DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Objections
2. Claims 7 and 16 are objected to because of the following informalities: a) In claim 7 lines 3-4, please change: "the wireline data representing input data processed by the artificial neural network, the core sample data representing a set of ground truth values" to
-- the wireline data representing input data processed by the artificial neural network, and the core sample dataset representing a set of ground truth values--.
b) In claim 16 lines 3-4, please change: "the wireline data representing input data processed by the artificial neural network, the core sample data representing a set of ground truth values" to
-- the wireline data representing input data processed by the artificial neural network, and the core sample dataset representing a set of ground truth values--.
Appropriate correction is required.
Claim Rejections - 35 USC § 101
3. 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 1-18 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
In view of the new 2019 Revised Patent Subject Matter Eligibility Guidance (Federal Register Vol. 84, No. 4, January 7, 2019), the Examiner has considered the claims and has determined that under step 1, claims 1-9 are to a process, and claims 10-18 are to another process. Next under the new step 2A prong 1 analysis, the claims are considered to determine if they recite an abstract idea (judicial exception) under the following groupings: (a) mathematical concepts, (b) certain methods of organizing human activity, or (c) mental processes. The independent claims contain at least the following bolded limitations (see representative independent claims) that fall into the grouping of mathematical concepts and/or mental processes:
1. A method of exploring for hydrocarbons in a reservoir, the method comprising:
obtaining wireline logs for one or more first wells;
obtaining reservoir rock property data from core samples from the one or more first wells;
correlating the wireline logs with the measured reservoir rock properties;
running a logging tool down a second well to generate wireline logs for the second well;
processing the wireline logs for the second well using a machine learning model trained on the correlated wireline logs-reservoir rock properties data of the one or more first wells to generate a set of predicted rock properties of the second well;
determining a difference between the predicted rock properties of the second well and measured rock properties;
applying the difference to generate log depth corrections for each of the rock properties; and generating a pseudo-log of rock properties of the second well based at least in part on applying the log depth corrections to the predicted rock properties.
10. A method for exploring a reservoir containing hydrocarbons, the method comprising:
obtaining wireline log data from a well;
processing the wireline log data using a machine learning model to generate a set of predicted rock properties of the well;
determining a difference between the wireline log data and the set of predicted rock properties of the well; applying the difference to generate log depth corrections for each of the rock properties; and
generating a pseudo-log of rock properties of the second well based at least in part on applying the log depth corrections to the predicted rock properties.
It is important to note that a mathematical concept need not be expressed in mathematical symbols, because "[w]ords used in a claim operating on data to solve a problem can serve the same purpose as a formula."(see MPEP 2106.04(a)(2) I.). The limitations of "correlating the wireline logs with the measured reservoir rock properties" amounts to a mental process to compare between two sets of data to determine relationships or correlations between the data, or a mathematical calculation if the correlation is more complex and is represented by mathematical formulas. The limitations of "processing the wireline logs for the second well using a machine learning model trained on the correlated wireline logs- reservoir rock properties data of the one or more first wells to generate a set of predicted rock properties of the second well" or "processing the wireline log data using a machine learning model to generate a set of predicted rock properties of the well" amount to applying an established mathematical model to solve for a set of predicted rock properties. Patents that do no more than claim the application of generic machine learning to new data environments, without disclosing improvements to the machine learning models to be applied, are patent ineligible under § 101 (see Recentive Analytics, Inc. v. Fox Corp., 134 F.4th 1205 (Fed. Cir. 2025)). The use of an existing machine learning model is just the action of using a function which takes input parameters and returns output parameters, where the complexity of the model can encompass basic relationships simple enough to be represented with pen and paper by a person. The limitations of "determining a difference between the predicted rock properties of the second well and measured rock properties" or "determining a difference between the wireline log data and the set of predicted rock properties of the well" amount to a mental process to compare between a different pair of data to determine a difference, or a mathematical calculation to subtract between two sets of data. The limitations of "applying the difference to generate log depth corrections for each of the rock properties" amount to mathematical calculations to numerically correct the values of each of the rock properties. The limitations of "generating a pseudo-log of rock properties of the second well based at least in part on applying the log depth corrections to the predicted rock properties" amount to mathematically plotting/interpolating the rock properties onto a graph/log, and ultimately amounts to generating an abstract data-based representation of numerical data.
Next in step 2A prong 2, the independent claims are analyzed to determine whether there are additional elements or combination of elements that apply, rely on, or use the judicial exception in a manner that imposes a meaningful limit on the judicial exception such that it is more than a drafting effort designed to monopolize the exception, in order to integrate the judicial exception into a practical application. These limitations have been identified and underlined above, and are not indicative of integration into a practical application because: (1) "a method of exploring for hydrocarbons in a reservoir" or "a method for exploring a reservoir containing hydrocarbons" amounts to generally linking the use of the judicial exception to a particular technological environment or field of use (see MPEP 2106.05(h)), as the exploration is described at a high level without any applied physical steps to carry out the exploration or an applied control/change to any exploration; and (2) "the limitations of "obtaining wireline logs for one or more first wells," "obtaining reservoir rock property data from core samples from the one or more first wells," "running a logging tool down a second well to generate wireline logs for the second well," and "obtaining wireline log data from a well" amount to adding insignificant extra-solution data gathering activity to the judicial exception (see MPEP 2106.05(g)) to gather the necessary data needed for the abstract idea calculations.
Next in step 2B, the independent claims are considered to determine if they recite additional elements that amount to an inventive concept (“significantly more”) than the recited judicial exception. These limitations have been identified and also underlined above, and are not indicative of an inventive concept ("significantly more") because: (1) "a method of exploring for hydrocarbons in a reservoir" or "a method for exploring a reservoir containing hydrocarbons" amounts to generally linking the use of the judicial exception to a particular technological environment or field of use (see MPEP 2106.05(h)), as the exploration is described at a high level without any applied physical steps to carry out the exploration or describe an applied control/change to any exploration; and (2) "the limitations of "obtaining wireline logs for one or more first wells," "obtaining reservoir rock property data from core samples from the one or more first wells," "running a logging tool down a second well to generate wireline logs for the second well," and "obtaining wireline log data from a well" amount to adding insignificant extra-solution data gathering activity to the judicial exception (see MPEP 2106.05(g)), and do not describe any gathering of data using a particular physical measurement arrangement.
Dependent claims 2-9 and 11-18 contain additional limitations that fall under abstract idea grouping of mathematical concepts to describe further variable definitions, calculations carried out by machine learning model, mathematical functions that make up the machine learning model, and training/validating of the neural network using mathematical algorithms. The training of a neural network, when given the broadest reasonable interpretation in light of the background, amount to carrying out mathematical calculations to derive a trained neural network, especially when explicit mathematical algorithms such as a Levenberg-Marquardt algorithm and Bayesian regularization backpropagation algorithm are described such as in claims 6 and 15 (see also similar Example 47 claim 2 from the July 2024 Subject Matter Eligibility Examples from the 2024 Guidance Update on Patent Subject Matter Eligibility, Including on Artificial Intelligence, 89 FR 58128).
4. An invention is not rendered ineligible for patent simply because it involves an abstract concept. Applications of such concepts "to a new and useful end" remain eligible for patent protection (see Alice Corp., 134 S. Ct. at 2354 (quoting Benson, 409 U.S. at 67)). However, "a claim for a new abstract idea is still an abstract idea" (see Synopsys v. Mentor Graphics Corp. _F.3d_, 120 U.S.P.Q. 2d1473 (Fed. Cir. 2016)). There needs to be additional elements or combination of additional elements in the claim to apply, rely on, or use the judicial exception in a manner that imposes a meaningful limit on the judicial exception or render the claim as a whole to be significantly more than the exception itself in order to demonstrate “integration into a practical application” or an “inventive concept.” For instance, particularly configured or installed physical sensor/machine arrangements for actively obtaining the measurement data, or further physical applications using the abstract data-based pseudo-log of rock properties to drive a transformation (such as directed drilling), change/control in physical operation (such as modifying a well trajectory), or repair/maintenance of a technology or technical process could provide integration into a practical application to demonstrate an improvement to the technology or technical field.
Claim Rejections - 35 USC § 112
5. 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.
Claims 1-18 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
a) Claim 1 line 5 recites "correlating the wireline logs with the measured reservoir rock properties…". There is insufficient antecedent basis for the limitation of "the measured reservoir rock properties", as there is no previous recitation for any measuring or measurement of reservoir rock properties. The claim does recite "obtaining" reservoir rock property data, but it is not clear if this "obtained" rock property data is necessarily the same as the "measured" reservoir rock properties. Appropriate correction/clarification is requested.
b) Claim 10 lines 9-10 recites the limitation "generating a pseudo-log of rock properties of the second well based at least in part on applying the log depth corrections to the predicted rock properties." There is insufficient antecedent basis for the limitation of "the second well" in the claim, as there is no previous recitation or teaching of any "second well." Appropriate correction/clarification is requested.
6. Dependent claims 2-9 depend from claim 1 and are rejected for at least the same reasons as given for claim 1. Dependent claims 11-18 depend from claim 10 and are rejected for at least the same reasons as given for claim 10.
Claim Rejections - 35 USC § 102
7. 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 (i.e., changing from AIA to pre-AIA ) 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 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.
8. Claims 1-5, 7-14, and 16-18 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Anifowose et al. (US Pat. Pub. 2021/0254457, hereinafter "Anifowose").
In regards to claim 1, Anifowose teaches a method of exploring for hydrocarbons in a reservoir (Anifowose abstract teaches a method of exploring for hydrocarbons through an analysis of reservoir rock grain sizes), the method comprising:
obtaining wireline logs for one or more first wells (Anifowose abstract and paragraphs [0004]-[0005] teach obtaining wirelines logs from one or more first wells);
obtaining reservoir rock property data from core samples from the one or more first wells (Anifowose abstract and paragraphs [0004] teach estimating grain sizes (a reservoir rock property) from a plurality of core samples extracted from a different depth from the one or more first wells);
correlating the wireline logs with the measured reservoir rock properties (Anifowose paragraph [0046] teaches creating a mathematical relationship between the wireline logs and the estimated grain sizes (rock properties), including a weight factor obtained from the degree of correlation between the wireline log and the estimated grain size, in order to train a machine learning engine/model);
running a logging tool down a second well to generate wireline logs for the second well (Anifowose abstract and paragraphs [0004], [0016], and [0020] teach running a logging tool down a new (second) well to generate wireline logs for the second well);
processing the wireline logs for the second well using a machine learning model trained on the correlated wireline logs-reservoir rock properties data of the one or more first wells to generate a set of predicted rock properties of the second well (Anifowose abstract and paragraphs [0004], [0016], and [0020] teach processing the wireline logs for the second well using a machine learning model trained on the correlated wireline logs and grain depths dataset from the one or more first wells to generate a set of continuous grain sizes (predicted rock properties) of the second well);
determining a difference between the predicted rock properties of the second well and measured rock properties (Anifowose paragraphs [0049]-[0050] teach determining a residual (difference) between the estimated output of rock properties with an actual (measured) output portion);
applying the difference to generate log depth corrections for each of the rock properties (Anifowose paragraphs [0049]-[0050] teach applying the residual difference against a threshold to generate log depth corrections for adjusting the learning parameters of the machine learning model until the residual is less than the threshold and the machine learning model is validated, and paragraphs [0045]-[0047] teach where the learning parameters include weight coefficients that provide log depth corrections for the estimated grain sizes across the multiple depths); and
generating a pseudo-log of rock properties of the second well based at least in part on applying the log depth corrections to the predicted rock properties (Anifowose paragraph [0051] teaches generating a grain size log produced by the validated machine learning model as a pseudo-log based on the applied (validated) depth corrections to the predicted grain size rock properties).
In regards to claim 2, Anifowose teaches the method wherein reservoir rock property data includes porosity, permeability, grain density, and geochemical and elemental data (Anifowose paragraph [0005] teaches where the reservoir rock property data includes porosity, permeability, grain size over a plurality of depths (as a measure of grain density), and geochemical/elemental data such as from gamma ray logging).
In regards to claim 3, Anifowose teaches the method wherein the machine learning model generates a continuous set of predicted rock properties along the main axis of the well (Anifowose abstract and paragraph [0004] teaches where the machine learning model generates a continuous grain size log over a plurality of continuous depths (along a depth axis) of the second well).
In regards to claim 4, Anifowose teaches the method wherein the machine learning model is an artificial neural network (Anifowose paragraph [0005] teaches where the machine learning mode ls an artificial neural network (ANN)).
In regards to claim 5, Anifowose teaches the method wherein the artificial neural network includes one or more hidden layers (Anifowose paragraph [0045] teaches one or more number of hidden layers of the artificial neural network that can be adjusted), the one or more hidden layers including a summation layer comprising a linear function (Anifowose paragraph [0032] teaches a hidden layer for a summation layer for registering multiple thin section images to form a compositional analysis image using a linear registration algorithm) and an activation layer comprising a sigmoid function (Anifowose paragraph [0046] teaches an activation layer to transform the input space to a high-dimensional nonlinear space using a sigmoid function).
In regards to claim 7, Anifowose teaches the method wherein a dataset comprising wireline data from one or more wells and a corresponding core sample dataset from the one or more wells are used to train and validate the artificial neural network (Anifowose paragraph [0004] teaches where a dataset comprising wireline data from one or more wells and a corresponding core sample dataset from the one or more wells at different depths in the wells are used to train the machine learning model (artificial neural network), and paragraph [0049] teaches where a portion (less than 50%) of the wireline log and grain size core sample dataset are used to validate the machine learning model), the wireline data representing input data processed by the artificial neural network, the core sample data representing a set of ground truth values corresponding to a set of predicted rock values (Anifowose paragraphs [0045]-[0047] teach where the wireline logs represent input data X1…X6 that are processed by the machine learning engine (artificial neural network), and the core sample data Y output represents a resulting high-dimensional nonlinear space that matches the nature of the subsurface data (as ground truth values) corresponding to a set of predicted output grain sizes).
In regards to claim 8, Anifowose teaches the method wherein the dataset is split into a training dataset and a validation dataset, the training dataset used to train the artificial neural network, the validation dataset used to validate a set of outputs of the artificial neural network (Anifowose paragraph [0049] teaches splitting the dataset is split into a training dataset (majority) and a minority (less than 50%) validation dataset, where the training dataset is used to train the machine learning engine (artificial neural network) and the validation dataset used to validate the outputs of the machine learning engine (artificial neural network)).
In regards to claim 9, Anifowose teaches the method wherein the artificial neural network is retrained with new training data to update a set of weights corresponding to a nonlinear function of the artificial neural network (Anifowose paragraph [0052] teaches where the machine learning model (artificial neural network) is retrained with new training data to derive new learning parameters, and paragraphs [0045]-[0047] teaches where the learning parameters include weight coefficients corresponding to a nonlinear function (such as a Gaussian or sigmoid function) of the machine learning engine (artificial neural network)).
In regards to claim 10, Anifowose teaches a method for exploring a reservoir containing hydrocarbons (Anifowose abstract teaches a method of exploring a reservoir well for hydrocarbons through an analysis of reservoir rock grain sizes), the method comprising:
obtaining wireline log data from a well (Anifowose abstract and paragraphs [0004], [0016], and [0020] teach running a logging tool down a new second well to generate wireline logs for the well);
processing the wireline log data using a machine learning model to generate a set of predicted rock properties of the well (Anifowose abstract and paragraphs [0004], [0016], and [0020] teach processing the wireline logs for the new well using a machine learning model (trained from data of one or more first wells) to generate a set of continuous grain sizes (predicted rock properties) of the second well);
determining a difference between the wireline log data and the set of predicted rock properties of the well (Anifowose paragraphs [0049]-[0050] teach carrying out validation to determine a residual (difference) between a validation minority of the wireline log data structure and the estimated set of grain sizes (predicted rock properties));
applying the difference to generate log depth corrections for each of the rock properties (Anifowose paragraphs [0049]-[0050] teach applying the residual difference against a threshold to generate log depth corrections for adjusting the learning parameters of the machine learning model until the residual is less than the threshold and the machine learning model is validated, and paragraphs [0045]-[0047] teach where the learning parameters include weight coefficients that provide log depth corrections for the estimated grain sizes across the multiple depths); and
generating a pseudo-log of rock properties of the second well based at least in part on applying the log depth corrections to the predicted rock properties (Anifowose paragraph [0051] teaches generating a grain size log produced by the validated machine learning model as a pseudo-log based on the applied (validated) depth corrections to the predicted grain size rock properties).
In regards to claim 11, Anifowose teaches the method wherein rock properties include porosity, permeability, grain density, and geochemical and elemental data (Anifowose paragraph [0005] teaches where the reservoir rock property data includes porosity, permeability, grain size over a plurality of depths (as a measure of grain density), and geochemical/elemental data such as from gamma ray logging).
In regards to claim 12, Anifowose teaches the method wherein the machine learning model generates a continuous set of predicted rock properties along the main axis of the well (Anifowose abstract and paragraph [0004] teaches where the machine learning model generates a continuous grain size log over a plurality of continuous depths (along a depth axis) of the second well).
In regards to claim 13, Anifowose teaches the method wherein the machine learning model is an artificial neural network (Anifowose paragraph [0005] teaches where the machine learning mode ls an artificial neural network (ANN)).
In regards to claim 14, Anifowose teaches the method wherein the artificial neural network includes one or more hidden layers (Anifowose paragraph [0045] teaches one or more number of hidden layers of the artificial neural network that can be adjusted), the one or more hidden layers including a summation layer comprising a linear function (Anifowose paragraph [0032] teaches a hidden layer for a summation layer for registering multiple thin section images to form a compositional analysis image using a linear registration algorithm) and an activation layer comprising a sigmoid function (Anifowose paragraph [0046] teaches an activation layer to transform the input space to a high-dimensional nonlinear space using a sigmoid function).
In regards to claim 16, Anifowose teaches the method wherein a dataset comprising wireline data from one or more wells and a corresponding core sample dataset from the one or more wells are used to train and validate the artificial neural network (Anifowose paragraph [0004] teaches where a dataset comprising wireline data from one or more wells and a corresponding core sample dataset from the one or more wells at different depths in the wells are used to train the machine learning model (artificial neural network), and paragraph [0049] teaches where a portion (less than 50%) of the wireline log and grain size core sample dataset are used to validate the machine learning model), the wireline data representing input data processed by the artificial neural network, the core sample data representing a set of ground truth values corresponding to a set of predicted rock values (Anifowose paragraphs [0045]-[0047] teach where the wireline logs represent input data X1…X6 that are processed by the machine learning engine (artificial neural network), and the core sample data Y output represents a resulting high-dimensional nonlinear space that matches the nature of the subsurface data (as ground truth values) corresponding to a set of predicted output grain sizes).
In regards to claim 17, Anifowose teaches the method wherein the dataset is split into a training dataset and a validation dataset, the training dataset used to train the artificial neural network, the validation dataset used to validate a set of outputs of the artificial neural network (Anifowose paragraph [0049] teaches splitting the dataset is split into a training dataset (majority) and a minority (less than 50%) validation dataset, where the training dataset is used to train the machine learning engine (artificial neural network) and the validation dataset used to validate the outputs of the machine learning engine (artificial neural network)).
In regards to claim 18, Anifowose teaches the method wherein the artificial neural network is retrained with new training data to update a set of weights corresponding to a nonlinear function of the artificial neural network (Anifowose paragraph [0052] teaches where the machine learning model (artificial neural network) is retrained with new training data to derive new learning parameters, and paragraphs [0045]-[0047] teaches where the learning parameters include weight coefficients corresponding to a nonlinear function (such as a Gaussian or sigmoid function) of the machine learning engine (artificial neural network)).
Claim Rejections - 35 USC § 103
9. 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.
10. Claims 6 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Anifowose et al. (Us Pat. Pub. 2021/0254457) as applied to claim 4 or claim 10 above, and further in view of Zaiss et al. (US Pat. Pub. 2020/0072931, hereinafter "Zaiss").
In regards to claim 6, Anifowose teaches the method as explained in the rejection of claim 4 above.
Anifowose fails to expressly teach wherein the artificial neural network is trained using a Levenberg-Marquardt algorithm and a Bayesian regularization backpropagation algorithm.
Zaiss paragraph [0028] teaches where a machine learning estimation procedure comprises at least one neural network (artificial neural network), and Zaiss paragraph [0045] teaches where configuring a neural network (NN) includes selecting or adapting a regression model and an associated NN architecture. Zaiss paragraph [0048] teaches where input parameters are employed as starting values in a non-linear regression procedure, such as using a Levenberg-Marquardt-algorithm, in order to create a parameter map of a sample. Zaiss paragraph [0056] teaches further carrying out a training process using back-propagation optimization such as with a Bayesian regularization backpropagation algorithm.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to further combine the teachings of Zaiss because the training of an artificial neural network is known to involve the use of multiple types of algorithms such as a Levenberg-Marquardt algorithm to train an appropriate starting parameter map of an analyzed sample, and using a Bayesian regularization backpropagation algorithm to carry out a back-propagation optimization training process. Therefore, it would be well within the level of ordinary skill to specify known training algorithms such as the Levenberg-Marquardt algorithm and Bayesian regularization backpropagation algorithm to appropriately configure a neural network for efficiently performing parameter estimation.
In regards to claim 15, Anifowose teaches the method as explained in the rejection of claim 10 above.
Anifowose fails to expressly teach wherein the artificial neural network is trained using a Levenberg-Marquardt algorithm and a Bayesian regularization backpropagation algorithm.
Zaiss paragraph [0028] teaches where a machine learning estimation procedure comprises at least one neural network (artificial neural network), and Zaiss paragraph [0045] teaches where configuring a neural network (NN) includes selecting or adapting a regression model and an associated NN architecture. Zaiss paragraph [0048] teaches where input parameters are employed as starting values in a non-linear regression procedure, such as using a Levenberg-Marquardt-algorithm, in order to create a parameter map of a sample. Zaiss paragraph [0056] teaches further carrying out a training process using back-propagation optimization such as with a Bayesian regularization backpropagation algorithm.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to further combine the teachings of Zaiss because the training of an artificial neural network is known to involve the use of multiple types of algorithms such as a Levenberg-Marquardt algorithm to train an appropriate starting parameter map of an analyzed sample, and using a Bayesian regularization backpropagation algorithm to carry out a back-propagation optimization training process. Therefore, it would be well within the level of ordinary skill to specify known training algorithms such as the Levenberg-Marquardt algorithm and Bayesian regularization backpropagation algorithm to appropriately configure a neural network for efficiently performing parameter estimation.
Pertinent Art
11. Applicants are directed to consider additional pertinent prior art included on the Notice of References Cited (PTOL 892) attached herewith. The Examiner has pointed out particular references contained in the prior art of record within the body of this action for the convenience of the Applicant. Although the specified citations are representative of the teachings in the art and are applied to the specific limitations within the individual claim, other passages and figures may apply. Applicant, in preparing the response, should consider fully the entire reference as potentially teaching all or part of the claimed invention, as well as the context of the of the passage as taught by the prior art or disclosed by the Examiner. The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
C. Pei (US Pat Pub. 2012/0222901) discloses Synthetic Formation Evaluation Logs Based on Drilling Vibrations.
D. Millheim et al. (US Pat. No. 5,012,674) discloses Method of Exploration for Hydrocarbons.
E. Neff (US Pat. No. 6,654,692) discloses Method of Predicting Rock Properties from Seismic Data.
Conclusion
12. Any inquiry concerning this communication or earlier communications from the examiner should be directed to PAUL D LEE whose telephone number is (571)270-1598. The examiner can normally be reached on M to F, 9:30 am to 6 pm.
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, Arleen Vazquez can be reached at 571-272-2619. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see https://ppair-my.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/PAUL D LEE/Primary Examiner, Art Unit 2857 8/3/2026
Prosecution Insights