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 .
The office action is in response to the application filed on March 13, 2024.
Claims 1-14 are pending and have been examined. Claims 1-14 are rejected.
Information Disclosure Statement
Acknowledgment is made of the information disclosure statements filed March 13, 2024, August 14, 2024, October 09, 2024, February 17, 2025, April 17, 2025, and July 11, 2025, which comply with 37 CFR 1.97. As such, the information disclosure statements have been placed in the application file and the information referred to therein has been considered by the examiner.
Priority
Applicant's claim for the benefit of a prior-filed application under 35 U.S.C. 119(e) or under 35 U.S.C. 120, 121, 365(c), or 386(c) is acknowledged. The present application claims priority to U.S. Provisional application No. 63/246,090 (hereinafter "the '090 provisional application") filed on September 20, 2021.
The as-filed original specification of the '090 provisional application provides adequate support or enablement for all limitation elements of claims 1-14.
Therefore, the effective filing date for claims 1-14 of the instant application is the effective filing date of the provisional application, September 20, 2021.
Claim Objections
Claim 6 is objected to because of the following informalities:
"wherein a machine learning" should read "wherein machine learning".
Appropriate correction is required.
Claim 10 is objected to under 37 CFR 1.75 as being a substantial duplicate of claim 9. When two claims in an application are duplicates or else are so close in content that they both cover the same thing, despite a slight difference in wording, it is proper after allowing one claim to object to the other as being a substantial duplicate of the allowed claim. See MPEP § 608.01(m).
Claim 13 is objected to because of the following informalities:
"The computer program product according to claim 10," should read "The computer program product according to claim 12,".
Appropriate correction is required.
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.
Claim 10 is rejected under 35 U.S.C. 112(b) 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.
Claim 10 recites “wherein the improving the created at least two training datasets, wherein training dataset improvement is accomplished by using transfer learning.” This claim language is indefinite because it is grammatically incomplete, and its scope cannot be ascertained by a person of ordinary skill in the art. The premise of the first “wherein” clause is referring back to the “improving” step of claim 9 but is not followed by any predicate establishing what is being claimed about that step, before the claim proceeds directly into a second, nested “wherein” clause. It is unclear whether the first “wherein” clause was intended to introduce an independent limitation that was omitted, or whether the claim was intended to read differently altogether.
Therefore, Claim 10 is rejected.
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 therefore, subject to the conditions and requirements of this title.
Claims 1-14 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter.
According to the USPTO guidelines, a claim is directed to non-statutory subject matter if:
Step 1: The claim does not fall within one of the four statutory categories of invention (process, machine, manufacture, or composition of matter), or,
Step 2: The claim recites a judicial exception, e.g. an abstract idea, without reciting additional elements that amount to significantly more than the judicial exception, as determined using the following analysis:
Step 2A, Prong 1: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Step 2A, Prong 2: Does the claim recite additional elements that integrate the judicial exception into a practical application?
Step 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception?
MPEP 2106.04(a)(2)(I) states: "The mathematical concepts grouping is defined as
mathematical relationships, mathematical formulas or equations, and mathematical
calculations."
MPEP 2106.04(a)(2)(III) states: "Accordingly, the "mental processes" abstract idea grouping is defined as concepts performed in the human mind, and examples of mental
processes include observations, evaluations, judgements, and opinions.
Further, the MPEP states: "The courts do not distinguish between mental processes that
are performed entirely in the human mind and mental processes that require a human to use a
physical aid (e.g. pen and paper or a slide run) to perform the claim limitation.
Using the two-step inquiry, it is clear that Claims 1-14 are each directed to non-statutory
subject matter as shown below:
Please note the following:
The following groups of claims are expressed in different statutory categories:
Claims 1-11 are directed to a method for providing automated stratigraphy interpretations.
Claims 12-14 are directed to a computer program product storing computer readable program code which, when executed by a processor, cause the processor to carry out a process.
With respect to Claim 1, which is an independent claim:
Step 1: Claim 1 is directed to a method, also known as a process, which is one of the four statutory categories of patentable subject matter.
Step 2A, Prong 1: A judicial exception is recited in the claims as they recite mental processes, which are abstract ideas:
“A method for automated stratigraphy interpretation, comprising: creating at least two training datasets to be used for the interpretation;” ; Creating at least 2 training datasets to be used for stratigraphical interpretations is an abstract idea of a mental process that can practically be performed in the human mind, with or without the use of a physical aid such as pen and paper (including an observation, evaluation, judgment, opinion) -See MPEP § 2106.04(a)(2)(III).
“developing at least one machine learning technique, wherein the at least one learning technique is configured to extract and automatically label stratigraphic trends;” ; Developing a machine learning technique used to extract and automatically label stratigraphic trends is an abstract idea of a mental process that can practically be performed in the human mind, with or without the use of a physical aid such as pen and paper (including an observation, evaluation, judgment, opinion) -See MPEP § 2106.04(a)(2)(III).
“and computation of uncertainties for the interpretation.” ; Performing computations of uncertainties for interpretation purposes is an abstract idea of a mathematical relationship, as directed to “a mathematical relationship is a relationship between variables or numbers. A mathematical relationship may be expressed in words or using mathematical symbols”. See MPEP § 2106.04(a)(2)(I)(A).
Step 2A, Prong 2: The claims do not recite additional elements that integrate the judicial exception into a practical application:
Step 2B: The claims do not recite additional elements that amount to significantly more than the judicial exception.
Therefore, Claim 1 is directed to non-statutory subject matter and rejected.
With respect to Claim 2 which is dependent on Claim 1 respectively:
Step 2A, Prong 1: A judicial exception is recited in the claims as they recite mental processes, which are abstract ideas:
“wherein the method is configured to interpret sequence stratigraphy trends from the data sets.” ; Interpreting sequence stratigraphy trends from datasets is an abstract idea of a mental process that can practically be performed in the human mind, with or without the use of a physical aid such as pen and paper (including an observation, evaluation, judgment, opinion) -See MPEP § 2106.04(a)(2)(III).
Step 2A, Prong 2: The claims do not recite additional elements that integrate the judicial exception into a practical application:
Step 2B: The claims do not recite additional elements that amount to significantly more than the judicial exception.
Therefore, Claim 2 is directed to non-statutory subject matter and rejected.
With respect to Claim 3 which is dependent on Claim 1 respectively:
Step 2A, Prong 1: A judicial exception is recited in the claims as they recite mental processes, which are abstract ideas:
“wherein the method is configured to interpret grain size trends from the data sets.” ; Interpreting grain size trends from data sets is an abstract idea of a mental process that can practically be performed in the human mind, with or without the use of a physical aid such as pen and paper (including an observation, evaluation, judgment, opinion) -See MPEP § 2106.04(a)(2)(III).
Step 2A, Prong 2: The claims do not recite additional elements that integrate the judicial exception into a practical application:
Step 2B: The claims do not recite additional elements that amount to significantly more than the judicial exception.
Therefore, Claim 3 is directed to non-statutory subject matter and rejected.
With respect to Claim 4 which is dependent on Claim 1 respectively:
Step 2A, Prong 1: The claim incorporates the abstract idea of the independent claim.
Step 2A, Prong 2: The claims do not recite additional elements that integrate the judicial exception into a practical application:
“wherein at least one of the two training datasets is from field well log data.” ; The utilization of field well log data generally links the use of the abstract idea to a particular technological environment or field of use - See MPEP § 2106.05(h).
Step 2B: The claims do not recite additional elements that amount to significantly more than the judicial exception. The usage of field well log data is generally linked to a particular technological environment or field of use (civil/geotechnical engineering) - see MPEP 2106.05(h).
Therefore, Claim 4 is directed to non-statutory subject matter and rejected.
With respect to Claim 5 which is dependent on Claim 1 respectively:
Step 2A, Prong 1: The claim incorporates the abstract idea of the independent claim.
Step 2A, Prong 2: The claims do not recite additional elements that integrate the judicial exception into a practical application:
“wherein at least one of the two training datasets is from geotechnical data.” ; The utilization of geotechnical data generally links the use of the abstract idea to a particular technological environment or field of use - See MPEP § 2106.05(h).
Step 2B: The claims do not recite additional elements that amount to significantly more than the judicial exception. The usage of geotechnical data is generally linked to a particular technological environment or field of use (civil/geotechnical engineering) - see MPEP 2106.05(h).
Therefore, Claim 5 is directed to non-statutory subject matter and rejected.
With respect to Claim 6 which is dependent on Claim 1 respectively:
Step 2A, Prong 1: The claim incorporates the abstract idea of the independent claim.
Step 2A, Prong 2: The claims do not recite additional elements that integrate the judicial exception into a practical application:
“wherein a machine learning is used to perform the interpretation.” ; Utilizing machine learning for interpretation purposes only amounts to "apply it" and the mere instructions to implement an abstract idea on a computer - see MPEP 2106.05(f)(1) in addition to generally links the use of the abstract idea to a particular technological environment or field of use - See MPEP § 2106.05(h).
Step 2B: The claims do not recite additional elements that amount to significantly more than the judicial exception. Utilizing machine learning for interpretation purposes amounts to "apply it" and mere instructions to implement an abstract idea on a computer. The claim fails to recite details of how a solution or outcome to a problem is accomplished because it is unclear how the "AI system" or "machine learning" is used nor does the specification make it clear how these actions are performed - see MPEP 2106.05(f)(1)). The usage of machine learning is generally linked to a particular technological environment or field of use (AI/ML) - see MPEP 2106.05(h).
Therefore, Claim 6 is directed to non-statutory subject matter and rejected.
With respect to Claim 7 which is dependent on Claim 1 respectively:
Step 2A, Prong 1: The claim incorporates the abstract idea of the independent claim.
Step 2A, Prong 2: The claims do not recite additional elements that integrate the judicial exception into a practical application:
“wherein the machine learning is performed through a neural network.” ; Utilizing machine learning for interpretation purposes only amounts to "apply it" and the mere instructions to implement an abstract idea on a computer - see MPEP 2106.05(f)(1) in addition to generally links the use of the abstract idea to a particular technological environment or field of use - See MPEP § 2106.05(h).
Step 2B: The claims do not recite additional elements that amount to significantly more than the judicial exception. Utilizing machine learning for interpretation purposes amounts to "apply it" and mere instructions to implement an abstract idea on a computer. The claim fails to recite details of how a solution or outcome to a problem is accomplished because it is unclear how the "AI system" or "machine learning" is used nor does the specification make it clear how these actions are performed - see MPEP 2106.05(f)(1)). The usage of machine learning is generally linked to a particular technological environment or field of use (AI/ML) - see MPEP 2106.05(h).
Therefore, Claim 7 is directed to non-statutory subject matter and rejected.
With respect to Claim 8 which is dependent on Claim 7 respectively:
Step 2A, Prong 1: A judicial exception is recited in the claims as they recite mental processes, which are abstract ideas:
“wherein weights and parameters are calculated with each successive evaluation of a subsequent data set.” ; Calculating weights and parameters with successive evaluations of subsequent datasets is an abstract idea of a mathematical relationship, as directed to “a mathematical relationship is a relationship between variables or numbers. A mathematical relationship may be expressed in words or using mathematical symbols”. See MPEP § 2106.04(a)(2)(I)(A).
Step 2A, Prong 2: The claims do not recite additional elements that integrate the judicial exception into a practical application:
Step 2B: The claims do not recite additional elements that amount to significantly more than the judicial exception.
Therefore, Claim 8 is directed to non-statutory subject matter and rejected.
With respect to Claims 9 and 10 which have identical claim limitations:
Step 2A, Prong 1: A judicial exception is recited in the claims as they recite mental processes, which are abstract ideas:
“improving the created at least two training datasets, wherein training dataset improvement is accomplished by using transfer learning.” ; Improving the training datasets by using transfer learning is an abstract idea of a mental process that can practically be performed in the human mind, with or without the use of a physical aid such as pen and paper (including an observation, evaluation, judgment, opinion) -See MPEP § 2106.04(a)(2)(III).
Step 2A, Prong 2: The claims do not recite additional elements that integrate the judicial exception into a practical application:
Step 2B: The claims do not recite additional elements that amount to significantly more than the judicial exception.
Therefore, Claims 9 and 10 are directed to non-statutory subject matter and rejected.
With respect to Claim 11 which is dependent on Claim 1 respectively:
Step 2A, Prong 1: The claim incorporates the abstract idea of the independent claim.
Step 2A, Prong 2: The claims do not recite additional elements that integrate the judicial exception into a practical application:
“wherein at least one data set contain data from a gamma ray survey.” ; The utilization of gamma ray survey data generally links the use of the abstract idea to a particular technological environment or field of use - See MPEP § 2106.05(h).
Step 2B: The claims do not recite additional elements that amount to significantly more than the judicial exception. The usage of gamma ray survey data is generally linked to a particular technological environment or field of use (civil/geotechnical engineering) - see MPEP 2106.05(h).
Therefore, Claim 11 is directed to non-statutory subject matter and rejected.
With respect to Claim 12, which is an independent claim:
Step 1: Claim 12 is directed to a computer usable medium configured with computer readable program code, which does not fall within at least one of the four statutory categories of patentable subject matter. Under broadest reasonable interpretation, the claimed “computer usable medium” is not limited to non-transitory forms and therefore, encompasses transitory propagating signals per se. The specification also does not define or limit the term to exclude transitory embodiments further negating subject matter eligibility.
Therefore, Claim 12 is directed to non-statutory subject matter and rejected.
With respect to Claim 13 which is dependent on Claim 12 respectively:
Step 2A, Prong 1: The claim incorporates the subject matter ineligibility rejection of the independent claim, however on its own, a judicial exception is recited in the claims as they recite mental processes, which are abstract ideas:
“wherein the method further comprises improving the created at least two training datasets, wherein training dataset improvement is accomplished by using transfer learning.” ; Improving the at least 2 created training datasets by using transfer learning is an abstract idea of a mental process that can practically be performed in the human mind, with or without the use of a physical aid such as pen and paper (including an observation, evaluation, judgment, opinion) -See MPEP § 2106.04(a)(2)(III).
Step 2A, Prong 2: The claims do not recite additional elements that integrate the judicial exception into a practical application:
Step 2B: The claims do not recite additional elements that amount to significantly more than the judicial exception.
Therefore, Claim 13 is directed to non-statutory subject matter and rejected.
With respect to Claim 14 which is dependent on Claim 12 respectively:
Step 2A, Prong 1: The claim incorporates the subject matter ineligibility rejection and abstract idea of its independent claim.
Step 2A, Prong 2: The claims do not recite additional elements that integrate the judicial exception into a practical application:
“wherein the computer is one of a server, a personal computer, a cellular telephone, and a cloud-based computing arrangement.” ; Utilizing a server, personal computer, cellular telephone, and cloud-based computing arrangement only amounts to "apply it" and the mere instructions to apply the abstract idea using a generic computer component - see MPEP 2106.05(f)(2) in addition to generally links the use of the abstract idea to a particular technological environment or field of use - See MPEP § 2106.05(h).
Step 2B: The claims do not recite additional elements that amount to significantly more than the judicial exception. Utilizing a server, personal computer, cellular telephone, and cloud-based computing arrangement amounts to "apply it" (or an equivalent) and mere instructions to implement an abstract idea on a computer using a generic computer component or merely using a computer in its ordinary capacity as a tool to perform an existing process. -See MPEP 2106.05(f)(2). The usage of a server, personal computer, cellular telephone, and cloud-based computing arrangement is generally linked to a particular technological environment or field of use (comp. hardware) - see MPEP 2106.05(h).
Therefore, Claim 14 is directed to non-statutory subject matter and rejected.
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 (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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
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 non-obviousness.
Claims 1, 3, 4, 6, 11, and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Halotel et. Al, (Value of Geologically Derived Features in Machine Learning Facies Classification, published November 16, 2019, hereinafter "Halotel"), in view of Hall, (Facies classification using machine learning, published October 01, 2016). The specified dates are before the effective filing date of this application, i.e., March 13, 2024, as well as the provisional application date, September 20, 2021, where it applies.
With respect to independent Claims 1 and 12:
Halotel teaches:
"creating at least two training datasets to be used for the interpretation;" ([Pg. 16] discloses reshuffling well assignments to compile and create 36 distinct training/validation set combinations for interpretation, "To design the training and validation sets, two wells in any one case were set aside for validation, while the remaining seven wells were used for training. Together, the two validation wells and seven training wells represent one possible training/validation case…To accommodate this, the well sets for validation and training were reshuffled until all possible combinations were used. This was motivated by the lack of a priori means to select the combination of wells able to predict with the highest accuracy. Shuffling of the training and validation sets produces predictions which may vary from one data combination to another. Here, the uncertainty range is assessed across the 36 possible predictions based on different combinations of training and validation sets for each of the three blind test well experiments.” [Pg. 16] further discloses a second independently configured training dataset instance, “A slightly different experimental setup was implemented to investigate the value of the additional geologically constrained input. The training data were set to seven wells: Luke G U, Kimzey A, Cross H Cattle, Nolan, Recruit F9, Newby, and Churchman Bible, while the validation set was composed of two wells: Shrimplin and Alexander D (Fig. 1b). The test set contained the remaining well (Shankle). The choice of training and validation sets was made such that at least one sample from each facies was contained in the training set, increasing the likelihood of correct facies assignment and therefore higher classification accuracy.”)
“and computation of uncertainties for the interpretation.” ([Pg. 7] discloses calculating computations of uncertainties for the interpretation, “The second experiment examines the impact of additional geologically independent features, through evaluation of the test prediction accuracy and input feature importance. Then, the impact of random and systematic noise on the robust ness of the classifier is investigated. Finally, the classification uncertainty is assessed using different combinations of training/validation sets.” [Pg. 26] further discloses computation of uncertainties, “Uncertainty in facies classification is quantified by the range of outcomes across the multiple classifiers computed based on the unique training/validation well combinations.”)
Halotel alone does not appear to explicitly disclose:
“developing at least one machine learning technique, wherein the at least one learning technique is configured to extract and automatically label stratigraphic trends;”
However, Hall teaches:
“developing at least one machine learning technique, wherein the at least one learning technique is configured to extract and automatically label stratigraphic trends;” ([Pg. 906] discloses developing a machine learning technique configured to extract and label (assign) stratigraphic trends, “You can think of it as a set of data-analysis methods that includes classification, clustering, and regression. These algorithms can be used to discover features and trends within the data without being explicitly programmed, in essence learning from the data itself…Once we have trained a classifier, we will use it to assign facies to wells that have not been described.” [Pg. 909] further discloses extracting and labeling stratigraphic trends, “To evaluate the accuracy of our classifier we will use the well we kept for a blind test and compare the predicted facies with the actual ones. We need to extract the facies labels and features of this data set and rescale the features using the same parameters used to rescale the training set…Now we can use our trained classifier to predict facies labels for this well, and store the results in the Prediction column of the test_well dataframe. Because we know the true facies labels of the vectors in the test data set, we can use the results to evaluate the accuracy of the classifier on this well.”)
Halotel and Hall are analogous art and in the same field of invention because both references pertain to machine learning for lithofacies classification and apply support vector machines to wireline well-log data. While Halotel teaches advancing science by integrating geological interpretative features (grain size, pore size) and rules to improve classifier accuracy and uncertainty assessment, Hall teaches utilizing python tools to train a support vector machine on a specific dataset from Kansas gas fields with explicit variables like gamma ray and resistivity. It would have been obvious to a person having ordinary skill in the art (PHOSITA) before the effective filing date of the claimed invention to implement the base reference of Halotel (assessing and reducing interpretation uncertainty and human bias) with the teachings of Hall (specific log measurements like GR and PHIND) in order to accelerate how experts label large sets of well data and find better ways to predict rock types from measurements. One of ordinary skill in the art would be motivated to do so because by integrating Hall's framework into the methods of Halotel one would be able to note that a system as such can allow us to, "anticipate that the use of additional geological interpretative features, combined with conventional wireline log features, will lead to considerable improvement in the facies classification of cored wells, {[pg. 28] of Halotel}."
Therefore, Claims 1 and 12 are rejected.
With respect to Claim 3:
The combination of Halotel-Hall teaches:
"wherein the method is configured to interpret grain size trends from the data sets." (Halotel [Pg. 7] discloses interpreting grain size trends from the datasets, “Facies interpretation relies on the geological context described by geologically interpretative features and petrophysical rules. A lithofacies is primarily defined based on the texture, mineralogy, and grain size,” Halotel [Pg. 24] further discloses manipulating the grain size in pertinence to interpreting trends, “Injecting random noise (i.e., 100% depth-shuffled grain size inputs) results in the classifier disregarding this feature. This is emphasized by the change of rank of the grain size input with regards to the feature importance (from third most important to least important, Fig. 8c), while the average test accuracy prediction remains as high as 99%.”)
Therefore, Claim 3 is rejected.
With respect to Claim 4:
The combination of Halotel-Hall teaches:
"wherein at least one of the two training datasets is from field well log data." (Hall [Pg. 906] discloses that the two training datasets contain field well log data, “In our case, the features will be well-log data from nine gas wells…The data set we will use comes from a University of Kansas class exercise on the Hugoton and Panoma gas fields…In machine learning terminology, the set of measurements at each depth interval comprises a feature vector, each of which is associated with a class (the facies type). We will use the pandas library to load the data into a data frame, which provides a convenient data structure to work with well-log data.”)
Therefore, Claim 4 is rejected.
With respect to Claim 6:
The combination of Halotel-Hall appears to explicitly disclose:
“wherein a machine learning is used to perform the interpretation.” (Halotel [Pg. 6] discloses using machine learning to perform interpretations, “Automation of lithofacies classification using machine learning tools appears to a promising solution for the challenges faced during traditional manual interpretation.” Halotel [Pg. 9] further teaches machine learning based interpretations, “Supervised machine learning classification implies setting up a system of inputs (i.e., explanatory variables), whose combination results in a target variable (i.e., facies labels). Defining the correct combination of inputs is essential for the classification outcome and plays a major role in the performance of the classifier. The output data in this supervised classification study are interpreted lithofacies, which are subject to human bias and uncertainty.”)
Therefore, Claim 6 is rejected.
With respect to Claim 11:
The combination of Halotel-Hall appears to explicitly disclose:
“wherein at least one data set contain data from a gamma ray survey.” (Hall [Pg. 906] discloses that at least one data set contains data from a gamma ray survey, “We can use data.describe() to provide a quick overview of the statistical distribution of the training data (Table 1). We can see from the count row in Table 1 that we have a total of 3232 feature vectors in the data set. The feature vectors consist of the following variables: 1) Gamma ray (GR).”)
Therefore, Claim 11 is rejected.
Claims 2, 7, and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Halotel, in view of Hall, further in view of Snow et. Al (US20150378042A1, filed on February 13, 2014, hereinafter "Snow"). The specified dates are before the effective filing date of this application, i.e., March 13, 2024, as well as the provisional application date, September 20, 2021, where it applies.
With respect to Claim 2:
The combination of Halotel-Hall does not appear to explicitly disclose:
"wherein the method is configured to interpret sequence stratigraphy trends from the data sets."
However, Snow teaches:
"wherein the method is configured to interpret sequence stratigraphy trends from the data sets." ([0108] discloses interpreting stratigraphy trends (patterns) from the datasets, “Using a trained artificial neural network may enable classifications of log measurements shape patterns to be of a higher certainty, and may also be used as a filter to identify well log measurements that need a secondary attribute to be applied in order to identify geologic features. For example, the neural network could be optimized for identifying all well log measurements with a coarsening upwards or fining upwards pattern. The identified patterns could then be subjected to further tests to evaluate if they are composite or simple log measurement shape patterns.” [0114] further discloses that the stratigraphy trends from these datasets can provide interpretations, “This relationship has led geoscientists to use the log shape patterns observed in well log measurements to make interpretations on depositional environment.”)
Halotel-Hall-Snow are analogous art and in the same field of invention because all three references pertain to analyzing subsurface geological formations and wellbore data, specifically utilizing computational or machine learning techniques to classify or characterize rock properties and lithofacies from well measurements. While Halotel teaches adding geological interpretative features and rule-based constraints to machine learning to reduce bias and measure uncertainty, Hall teaches the shift from expensive proprietary software to free open-source machine learning packages like scikit-learn for processing well logs. Similarly, Snow teaches a direct mathematical or attribute-based method to derive physical formation characteristics from specific axial changes in raw wellbore measurements. It would have been obvious to a person having ordinary skill in the art (PHOSITA) before the effective filing date of the claimed invention to implement the base reference of Halotel (Geological Integration) with the teachings of Hall (predicting facies on unassigned wells using big data) and the teachings of Snow (Algorithmic Subsurface Axial Changes) in order to automate geological data evaluation, enhance open-source tool application, and improve upon physical parameter inversion. One of ordinary skill in the art would be motivated to do so because by integrating Hall and Snow's frameworks into the methods of Halotel one would be able to recognize that a system as such can, "provide powerful algorithms that can be applied to problems in the geosciences with just a few lines of code, {[Pg. 909] of Hall}."
Therefore, Claim 2 is rejected.
With respect to Claim 7:
The combination of Halotel-Hall alone does not appear to explicitly disclose:
“wherein the machine learning is performed through a neural network.”
However, Snow teaches:
“wherein the machine learning is performed through a neural network.” ([0108] discloses utilizing machine learning specifically a neural network, “Neural Network Method for Classification: This method utilizes a neural network that is a trained on a sample dataset utilizing a plurality of the attributes and methods described above to classify the log-shape patterns observed in the well log data into the log shape pattern types given in FIG. 3.”)
Therefore, Claim 7 is rejected.
With respect to Claim 14:
The combination of Halotel-Hall alone does not appear to explicitly disclose:
“wherein the computer is one of a server, a personal computer, a cellular telephone, and a cloud-based computing arrangement.”
However, Snow teaches:
“wherein the computer is one of a server, a personal computer, a cellular telephone, and a cloud-based computing arrangement.” ([0136] discloses a computer system with servers, hardware components, cloud-based computing arrangements, and cellular connectivity, “FIG. 25 depicts an example computing system 100 in accordance with some embodiments. The computing system 100 may be an individual computer system 101A or an arrangement of distributed computer systems…The processor(s) 104 may also be connected to a network interface 108 to allow the computer system 101A to communicate over a data network 110 with one or more additional computer systems and/or computing systems, such as 101B, 101C, and/or 101D (note that computer systems 101B, 101C and/or 101D may or may not share the same architecture as computer system 101A, and may be located in different physical locations, for example, computer systems 101A and 101B may be on a ship underway on the ocean or on a well drilling location, while in communication with one or more computer systems such as 101C and/or 101D that may be located in one or more data centers on shore, aboard ships, and/or located in varying countries on different continents).” [0139] further reinforces that this computing arrangement can be configured to include the disclosed computing components, “It should be appreciated that computing system 100 is only one example of a computing system, and that computing system 100 may have more or fewer components than shown, may combine additional components not depicted in the example embodiment of FIG. 25, and/or computing system 100 may have a different configuration or arrangement of the components depicted in FIG. 25. The various components shown in FIG.25 may be implemented in hardware, software, or a combination of both hardware and software, including one or more signal processing and/or application specific integrated circuits.”) Examiner’s Note: Flexibility of computer system includes the capability for distributed cloud and remote network storage/execution as well as edge computing devices i.e. (cellular) and onshore data centers.
Therefore, Claim 14 is rejected
Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over Halotel, in view of Hall, further in view of Wang et. Al (Probabilistic identification of underground soil stratification using cone penetration tests, published May 09, 2013, hereinafter "Wang"). The specified dates are before the effective filing date of this application, i.e., March 13, 2024, as well as the provisional application date, September 20, 2021, where it applies.
With respect to Claim 5:
The combination of Halotel-Hall appears to explicitly disclose:
“wherein at least one of the two training datasets-------” (Halotel [Pg. 15] discloses at least one of the two training datasets, “A training set must therefore be representative of the patterns to be classified to produce adequate estimates (Duda et al. 2012). The training set is used to fit the model for any combination of hyperparameters,…while the remaining k −1 folds are used as the training set to fit the model”)
The combination of Halotel-Hall does not appear to explicitly disclose:
"---------is from geotechnical data."
However, Wang teaches:
"---------is from geotechnical data." ([Pg. 766] discloses that the training data encompasses the geotechnical type, “develops Bayesian approaches for underground soil stratum identification and soil classification using cone penetration tests (CPTs). The uncertainty in the CPT-based soil classification using the Robertson chart is modeled explicitly in the Bayesian approaches, and the probability that the soil belongs to one of the nine soil types in the Robertson chart based on a set of CPT data.” [Pg. 775] further teaches that the data is of geotechnical type, “CPT data. A Bayesian framework for soil stratum identification and soil classification based on CPT data has been developed. The probability that the soil belongs to one of the nine soil types in the Robertson chart for a given set of CPT data has been formulated using the maximum entropy principle.”) Examiner’s Note: As per [033] of the specification, CPT data is geotechnical data.
Halotel-Hall-Wang are analogous art and in the same field of invention because all three references pertain to automating subsurface and geological classification while accounting for uncertainty using advanced data-driven or probabilistic methods. While Halotel teaches integrating human expert knowledge and geological rule-based constraints (such as grain size, pore size, and argillaceous content) directly into machine learning inputs, Hall teaches the democratization of data science tools, specifically highlighting how free, open-source Python toolkits like scikit-learn lower the barrier for analyzing voluminous well-log datasets. Similarly, Wang teaches applying probabilistic bayesian model class selection and system identification to Cone Penetration Tests (CPTs) to determine underground layer boundaries and soil types simultaneously. It would have been obvious to a person having ordinary skill in the art (PHOSITA) before the effective filing date of the claimed invention to implement the base reference of Halotel (Geological Feature Integration) with the teachings of Hall (Open-Source Machine Learning on Wireline Logs) and the teachings of Wang (Bayesian Stratum Identification via CPT) in order to enhance subsurface classification, modeling data uncertainty, and applying advanced computational or statistical algorithms to sub-surface measurements. One of ordinary skill in the art would be motivated to do so because by integrating Hall and Wang's frameworks into the methods of Halotel one would be able to recognize that a system as such, "improves substantially the resolution along the depth in the characterization of underground soil stratigraphy. CPT also enjoys many other advantages. It is less disruptive than drilling operations and has a strong theoretical basis, {[Pg. 766] of Wang}."
Therefore, Claim 5 is rejected.
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Halotel, in view of Hall, further in view of Snow, further in view of Siahkoohi et. Al (The importance of transfer learning in seismic modeling and imaging, published October 09, 2019, hereinafter "Siahkoohi"). The specified dates are before the effective filing date of this application, i.e., March 13, 2024, as well as the provisional application date, September 20, 2021, where it applies.
With respect to Claim 8:
The combination of Halotel-Hall-Snow alone does not appear to explicitly disclose:
“wherein weights and parameters are calculated with each successive evaluation of a subsequent data set.”
However, Siahkoohi teaches:
“wherein weights and parameters are calculated with each successive evaluation of a subsequent data set.” ([Pg. A48] discloses calculating and successively evaluating (simulating) weights and parameters of subsequent datasets, “The above operations are key to iterative wave-equation-based inversion in which observed data are matched with simulated data. Because each operation involves the wave equation, simulations either miss important physics or are too expensive to evaluate accurately. The key idea now is to condition by training CNNs with pairs of low- and high-fidelity simulations…During transfer learning, the weights of a pretrained neural network from the nearby surveys are finetuned to work with data from the current survey. Because transfer learning can be done with a relatively small fraction (≈5%) of data from the pertinent survey, this can lead to an economically viable workflow because this type of data can often be made available, e.g., by applying more expensive conventional processing on a small fraction of the data of the current survey.” [Pg. A51] further showcases sequentially and successively evaluating (simulating) and updating the weights and parameters of the dataset, “As an example of gradient conditioning, we pretrain a CNN by minimizing objectives 4 with λ ¼ 100 for 100 passes over 804 pairs of low- and high-fidelity single-shot reverse time migrations simulated for four nearby surveys defined by four different vertical 2D slices taken from the 3D BG Compass velocity model. As before, we find the value for λ via extensive parameter testing. Because these 2D slices are different from the current velocity model, we need to transfer train. We do this by carrying out an additional training round via 20 passes over only 11 low- and high-fidelity gradient pairs, simulated on 1 in every 20 shot locations, out of 201 available shot locations.”)
Halotel-Hall-Snow-Siahkoohi are analogous art and in the same field of invention because all four references pertain to utilizing data-driven automation and computational models to analyze subterranean formations and manage incomplete subsurface datasets. While Halotel teaches dynamically adding geological rule-based constraints and expert insights into machine learning to reduce bias and measure uncertainty in facies classification, Hall teaches the practical use of open-source Python tools like scikit-learn and supervised Support Vector Machines to classify lithofacies from well logs. Similarly, Snow teaches a specific procedural method for accepting physical wellbore measurements and calculating formation attributes across an axial interval, while Siahkoohi teaches applying transfer learning and neural networks pre-trained on nearby surveys to map low-cost seismic data into high-fidelity solutions. It would have been obvious to a person having ordinary skill in the art (PHOSITA) before the effective filing date of the claimed invention to implement the base reference of Halotel (Subsurface Analysis) with the teachings of Hall (classify lithofacies using well-log measurements) with the teachings of Snow (calculating axial attribute changes) further with the teachings of Siahkoohi (low-fidelity seismic forward-modeling data into high-fidelity solutions using nearby survey data) in order to enhance computational models to process high-dimensional subsurface measurements and bridge the gap between raw physical observations and geological insight. One of ordinary skill in the art would be motivated to do so because by integrating Hall, Snow, and Siahkoohi’s frameworks into the methods of Halotel one would be able to recognize that, "Key in this development will be the ability of these neural networks to generalize sufficiently so that the cost of transfer learning remains small enough, {[pg. A51] of Siahkoohi}."
Therefore, Claim 8 is rejected.
Claims 9, 10, and 13 are rejected under 35 U.S.C. 103 as being unpatentable over Halotel, in view of Hall, further in view of Siahkoohi et. Al (The importance of transfer learning in seismic modeling and imaging, published October 09, 2019, hereinafter "Siahkoohi"). The specified dates are before the effective filing date of this application, i.e., March 13, 2024, as well as the provisional application date, September 20, 2021, where it applies.
With respect to Claims 9, 10, and 13:
The combination of Halotel-Hall-Siahkoohi alone does not appear to explicitly disclose:
“improving the created at least two training datasets, wherein training dataset improvement is accomplished by using transfer learning.”
However, Siahkoohi teaches:
“improving the created at least two training datasets, wherein training dataset improvement is accomplished by using transfer learning.” ([Pg. A47] discloses utilizing transfer learning, “we use transfer learning to fine-tune this pretrained network with a small percentage of additional training data obtained from the current survey.” [Pg. A50] showcases improving the created two training dataset examples, “To demonstrate how CNNs handle incomplete and/or inaccurate physics, we consider two examples in which we use a poor discretization…For this purpose, we first train a CNN on pairs of low- and high-fidelity single-shot reverse time migrations from a background velocity model that is obtained from a “nearby” survey…Second, we correct wave simulations themselves with a neural network that is trained on a family of related nearby velocity models.” [Pg. A51] further discloses improving the datasets through transfer learning, “Because the cropped velocity structures are less complex than the original velocity model, an additional round of transfer learning is required. We fine-tune the CNN by training on 1500 (5%) low- and high-fidelity snapshot pairs. For training, we use λ ¼ 100 in objectives 4, and we made 4.5 passes through the full data set (i.e., we touch all shots four times and half of them five times) followed by 11 passes during transfer learning… We argue that this may lead to future improvements in efficiency in which computationally expensive (e.g., wave-equation driven) processing can partly be replaced by a potentially numerically more efficient neural network.”)
Halotel-Hall-Siahkoohi are analogous art and in the same field of invention because all three references pertain to using machine learning and data-driven algorithms to solve complex subsurface, geophysical, and petrophysical problems that are traditionally data-heavy, manual, or computationally expensive. While Halotel teaches comparing support vector machines and random forest classifiers, Hall teaches a basic supervised learning workflow using well-log measurements from gas wells to classify lithofacies. Similarly, Siahkoohi teaches forward modeling and seismic data correction using pretraining and transfer learning. It would have been obvious to a person having ordinary skill in the art (PHOSITA) before the effective filing date of the claimed invention to implement the base reference of Halotel (Integration of Geological Rules & Uncertainty) with the teachings of Hall (Open-Source Machine Learning Tutorial) and the teachings of Siahkoohi (Physics Correction via Transfer Learning) in order to successfully apply advanced computational methods to solve geotechnical and geophysical challenges by improving efficiency, automation, or data fidelity. One of ordinary skill in the art would be motivated to do so because by integrating Hall and Siahkoohi's frameworks into the methods of Halotel one would be able to recognize that a system as such can allow us to, "anticipate that the use of additional geological interpretative features, combined with conventional wireline log features, will lead to considerable improvement in the facies classification of cored wells, {[pg. 28] of Halotel}."
Therefore, Claims 9, 10, and 13 are rejected.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure: Chen et. Al (MED3D: TRANSFER LEARNING FOR 3D MEDICAL IMAGE ANALYSIS, Published July 17, 2019).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to NOOR F CHEEMA whose telephone number is (571)272-9642. The examiner can normally be reached Monday-Friday 7:30am-5:00pm alternative Fridays off.
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 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.
/N.F.C./Examiner, Art Unit 2142
/Mariela Reyes/Supervisory Patent Examiner, Art Unit 2142
Prosecution Insights