1, 8 and 15, “training… the discriminator and the generator by evaluating the output of the discriminator, wherein parameters of the discriminator and generator are iteratively updated…” should be “training… the discriminator and the generator by evaluating the output of the discriminator, wherein parameters of the discriminator and the generator are iteratively updated…”
In claims 2-7, “The computer implemented method of claim 1” should be “The computer-implemented method of claim 1” (a hyphen is missing)
In claims 2, 9 and 16, “wherein the binary classification classifies the inputs of the discriminator as real data or fake data” should be “wherein the binary classification classifies the input of the discriminator as real data or fake data.” (inconsistent terms: “the input” in claim 1 vs. “the inputs” in claim 2)
Appropriate correction is required.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
-
Claims 1-20 rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more
Step 1: Claims 1-7 recite a method. Claims 8-14 recite an apparatus. Claims 15-20 recite a system. Therefore, claims 1-7 are directed to a process, and claims 8-20 are directed to a machine.
With respect to claims 1, 8 and 15:
2A Prong 1: The claim recites a judicial exception.
estimating… gas rates (mental process – evaluation,--- estimating gas rates)
2A Prong 2: The judicial exception is not integrated into a practical application.
… using at least one hardware processor… using the at least one hardware processor… using the at least one hardware processor… using the at least one hardware processor… (mere instructions to apply an exception, (2) Whether the claim invokes computers - MPEP 2106.05(f); generic computer components)
inputting… training data into a generator, wherein the generator outputs generated data samples; (insignificant extra-solution activity – MPEP 2106.05(g), (3) data gathering and outputting)
providing… input to a discriminator, the input comprising the generated data samples and real data samples, wherein the discriminator outputs a binary classification of the input; (insignificant extra-solution activity – MPEP 2106.05(g), (3) data gathering and outputting)
training… the discriminator and the generator by evaluating the output of the discriminator, wherein parameters of the discriminator and generator are iteratively updated based on the output of the discriminator; and (mere instructions to apply an exception – MPEP 2106.05(f), (3) The particularity or generality of the application of the judicial exception; training the GAN model and updating the parameters of the GAN model)
… using the trained generator (mere instructions to apply an exception – MPEP 2106.05(f), (3) The particularity or generality of the application of the judicial exception; using the generator)
Since the claim as a whole, looking at the additional elements individually and in combination, does not contain any other additional elements that are indicative of integration into a practical application, the claim is directed to an abstract idea.
2B: The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
… using at least one hardware processor… using the at least one hardware processor… using the at least one hardware processor… using the at least one hardware processor… (mere instructions to apply an exception, (2) Whether the claim invokes computers - MPEP 2106.05(f); generic computer components)
inputting… training data into a generator, wherein the generator outputs generated data samples; (insignificant extra-solution activity – MPEP 2106.05(g), (3) data gathering and outputting, and WURC: receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 - MPEP 2106.05(d)(II)(i))
providing… input to a discriminator, the input comprising the generated data samples and real data samples, wherein the discriminator outputs a binary classification of the input; (insignificant extra-solution activity – MPEP 2106.05(g), (3) data gathering and outputting, and WURC: receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 - MPEP 2106.05(d)(II)(i))
training… the discriminator and the generator by evaluating the output of the discriminator, wherein parameters of the discriminator and generator are iteratively updated based on the output of the discriminator; and (mere instructions to apply an exception – MPEP 2106.05(f), (3) The particularity or generality of the application of the judicial exception; training the GAN model and updating the parameters of the GAN model)
… using the trained generator (mere instructions to apply an exception – MPEP 2106.05(f), (3) The particularity or generality of the application of the judicial exception; using the generator)
Considering the additional elements individually and in combination, and the claim as a whole, the additional elements do not provide significantly more than the abstract idea. Therefore, the claim is not patent eligible.
With respect to claims 2, 9 and 16:
2A Prong 1: The claim recites a judicial exception.
wherein the binary classification classifies the inputs of the discriminator as real data or fake data. (mental process – evaluation or judgement,--- classifying the inputs as real or fake)
With respect to claims 3, 10 and 17:
2A Prong 2: The judicial exception is not integrated into a practical application.
wherein the training data is historical data obtained from previously drilled wells. (insignificant extra-solution activity – MPEP 2106.05(g), (3) data gathering and outputting)
Since the claim as a whole, looking at the additional elements individually and in combination, does not contain any other additional elements that are indicative of integration into a practical application, the claim is directed to an abstract idea.
2B: The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
wherein the training data is historical data obtained from previously drilled wells. (insignificant extra-solution activity – MPEP 2106.05(g), (3) data gathering and outputting, and WURC: receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 - MPEP 2106.05(d)(II)(i))
Considering the additional elements individually and in combination, and the claim as a whole, the additional elements do not provide significantly more than the abstract idea. Therefore, the claim is not patent eligible.
With respect to claims 4, 11 and 18:
2A Prong 2: The judicial exception is not integrated into a practical application.
wherein the real data is historical data obtained from previously drilled wells. (insignificant extra-solution activity – MPEP 2106.05(g), (3) data gathering and outputting)
Since the claim as a whole, looking at the additional elements individually and in combination, does not contain any other additional elements that are indicative of integration into a practical application, the claim is directed to an abstract idea.
2B: The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
wherein the real data is historical data obtained from previously drilled wells. (insignificant extra-solution activity – MPEP 2106.05(g), (3) data gathering and outputting, and WURC: receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 - MPEP 2106.05(d)(II)(i))
Considering the additional elements individually and in combination, and the claim as a whole, the additional elements do not provide significantly more than the abstract idea. Therefore, the claim is not patent eligible.
With respect to claims 5, 12 and 19:
2A Prong 1: The claim recites a judicial exception.
wherein evaluating the discriminator comprises calculating at least one performance metric and determining that the at least one performance metric satisfies a corresponding performance metric threshold. (mental process – evaluation or judgement,--- calculating performance metric and determining the metric satisfies a threshold)
With respect to claims 6, 13 and 20:
2A Prong 2: The judicial exception is not integrated into a practical application.
wherein the generator is trained using regression analysis. (mere instructions to apply an exception – MPEP 2106.05(f), (3) The particularity or generality of the application of the judicial exception; training the generator using regression analysis)
Since the claim as a whole, looking at the additional elements individually and in combination, does not contain any other additional elements that are indicative of integration into a practical application, the claim is directed to an abstract idea.
2B: The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
wherein the generator is trained using regression analysis. (mere instructions to apply an exception – MPEP 2106.05(f), (3) The particularity or generality of the application of the judicial exception; training the generator using regression analysis)
Considering the additional elements individually and in combination, and the claim as a whole, the additional elements do not provide significantly more than the abstract idea. Therefore, the claim is not patent eligible.
With respect to claims 7 and 14:
2A Prong 1: The claim recites a judicial exception.
wherein the estimated gas rates are used to determine locations for new wells. (mental process – evaluation or judgement,--- using the gas rates to determine locations for new wells)
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-6, 8-13 and 15-20 rejected under 35 U.S.C. 102 (a)(1) as being anticipated by Denli (US 20200183047 A1, filed on 20191115)
In regard to claims 1, 8 and 15, Denli teaches: A computer-implemented method for predicting gas rate using a Generative Adversarial Network, the method comprising: (Denli, [0097] "reservoir flow simulations including surrogate models based deep network models may use the samples of reservoir models in order to estimate posterior distributions of dynamic reservoir properties or reservoir flow conditions (e.g., oil, gas and water production rates). [predicting gas rate]"; [0071] "Multiple realizations of the reservoir models, which may be generated by the generative network, [GAN] may thus be used to estimate the statistical distributions of the target reservoir quantities [predicting gas rate] which may include... distribution of dynamic properties affecting fluid flow conditions;"; [0063] "In one implementation of GAN, two neural networks, including a generative network (which generates candidate reservoir models) [GANs (a Generative Adversarial Network) include a generative/ (candidate) reservoir model (a generator)]and a discriminative network (which evaluates or classifies the candidate reservoir models), contest with each other."; [0077] "As discussed above, various machine learning methodologies are contemplated. As one example, a generative adversarial network (GAN) may be used, such as illustrated in FIGS. 6A-B"; also see [0079]; GANs include a generative/reservoir model (a generator), which is used to predict gas rates)
using at least one hardware processor… using the at least one hardware processor… using the at least one hardware processor… using the at least one hardware processor… (Denli, [0103]-[0104] "FIG. 11 is a diagram of an exemplary computer system 1300 that may be utilized to implement methods described herein. A central processing unit (CPU) 1302 is coupled to system bus 1304")
PNG
media_image1.png
220
714
media_image1.png
Greyscale
inputting… training data into a generator, wherein the generator outputs generated data samples; (Denli, [0078]-[0079] "Specifically, FIG. 6A is a first example block diagram 600 of a conditional generative-adversarial neural network (CGAN) schema in which the input to the generative model G (630) is conditioning data (e.g., geophysical data, petrophysical data and structural framework) x (610) and noise z (620). [inputting… training data into a generator] FIG. 6B is a second example block diagram 660 of a CGAN schema in which the input to the generative model G (680) is conditioning data x (610), noise z (620), and latent codes c (670)... GANs include generative models that learn mapping from one or more inputs to an output (such as y, G: z→y where y is output (e.g., reservoir model) and z is noise), through an adversarial training process. This is illustrated in FIG. 6A, with generative model G (630) outputting G(x, z) (640) [the generator outputs generated data samples G(x, z)] and in FIG. 6B, with generative model G (680) outputting G(c, x, z) (690)."; see Fig. 6A, inputting x 610 and z 620 [training data] to G 630, where in G 630 outputs G(x, z) 640)
providing... input to a discriminator, the input comprising the generated data samples and real data samples, (Denli, [0080] "In this training process, two models may be trained simultaneously, including a generative model G (630, 680) and a discriminative model D (655, 695) that learns to distinguish a training output y (also called reference output or ground truth) (650) from an output of generative model G (630, 680)."; see Fig. 6A, providing G(x, z) 640 [the generated data samples] and x 610 and y 650 [real data samples] to D 655 [a discriminator]) wherein the discriminator outputs a binary classification of the input; (Denli, [0101] "The discriminator may therefore attempt to discern which it considers as real and which it considers as fake."; [0046] "Training (machine learning) is typically an iterative process of adjusting the parameters of a neural network to minimize a loss function which may be based on an analytical function (e.g., binary cross entropy) or based on a neural network (e.g., discriminator). [a binary classification of the input]"; binary cross-entropy is a loss function used when the model performs a binary classification to separate input data into two classes)
training… the discriminator and the generator by evaluating the output of the discriminator, wherein parameters of the discriminator and generator are iteratively updated based on the output of the discriminator; and (Denli, [0046] "Training (machine learning) is typically an iterative process of adjusting the parameters of a neural network to minimize a loss function which may be based on an analytical function... "; [0087]-[0089] "Referring back to the objective function, it may take the form of: F_G(W_G) = E [... D(x, G(...)) [based on the output of the discriminator] ... ] (1) ... The discriminator D may be trained with an objective functional which may take the form of: F_D(W_d) = E[...D(W_D...)...] (2) ... Equations (1) and (2) may be iteratively solved in an alternating fashion...")
estimating... gas rates using the trained generator. (Denli, [0097] "reservoir flow simulations including surrogate models based deep network models may use the samples of reservoir models in order to estimate posterior distributions of dynamic reservoir properties or reservoir flow conditions (e.g., oil, gas and water production rates). [estimating gas rates]"; [0071] "Multiple realizations of the reservoir models, which may be generated by the generative network, [the trained generator] may thus be used to estimate the statistical distributions of the target reservoir quantities [estimating gas rates] which may include... distribution of dynamic properties affecting fluid flow conditions;")
Claims 8 and 15 recite substantially the same limitation as claim 1, therefore the rejection applied to claim 1 also apply to claims 8 and 15. In addition, Denli teaches: (claim 8) An apparatus comprising a non-transitory, computer readable, storage medium that stores instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising: (claim 15) A system, comprising: one or more memory modules; one or more hardware processors communicably coupled to the one or more memory modules, the one or more hardware processors configured to execute instructions stored on the one or more memory models to perform operations comprising: (Denli, [0103]-[0104] "FIG. 11 is a diagram of an exemplary computer system 1300 that may be utilized to implement methods described herein. A central processing unit (CPU) 1302 is coupled to system bus 1304… Examples of computer-readable media include a random access memory (RAM) 1306...")
In regard to claims 2, 9 and 16, Denli teaches: wherein the binary classification classifies the inputs of the discriminator as real data or fake data. (Denli, [0101] "The output of the generative model is thus passed to discriminator in order for the discriminator to evaluate its acceptance as a reservoir model. As discussed above, the discriminator is also provided with real reservoir samples extracted from the geological model. The discriminator may therefore attempt to discern which it considers as real and which it considers as fake. [real data or fake data]"; [0046] "Training (machine learning) is typically an iterative process of adjusting the parameters of a neural network to minimize a loss function which may be based on an analytical function (e.g., binary cross entropy) or based on a neural network (e.g., discriminator). [a binary classification of the input]")
In regard to claims 3, 10 and 17, Denli teaches: wherein the training data is historical data obtained from previously drilled wells. (Denli, [0040] "Conditioning data refers a collection of data or dataset to constraint, infer or determine one or more reservoir or stratigraphic models. Conditioning data might include... well log data, [historical data obtained from previously drilled wells] production data and reservoir structural framework."; well log data represents the direct measurements and records taken from previously drilled wells; see Fig. 6A, x 610 [the training data] is provided to G 630; conditioning input data (such as class labels) is provided to both the generator and the discriminator in a Conditional GAN (cGAN))
In regard to claims 4, 11 and 18, Denli teaches: wherein the real data is historical data obtained from previously drilled wells. (Denli, [0040] "Conditioning data refers a collection of data or dataset to constraint, infer or determine one or more reservoir or stratigraphic models. Conditioning data might include... well log data, [historical data obtained from previously drilled wells] production data and reservoir structural framework."; well log data represents the direct measurements and records taken from previously drilled wells; see Fig. 6A, x 610 [the real data] is provided to D 655; conditioning input data (such as class labels) is provided to both the generator and the discriminator in a Conditional GAN (cGAN))
In regard to claims 5, 12 and 19, Denli teaches: wherein evaluating the discriminator comprises calculating at least one performance metric and determining that the at least one performance metric satisfies a corresponding performance metric threshold. (Denli, [0080] "This competition between G and D networks may converge at a local Nash equilibrium of Game Theory (or GAN convergences when the D and G weights do not change more 1% of its starting weight values; [weights of D do not change more than 1%, satisfying a threshold] weights are the D and G model parameters which are updated during the training process based on an optimization method such stochastic gradient method)"; calculating changes of weight values of the discriminator D, i.e. [calculating performance metric] for GAN convergences)
In regard to claims 6, 13 and 20, Denli teaches: wherein the generator is trained using regression analysis. (Denli, [0083]-[0084] "The generative model may be based on a deep network, such as U-net, as illustrated in the block diagram 700 of FIG. 7, in which an autoencoder (AE), variational autoencoder (VAE) or any other suitable network maps {x, z, c} to an output of stratigraphic or reservoir model... The generative model G may be trained iteratively by solving an optimization problem which may be based on an objective functional involving discriminator D and a measure of reconstruction loss (e.g., an indication of the similarity of the generated data to the ground truth)... Thus, the individual losses may be a composite of other loss functions (e.g., the reconstruction loss may be L1 and L2 loss functions together). [using regression analysis, measuring the difference between predicted and actual data]")
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 7 and 14 rejected under 35 U.S.C. 103 as being unpatentable over Denli in view of Mustapha (US 20240311530 A1, filed on 20220207)
In regard to claims 7 and 14, Denli does not teach, but Mustapha teaches: wherein the estimated gas rates are used to determine locations for new wells. (Mustapha, [0004] "identifying a second hot spot of the subsurface volume using a machine learning model that is trained to predict well performance based at least in part on the one or more reservoir properties, evaluating the first and second hot spots for well placement based at least in part on the predicted well performance at the first and second hot spots, respectively, and selecting at least one of the first hot spot or the second hot spot for well construction. [determine locations for new wells]"; [0008] "training the machine learning model based on the historical well performance data and the reservoir properties, such that the machine learning model is configured to predict the performance of the both existing and new wells"; [0070] "Machine learning may be utilized to replace a simulator by predicting production data given a set of uncertainty parameters values."; [0119] "a methodology using machine learning methods may be used to: (1) predict future performance of an existing producing well; and/or (2) predict performance of an undrilled well at a new location... a well performance forecast may be based on historical well performance data (oil, gas, water production and injection rates and cumulative volumes; bottomhole, tubing head and reservoir pressure)"; [0122]-[0124] "Fast screening of performance of new wells at different locations will allow to optimize well placement process. This methodology may be integrated with the 'Well Placement Selection Under Uncertainty' method discussed above to test out different hotspots generated using probabilistic methods and rank them based on the performance of new wells. The workflow may be able to produce accurate real-time production forecast for existing wells and production prediction faster and able to screen thousands of locations to generate the most optimal location to drill a well. [determine locations for new wells]"; the ML model is trained to predict well performance data, and performance data include the gas rates, i.e. the ML model predicts the gas rates)
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified Denli to incorporate the teachings of Mustapha by including fast screening of performance of new wells at different locations. Doing so would allow to optimize well placement process, and generate the most optimal location to drill a well. (Denli, [0122]-[0124] "Fast screening of performance of new wells at different locations will allow to optimize well placement process... The workflow may be able to produce accurate real-time production forecast for existing wells and production prediction faster and able to screen thousands of locations to generate the most optimal location to drill a well.")
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SU-TING CHUANG whose telephone number is (408)918-7519. The examiner can normally be reached Monday - Thursday 8-5 PT.
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, Usmaan Saeed can be reached at (571) 272-4046. 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.
/S.C./Examiner, Art Unit 2146
/USMAAN SAEED/Supervisory Patent Examiner, Art Unit 2146
Prosecution Insights