DETAILED ACTION
Claims 1-20 are presented for examination.
This Office Action is in response to submission of documents on August 18, 2023.
Provisional nonstatutory double patenting rejection of claims 1-20 is maintained.
Rejection of claims 1-20 under 35 U.S.C. 101 for being directed to unpatentable subject matter is maintained.
Rejection of claims 1-6, 8-13, and 15-19 under 35 U.S.C. 103 for being obvious over Tawil in view Anifowose, Fornel, and Jagnnathan is maintained.
Rejection of claims 2, 5, 9, 12, 16, and 19 under 35 U.S.C. 103 for being obvious over Tawil in view Anifowose, Jagnnathan, and Fornel is maintained.
Rejection of claims 7, 14, and 20 under 35 U.S.C. 103 for being obvious over Tawil in view Anifowose, Fornel, Jagnnathan, and Chandra is maintained.
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 .
Response to Arguments
Regarding the provisional nonstatutory double patenting rejection of claims 1-20, Examiner acknowledges Applicant’s request that the rejection be held in abeyance until such time that the present application or co-pending application issue as a patent. Accordingly, the provisional rejection is maintained.
Regarding rejection of claims 1-20 under 35 U.S.C. 101 as being directed to unpatentable subject matter, Examiner is not persuaded by the present amendments and arguments. The claims, as amended, still recite judicial exceptions with additional elements that do not integrate the abstract idea into a practical application, nor do the claims recite significantly more than the judicial exceptions. For the following reasons, the rejection of claims 1-20 under 35 U.S.C. 101 are maintained:
As an initial matter, Applicant asserts that “the Examiner acknowledged during the Examiner interview conducted on February 2, 2026, that amendments according to those herein would likely overcome the present rejections.” Response at pg. 12. However, because the amendments presented herein are different than the amendments proposed for the interview, Examiner further indicated that any amendments would be considered once submitted in final form. As indicated in the Interview Summary, the proposed amendments that included “adjusting…” would be considered an additional element and may, if amended, include significantly more than the recited judicial exception. However, as presented herein, the limitation of “executing the second ML model…” is identified as a mental process and therefore cannot integrate the recited judicial exceptions into a practical application. See MPEP 2106.05, Subsection I.
To be directed to patentable subject matter, the claims must include additional elements (i.e., elements that are not judicial exceptions themselves) that integrate the judicial exceptions into a practical application and/or recite an improvement in technology. While the claims, as amended, do not include such elements, the Specification includes disclosure and concepts that, if incorporated, would likely overcome the rejection.
First, regarding an improvement in technology, the Specification, at [0017], includes disclosure related to how the present invention improves the accuracy of production forecasts. Thus, an additional element that incorporates this into the claims would likely overcome the rejection.
Second, at [0054], the Specification details an application wherein new wellsite data is received after the models have been generated and the models are automatically updated to reflect the new data (i.e., model parameters are readjusted). Performing such updates would not be practically performed in the human mind and therefore would be an additional element that integrates the judicial exceptions into a practical application.
Regarding rejection of the claims under 35 U.S.C. 112(a) and 35 U.S.C. 112(b), Examiner is persuaded in by the arguments and amendments. Accordingly, the rejections are withdrawn. However, in light of the amendments, a new rejection of the claims under 35 U.S.C. 112(b) is asserted. Particularly, the claims are indefinite for being unclear as to the functionality of the first ML model. The rejection, below, further elaborates on the issue.
Generally regarding the claims, the limitations of “a first well model,” “a second well model,” “a first ML model,” and “a second ML model” require different inputs and result in different outputs. To improve the readability of the claims and to generally clarify what is being claimed, Examiner suggests reciting the ML models as a two-step process: “training the ML model using X as training data, wherein the ML is trained to output Y in response to Z as inputs; and providing A to the ML model to generate, in response, B as output.”1 Thus, it is clearer what is being provided as both training data to the ML models and what is being provided to the ML models upon execution. Similarly, additional clarification regarding what each model (i.e., non-ML model) is modelling will improve clarity of the claims.
Regarding the rejection of the independent claims under 35 U.S.C. 103 as being obvious over Tawil in view of Anifowose, Fornel, and Jagnnathan, Examiner is not persuaded by the present amendments and arguments. Because the limitation of “generating, by the first ML model, an initial version of the second well model” is indefinite (see rejection under 35 U.S.C. 112(b), below), Examiner is required to give broadest reasonable interpretation to the limitation of “executing the second ML model to generate output comprising an adjustment to the initial version of the second well model, wherein the adjustment to the initial version of the second well model comprises automatically applying a set of updated parameters to the initial version of the second well model.” According to Examiner’s present interpretation, the limitation is taught at least by Jagnnathan at [0027]-[0028]. Accordingly, the rejection is maintained.
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 1-20 are provisionally rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-7, 9-15, and 17-20 of co-pending Application No. 17/560,982 (reference application). Although the claims at issue are not identical, they are not patentably distinct from each other because all of the limitations of this pending application are substantially recited in the claims of the reference application.
Application No. 17/556,092
Application No. 17/560,982
Claim 1:
A computer-implemented method of parameter matching for well planning and production forecasting, the method comprising:
acquiring, by a computing device from a data store, wellsite data for one or more existing production wells in a hydrocarbon producing field;
transforming, by the computing device, the wellsite data into one or more model data sets for predictive modeling by validating and clustering the wellsite data;
training, by using at least a first portion of the one or more model data sets as first training data, a first machine learning (ML) model to predict well logs for the one or more existing production wells; executing the first ML model, using at least a second portion of the one or more model data sets as input, to generate predicted well logs and
produce a first well model for estimating production of the one or more existing production wells;
tuning parameters of the first well model based on a comparison between the estimated production and an actual production of the one or more existing production wells, wherein tuning the parameters comprises generating tuned parameters by adjusting the estimated production based on the actual production;
training, using the tuned parameters of the first well model as second training data, a second ML model to predict updated parameters for a second well model corresponding with a new production well in the hydrocarbon producing field;
…
forecasting production of the new production well using the second well model updated with the parameter corrections generated by the second ML model.
[From above…]
executing the second ML model to generate output comprising an adjustment to the initial version of the second well model, wherein the adjustment to the initial version of the second well model comprises automatically applying a set of updated parameters to the initial version of the second well model; and
Claim 2
The method of claim 1, wherein tuning parameters of the first well model comprises:
comparing the estimated production of the one or more existing production wells with the actual production of the one or more existing production wells;
determining whether there is a match between the estimated production and the actual production of the one or more existing wells, based on the comparison and an error tolerance; and
when it is determined that there is not a match between the estimated production and the actual production, adjusting one or more parameters of the first well model to reduce a difference between the estimated production and the actual production of the one or more existing production wells.
Claim 3
The method of claim 1, wherein the wellsite data acquired for the one or more existing production wells includes static and dynamic data.
Claim 4
The method of claim 1, wherein the wellsite data includes production data, well completion data, and geologic data associated with the one or more existing production wells.
Claim 5
The method of claim 1, wherein the parameters of the first well model include a porosity, a permeability, and a fluid saturation of an underlying reservoir formation associated with the one or more existing production wells.
Claim 6
The method of claim 1, wherein each of the first and second ML models is a neural network.
Claim 7
The method of claim 1, wherein each of the first and second well models is a near wellbore model.
Claim 1:
A computer-implemented method of parameter matching for completion design, the method comprising:
acquiring, by a computing device, wellsite data for one or more existing production wells in a hydrocarbon producing field;
transforming, by the computing device, the wellsite data into one or more model data sets for predictive modeling;
training a first machine learning (ML) model to predict well logs for the one or more existing production wells, based on the one or more model data sets;
generating a first well model to estimate production for the one or more existing production wells, based on the well logs predicted using the trained first ML model;
tuning parameters of the first well model, based on a comparison between the estimated production and an actual production of the one or more existing production wells;
training a second ML model to predict parameters of a second well model for a new production well in the hydrocarbon producing field, based on the tuned parameters of the first well model;
forecasting production of the new production well
over a period of time, based on the predicted parameters of the second well model,
the predicted parameters of the second well model including completion design parameters for the new production well;
estimating completion costs for the new production well, based on the completion design parameters and the forecasted production over the period of time; and adjusting one or more of the completion design parameters for the new production well, based on the estimated completion costs and the forecasted production.
Claim 2
The method of claim 1, wherein the tuning of the parameters of the first well model comprises:
comparing the estimated production of the one or more existing production wells with the actual production of the one or more existing production wells;
determining whether there is an acceptable match between the estimated production and the actual production of the one or more existing wells, based on the comparison and an error tolerance; and
when it is determined that there is no acceptable match between the estimated production and the actual production, adjusting one or more of the parameters of the first well model to reduce a difference between the estimated production and the actual production of the one or more existing production wells.
Claim 3
The method of claim 1, wherein the wellsite data acquired for the one or more existing production wells includes static and dynamic data.
Claim 4
The method of claim 1, wherein the wellsite data includes production data, well completion data, and geologic data associated with the one or more existing production wells.
Claim 5
The method of claim 1, wherein the parameters of the first well model include a porosity, a permeability, and a fluid saturation of an underlying reservoir formation associated with the one or more existing production wells.
Claim 6
The method of claim 1, wherein each of the first and second ML models is a neural network.
Claim 7
The method of claim 1, wherein each of the first and second well models is a near wellbore model.
Claims 8-20 of the present application are identical to corresponding claims in Application No. Application No. 17/560,982.
This is a provisional non-statutory double patenting rejection because the patentably indistinct claims have not in fact been patented.
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.
Claims 1-20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as failing to set forth 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. Independent claim 1 recites “training…a first machine learning (ML) model to predict well logs….” However, the claim subsequently recites “generating, by the first ML model, an initial version of the second well model.” Thus, it is unclear how an ML model, trained to generate predicted well logs, can also generate a well model. Accordingly, the claim is unclear.
Based on the disclosure of the Specification, it appears that, in the disclose, the invention includes the first ML model generating well logs that are utilized to generate a well model (either the first or second, which may be the same model, according to [0055]). See Spec. at [0061]. Thus, the initial version of the second well model is generated based on output from the first ML model, not directly from the machine learning model. Thus, a limitation that recites that the predicted logs generated by the first ML model are used to construct a well model, the claim would be clearer.
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 are rejected under 35 U.S.C. 101 because the claimed invention is directed to judicial exceptions without significantly more. The claims recite mathematical calculations and mental processes. This judicial exception is not integrated into a practical application because the additional elements that are recited in the claims are extra-solution activities that do not integrate the judicial exceptions into a practical application. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because courts have found that the step of data gathering is not significantly more than a judicial exception.
Claim 1
Step 1: The claim is directed to a process, falling under one of the four statutory categories of invention.
Step 2A, Prong 1: The claim 1 limitations include (bolded for abstract idea identification):
Claim 1
Mapping Under Step 2A Prong 1
A computer-implemented method of parameter matching for well planning and production forecasting, the method comprising:
acquiring, by a computing device from a data store, wellsite data for one or more existing production wells in a hydrocarbon producing field;
transforming, by the computing device, the wellsite data into one or more model data sets for predictive modeling by validating and clustering the wellsite data;
training, by using at least a first portion of the one or more model data sets as first training data, a first machine learning (ML) model to predict well logs for the one or more existing production wells; executing the first ML model, using at least a second portion of the one or more model data sets as input, to generate predicted well logs and
produce a first well model for estimating production of the one or more existing production wells;
tuning parameters of the first well model based on a comparison between the estimated production and an actual production of the one or more existing production wells, wherein tuning the parameters comprises generating tuned parameters by adjusting the estimated production based on the actual production;
training, using the tuned parameters of the first well model as second training data,
a second ML model to predict updated parameters for a second well model corresponding with a new production well in the hydrocarbon producing field;
executing the second ML model to generate output comprising an adjustment to the initial version of the second well model, wherein the adjustment to the initial version of the second well model comprises automatically applying a set of updated parameters to the initial version of the second well model; and
forecasting production of the new production well using the second well model updated with the parameter corrections generated by the second ML model.
Abstract Idea: Mathematical Calculations and Mental Processes
Clustering data includes either performing one or more mathematical operations to group data together or a mental process that includes selecting data points with particular characteristics and grouping them according to the characteristics. Further, validating data includes reviewing the data for accuracy and removing data points that are outliers. See MPEP § 2106.04(a)(2), Subsection I and III.
Abstract Idea: Mathematical Calculations Training a machine learning model includes performing one or more mathematical operations to provide training data to the machine learning model, which itself is a mathematical concept because the model is comprised of one or more mathematical functions. See MPEP § 2106.04(a)(2), Subsection I.
Abstract Idea: Mathematical Calculations
A model is a mathematical construct that is comprised of multiple mathematical functions to simulate a real world phenomena. See MPEP § 2106.04(a)(2), Subsection I.
Abstract Idea: Mental Process
Tuning numerical parameters includes the process of evaluation and judgment, such as evaluating the model to determine (i.e., judge) if the output of the model meets a standard and to change the values until the model performs as intended. See e.g., MPEP 2106.04(a)(2), Subsection III.
Abstract Idea: Mathematical Calculations Training a machine learning model includes performing one or more mathematical operations to provide training data to the machine learning model, which itself is a mathematical concept because the model is comprised of one or more mathematical functions. See MPEP § 2106.04(a)(2), Subsection I.
Abstract Idea: Mathematical Calculations
A model is a mathematical construct that is comprised of multiple mathematical functions to simulate a real world phenomena. See MPEP § 2106.04(a)(2), Subsection I.
Abstract Idea: Mental Process
Adjusting a model’s parameters includes observing the output from the model, evaluating the current values of the parameters of the model, and through judgment, changing the parameters such that the output of the model more closely matches the expected output. See e.g., MPEP 2106.04(a)(2), Subsection III.
Abstract Idea: Mental Process
Forecasting involves the mental processes of observation, evaluation, and judgment. A human, through observation, can observe and evaluate the output of the model and, through judgment, project future well production. See e.g., MPEP 2106.04(a)(2), Subsection III.
Step 2A, Prong 2: The claim 1 limitations recite (bolded for additional element identification):
Claim 1
Mapping Under Step 2A Prong 2
A computer-implemented method of parameter matching for well planning and production forecasting, the method comprising:
acquiring, by a computing device from a data store, wellsite data for one or more existing production wells in a hydrocarbon producing field;
transforming, by the computing device, the wellsite data into one or more model data sets for predictive modeling by validating and clustering the wellsite data;
training, by using at least a first portion of the one or more model data sets as first training data, a first machine learning (ML) model to predict well logs for the one or more existing production wells; executing the first ML model, using at least a second portion of the one or more model data sets as input, to generate predicted well logs and
produce a first well model for estimating production of the one or more existing production wells;
tuning parameters of the first well model based on a comparison between the estimated production and an actual production of the one or more existing production wells, wherein tuning the parameters comprises generating tuned parameters by adjusting the estimated production based on the actual production;
training, using the tuned parameters of the first well model as second training data,
a second ML model to predict updated parameters for a second well model corresponding with a new production well in the hydrocarbon producing field;
executing the second ML model to generate output comprising an adjustment to the initial version of the second well model, wherein the adjustment to the initial version of the second well model comprises automatically applying a set of updated parameters to the initial version of the second well model; and
forecasting production of the new production well using the second well model updated with the parameter corrections generated by the second ML model.
Using a generic computer to perform an abstract idea is mere instructions to apply an exception. See MPEP 2106.05(f).
Acquiring data is mere data gathering, which is an extra-solution activity. All uses of the judicial exceptions (e.g., training a ML model, generating a model) require such data gathering and output. See MPEP 2106.05(g)(3).
Step 2B: Regarding Step 2B, the inquiry is whether any of the additional elements (i.e., the elements that are not the judicial exception) amount to significantly more than the recited judicial exception. Claim 1 recites the additional element of “acquiring…data,” which is an extra-solution activity that courts have found to be insignificantly more than the judicial exception. See Mayo, 566 U.S. at 79, 101 USPQ2d at 1968; OIP Techs., Inc. v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1092-93 (Fed. Cir. 2015) (presenting offers and gathering statistics amounted to mere data gathering); In re Grams, 888 F.2d 835, 839-40; 12 USPQ2d 1824, 1827-28 (Fed. Cir. 1989); CyberSource v. Retail Decisions, Inc., 654 F.3d 1366, 1375, 99 USPQ2d 1690, 1694 (Fed. Cir. 2011); Ultramercial, 772 F.3d at 715, 112 USPQ2d at 1754.
Accordingly, claim 1 is rejected under 35 U.S.C. 101 for being directed to unpatentable subject matter.
Claim 2
Claim 2 recites:
wherein tuning parameters of the first well model comprises: comparing the estimated production of the one or more existing production wells with the actual production of the one or more existing production wells;
This step is directed to the mental process of observation and evaluation. A human, with the aid of a generic computer, can review the values acquired from the wells with the predicted values from the model to evaluate the similarity of the corresponding values. See MPEP 2106.04(a)(2), Subsection III.
determining whether there is a match between the estimated production and the actual production of the one or more existing wells, based on the comparison and an error tolerance; and
This step is directed to the mental process of evaluation and judgment. A human, with the aid of a generic computer, can evaluate the differences between the values acquired from the wells with the predicted values from the model to evaluate whether the model produced acceptable results. See MPEP 2106.04(a)(2), Subsection III.
when it is determined that there is not a match between the estimated production and the actual production, adjusting one or more parameters of the first well model to reduce a difference between the estimated production and the actual production of the one or more existing production wells.
This step is directed to the mental process of evaluation and judgment. A human, with the aid of a generic computer, can evaluate the differences between the values acquired from the wells with the predicted values from the model to evaluate whether the model produced acceptable results and, if not, can use expertise and experience to adjust parameters to improve the functioning of the model. See MPEP 2106.04(a)(2), Subsection III.
Accordingly, claim 2 is rejected under 35 U.S.C. 101 for being directed to unpatentable subject matter.
Claim 3
Claim 3 recites wherein the wellsite data acquired for the one or more existing production wells includes static and dynamic data. The claim merely specifies a type of data that is acquired, which is an insignificant extra-solution activity, and the claim does not add additional elements that may integrate the judicial exception into a practical application. Accordingly, claim 3 is rejected under 35 U.S.C. 101 for being directed to unpatentable subject matter.
Claim 4
Claim 4 recites wherein the wellsite data includes production data, well completion data, and geologic data associated with the one or more existing production wells. The claim merely specifies a type of data that is acquired, which is an insignificant extra-solution activity, and the claim does not add additional elements that may integrate the judicial exception into a practical application. Accordingly, claim 4 is rejected under 35 U.S.C. 101 for being directed to unpatentable subject matter.
Claim 5
Claim 5 recites wherein the parameters of the first well model include a porosity, a permeability, and a fluid saturation of an underlying reservoir formation associated with the one or more existing production wells. The claim merely specifies types of parameters that are included in the model, which is a mathematical calculation. Thus, the claim does not add additional elements that may integrate the judicial exception into a practical application. Accordingly, claim 5 is rejected under 35 U.S.C. 101 for being directed to unpatentable subject matter.
Claim 6
Claim 6 recites wherein each of the first and second ML models is a neural network. The first and second ML models are both mathematical calculations, as described with regards to claim 1. This claim merely specifies a type of ML model, each of which is a judicial exception. The claim does not include additional elements that would integrate the judicial exceptions into a practical application. Accordingly, claim 6 is rejected under 35 U.S.C. 101 for being directed to unpatentable subject matter.
Claim 7
Claim 7 recites wherein each of the first and second well models is a near wellbore model. The first and second models are both mathematical constructs comprised of multiple functions, as described with regards to claim 1. This claim merely specifies types ML models, each of which is a judicial exception. The claim does not include additional elements that would integrate the judicial exceptions into a practical application. Accordingly, claim 7 is rejected under 35 U.S.C. 101 for being directed to unpatentable subject matter.
Claim 8
Claim 8 recites: A system comprising: a processor; and a memory coupled to the processor having instructions stored therein, which when executed by the processor, cause the processor to perform a plurality of functions, including functions to: perform a method substantially the same as the method recited in claim 1.
Reciting generic computer components to perform a judicial exception is merely using a computer in its normal capacity, which does not integrate the abstract idea into a practical application. Further, courts have found that reciting a computer is not significantly more than the judicial exception. See MPEP 2106.05(f); Affinity Labs v. DirecTV, 838 F.3d 1253, 1262, 120 USPQ2d 1201, 1207 (Fed. Cir. 2016) (cellular telephone); TLI Communications LLC v. AV Auto, LLC, 823 F.3d 607, 613, 118 USPQ2d 1744, 1748 (Fed. Cir. 2016) (computer server and telephone unit). Similarly, “claiming the improved speed or efficiency inherent with applying the abstract idea on a computer” does not integrate a judicial exception into a practical application or provide an inventive concept. Intellectual Ventures I LLC v. Capital One Bank (USA), 792 F.3d 1363, 1367, 115 USPQ2d 1636, 1639 (Fed. Cir. 2015).
According, claim 8 is rejected under 35 U.S.C. 101 for being directed to unpatentable subject matter.
Claim 9-14
Claims 9-14 recite substantially the same limitations as claims 2-7. Accordingly, for at least the same reasons as asserted regarding claims 2-7, claims 9-14 are rejected under 35 U.S.C. 101 for being directed to unpatentable subject matter.
Claim 15
Claim 15 recites a computer-readable storage medium having instructions stored therein, which when executed by a computer cause the computer to perform a plurality of functions, including functions to: perform a method substantially the same as the method recited in claim 1. The claim recites a “storage medium,” which can include a signal per se. Thus, the claim in not patentable under Step 1 of the test because it is not directed to a statutory category of patentable subject matter. However, even if amended to recite a statutory category (e.g., “non-transitory medium”), claim 15 is rejected under 35 U.S.C. 101 is still directed to unpatentable subject matter and therefore unpatentable subject matter.
Claim 16-20
Claims 16-20 recite substantially the same limitations as claims 2-5 and 7. Accordingly, for at least the same reasons as asserted regarding claims 2-5 and 7, claims 16-20 are rejected under 35 U.S.C. 101 for being directed to unpatentable subject matter.
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.
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.
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.
Claims 1-6, 8-13, and 15-19 are rejected under 35 U.S.C. 103 as being obvious over Tawil, et al., (U.S. Patent Pub. No. 2021/0317726), hereinafter “Tawil,” in view Anifowose, et al., (U.S. Patent Pub. No. 2021/0349001), hereinafter “Anifowose,” Fornel, et al., (U.S. Patent No. 7,752,022), hereinafter “Fornel” and Jagnnathan, et al., (U.S. Patent Pub. No. 2021/0164944), hereinafter “Jagnnathan.”
Claim 1
Tawil discloses:
A computer-implemented method of parameter matching for well planning and production forecasting, the method comprising:
Techniques are described for an integrated methodology that can be used by a computing system to automate processes for generating, and updating (e.g., in real-time), subsurface reservoir models….The reservoir models can be used to perform processes relating to hydrocarbon exploration, well planning, geo-steering, reservoir modeling, field development plan generation, and resource allocation for well planning operations. Tawil at [0005].
acquiring, by a computing device from a data store, wellsite data for one or more existing production wells in a hydrocarbon producing field;
The data processing capabilities of the earth model allow for computing more accurate estimations of hydrocarbon reserves in underground formations. Tawil at [0017].
WDS module 320 is a computing platform that enables earth model 300 to gain access to valuable well data and well data sources. The WDS module 320 can access the well data in real-time from various drillings rigs via satellite communication. Tawil at [0108].
“WDS” is “well data sources,” see Fig. 3, element 320.
transforming, by the computing device, the wellsite data into one or more model data sets for predictive modeling by validating and clustering the wellsite data;
The exploration data module 318 executes one or more of its workflow processes using data mining and business intelligence methods that leverage AI and ML technologies. For example, a data analysis and optimization program of the exploration data module 318 can invoke a predictive model of the ML engine 250 to perform statistical and stochastic analysis or modeling of the received hydrocarbon field and reservoir data. In some implementations, the statistical and stochastic approaches are employed to quantify, or precisely quantify, abnormal data conditions and data heterogeneity that can exists among the data values and variables of the received hydrocarbon data... The exploration data module 318 is configured to ensure consistent clean data is available to be utilized by the modules of the earth model 300. Tawil at [0107].
In some implementations, features or feature values of a training dataset for modeling geological properties can be derived using various techniques of a feature learning process, such as correlation analysis, variable clustering, or variable importance lists from decision trees, as well as techniques related to random feature selection. Tawil at [0144].
“Exploration data module” 318 performs data analysis and optimization, which is analogous to a “validating” the “wellsite data.”
In some implementations, the GDS module 322 is designed to bridge the gap between various geophysical data formats used by different vendors. In particular, the GDS module 322 is configured to receive multiple sets of geophysical data. At least two sets of the geophysical data can have distinct vendor-specific geophysical data formats. The GDS module 322 is operable to apply one or more data standards across the sets of geophysical data. For example, the GDS module 322 can use the one or more data standards to convert the respective vendor-specific formats to a standardized geophysical data format. The GDS module 322 uses the standardized geophysical data format to streamline and simplify the geophysical data and to make the data and related information more accessible by modules of the earth model 300. Tawil at [0113].
The “GDS module” transforms data by standardizing formats from various sources.
training, by using at least a first portion of the one or more model data sets as first training data, a first machine learning (ML) model to predict [data]
The data processed by the AI system 200 to generate the predictive models may be annotated training data…. Tawil at [0048].
A training dataset can be developed based on a feature engineering process of system 100 that uses various data processing methods to generate a set of features. The features or feature sets can be generated using numerical or other data values of a raw dataset. The raw dataset may be based on information and data obtained from sensors, geophones, or various other sources of seismic data…. Tawil at [0050].
“Data obtained from sensors, geophones, or various other sources of seismic data” is analogous to acquired wellsite data, which is utilized to generate the “model data sets” at the “transforming” step.
executing the first ML model, using at least a second portion of the one or more model data sets as input, to generate predicted well logs
During the training phase, the ML engine 250 generates one or more predictive models 264, 266, 268 in response to training the neural networks by processing the seismic data through layers of the neural networks 254, 256, 258… In some implementations, the ML engine 250 generates multiple distinct predictive models that are each configured to perform certain predictive, pattern mining, or inference functions relating to different aspects of hydrocarbon exploration in a subterranean region. Tawil at [0056].
For example, the ML engine 250 can generate a predictive model 264 (e.g., model_1) that is configured to automatically identify and select geological formation tops/surfaces in response to processing data values obtained from well logs as well as control processes for geological well drilling. Tawil at [0057].
In some examples, the processing methods can include the generation and forward modeling of pseudo well logs and structural updates. Tawil at [0092].
The “ML engine” includes multiple “generated models” (i.e., 264, 266, 268) that “perform certain predictive… aspects of hydrocarbon exploration,” analogous to “estimated production” based on “processing data values obtained from well logs,” including “pseudo” (i.e. “predicted”) well logs.
and produce a first well model for estimating production of the one or more existing production wells;
The system 100 uses ML engine 250 to generate an integrated multi-dimensional geological model 262. For example, the ML engine 250 generates the integrated multi-dimensional geological model 262 based on predictive models 264, 266, 268. As described in more detail later, the integrated multi-dimensional geological model is generally configured to model characteristics of reservoirs in the subterranean region and to estimate hydrocarbon reserves using at least one or more geological properties of layers and bodies of sedimentary in a subterranean region. Tawil at [0058].
For example, the system 100 can iteratively feedback, in real-time, data values that describe new or different properties of sediments at a layer of a region below a formation top that was selected for a well drilling operation. The data values can be processed at the ML engine 250 to update or enhance the analytical rules of the predictive model to improve upon the model's ability to accurately identify formations that can yield desired estimations of hydrocarbons. Tawil at [0061].
“Identify formations that can yield desired estimations of hydrocarbons” is analogous to estimating production.”
tuning parameters of the first well model based on a comparison between the estimated production and an actual production of the one or more existing production wells,
The system 100 is configured to automatically update the respective analytical rule of each predictive model in response to processing the new data values of seismic data (512). For example, each of the respective subsets of new data values that are derived from the second iteration of seismic data are processed at its corresponding predictive model to update, enhance, or otherwise optimize the particular functionality and analytical rules encoded at the predictive model. Tawil at [0150].
The data values can be processed at the ML engine 250 to update or enhance the analytical rules of the predictive model to improve upon the model's ability to accurately identify formations that can yield desired estimations of hydrocarbons. Tawil at [0061].
The “analytical rule of each predictive model” is analogous to a “parameter” of the respective model.
forecasting production of the new production well
The reservoir optimization module 316 can quantify the uncertainty of hydrocarbon volumes, which results in more reliable reserve estimations and field delineation and development plans. Tawil at [0103].
A “reserve estimation” and “development plan” are analogous to a new production well forecast.
Tawil does not appear to disclose:
wherein tuning the parameters comprises generating tuned parameters by adjusting the estimated production based on the actual production
training, using the tuned parameters of the first well model as second training data, a second ML model to predict updated parameters for a second well model corresponding with a new production well in the hydrocarbon producing field;
2
executing the second ML model to generate output comprising an adjustment to the initial version of the second well model, wherein the adjustment to the initial version of the second well model comprises automatically applying a set of updated parameters to the initial version of the second well model;
Anifowose, which is analogous art to the claimed invention, discloses:
training, by using at least a first portion of the one or more model data sets as first training data, a first machine learning (ML) model to predict well logs for the one or more existing production wells;
At 502, historical mud gas-permeability data is received from previously-drilled wells. The historical mud gas-permeability data identifies relationships between gas measurements obtained during drilling and permeability determined after drilling. As an example, the historical mud gas-permeability data associated with multiple rig platforms 102 can be received, including the results from each rig's gas mass spectrometer 120 and gas chromatograph 122. The corresponding permeability determined after drilling for each rig can also be received. From 502, method 500 proceeds to 504. Anifowose at [0037].
At 504, a formation hydrocarbon mobility model is trained using machine learning and the historical mud gas-permeability data. The machine learning can be performed using techniques of one or more of ANN, SVM, RT, RF, ELM, and T1FL/T2FL. From 504, method 500 proceeds to 506. Anifowose at [0038].
At 508, a real-time permeability log is generated for the new well using the formation hydrocarbon mobility model and real-time gas measurements. As an example, the real-time permeability log 322 can be generated for the new well. Anifowose at [0041].
The “formation hydrocarbon mobility model” is analogous to the “first ML model,” which is trained on “mud gas-permeability data” (analogous to the “model data sets”) and generates “a real-time permeability log,” analogous to a predicted “well log.”
Anifowose is analogous art to the claimed invention because both the reference and the claimed invention are directed to estimating production data based on wellsite data. It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the application, to combine the multi-model framework of Tawil with the model of Anifowose to result in a well-planning process that takes into account wellsite data and outputs permeability logs. One of ordinary skill in the art could have simply substituted one of the machine learning models of Tawil with the machine learning model of Anifowose to result in a process that would generate permeability logs as one of its outputs to utilize in well-planning, thus resulting in a more versatile process that utilizes additional inputs and provides additional outputs.
Fornel, which is analogous art to the claimed invention, discloses:
wherein tuning the parameters comprises generating tuned parameters by adjusting the estimated production based on the actual production
…comparing, with an objective function, the simulated dynamic production data and the simulated seismic data… Fornel at col. 4, lines 52-54.
…measuring the error between the observed data (production 15 and 4D seismic data 8) and the simulation results obtained for a fixed value of parameters θ. Fornel at col. 9, lines 59-61.
optimizing the geologic model by…updating at least the depth/time conversion model. Fornel at col. 4, lines 54-55.
Fornel is analogous art to the claimed invention because both are directed to generating a model to estimate well production based on wellsite data. It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the application, to combine Fornel with Tawil to result in a process of well-planning that includes comparing simulated production data with actual production data to adjust one or more of the parameters of a well model that was generated based on the machine learning model disclosed in Anifowose. Motivation to combine includes leveraging already existing production data and simulated production data to improve the performance of the parameter adjustment process described in Tawil (and/or the machine learning model process described in Anifowose).
Jagnnathan, which is analogous art to the claimed invention, discloses:
training, using the tuned parameters of the first well model as second training data, a second ML model to predict updated parameters for a second well model corresponding with a new production well in the hydrocarbon producing field;
At block 306, the hybrid physical/statistical model is used to set up a deep learning model. The deep learning model is preferably implemented as a deep neural network (DNN) (i.e., a neural network having two or more layers between input and output). In some embodiments, data derived from the hybrid physics/statistical modeling at block 305 may be used as training data for the deep learning model. The deep learning model may then be used in an inversion process (e.g., workflow 200 of FIG. 2) as a proxy for the forward model (e.g., block 206) of the pipeline to provide predicted or estimated values for comparison (e.g., block 203) to observed values. Jagnnathan at [0039].
The “data derived from the hybrid physics/statistical modeling” is analogous to the “tuned parameters of the first well model.”
The “predicted or estimated values for comparison to observed values” is analogous to “predict updated parameters” for a second well model.”
executing the second ML model to generate output comprising an adjustment to the initial version of the second well model, wherein the adjustment to the initial version of the second well model comprises automatically applying a set of updated parameters3 to the initial version of the second well model;
If the error or difference is below a predetermined threshold, meaning that the parameters of the forward model at block 206 have produced measurements that are a statistical match or best fit relative to the observed measurements, then workflow 200 proceeds to block 208….However, if the error or difference exceeds the predetermined threshold, then workflow 200 proceeds to block 205 where the model parameters are corrected, adjusted, or otherwise refined in a known manner. Jagnnathan at [0027]-[0028].
The “number of iterations” is analogous to “executing the second ML model.”
At block 207, the corrected parameters become the new parameters for the forward model at block 206 and the workflow 200 is repeated. This process continues for a number of iterations until the parameters for the forward model have been determined such that the error falls below a predetermined threshold. Jagnnathan at [0028].
Jagnnathan is analogous art because both are directed to utilizing machine learning models to adjust parameters of models in the field of oil and gas recovery. It would have been obvious to a person having ordinary skill in the art, before the effective filing date of the claimed invention, to combine the machine learning model and well models of Tawil and Anifowose with the machine learning model of Jagnnathan to result in a system that can generate well models for additional wells in a field based on data originally received from a producing well. Motivation to combine includes improving the operation of resulting models to predict well production as well as reducing computing time by tuning parameters of the well model based on already known and collected data. For example, by using the combined system, a well model for a new well can be generated with greater accuracy and speed by leveraging known data from an existing well.
Claim 2
Tawil, Anifowose, and Jagnnathan do not appear to disclose:
wherein tuning parameters of the first well model comprises: comparing the estimated production of the one or more existing production wells with the actual production of the one or more existing production wells;
determining whether there is a match between the estimated production and the actual production of the one or more existing wells, based on the comparison and an error tolerance; and
when it is determined that there is not a match between the estimated production and the actual production, adjusting one or more parameters of the first well model to reduce a difference between the estimated production and the actual production of the one or more existing production wells.
Fornel, which is analogous art to the claimed invention, discloses:
wherein tuning parameters of the first well model comprises: comparing the estimated production of the one or more existing production wells with the actual production of the one or more existing production wells;
…comparing, with an objective function, the simulated dynamic production data and the simulated seismic data… Fornel at col. 4, lines 52-54.
determining whether there is a match between the estimated production and the actual production of the one or more existing wells, based on the comparison and an error tolerance; and
…measuring the error between the observed data (production 15 and 4D seismic data 8) and the simulation results obtained for a fixed value of parameters θ. Fornel at col. 9, lines 59-61.
when it is determined that there is not a match between the estimated production and the actual production, adjusting one or more parameters of the first well model to reduce a difference between the estimated production and the actual production of the one or more existing production wells.
optimizing the geologic model by…updating at least the depth/time conversion model. Fornel at col. 4, lines 54-55.
Claim 3
Tawil discloses:
wherein the wellsite data acquired for the one or more existing production wells includes
This specification also describes systems and techniques for performing probabilistic modeling of reservoir properties in a subterranean region using well logs and relevant seismic data. Tawil at [0038].
static [data] and
For example, data values of the seismic data that indicate or describe properties of underground formations in the subterranean region are provided as inputs to data models of the ML engine 250. Tawil at [0141].
Seismic data can be “static” data that is a property of formations at a well.
dynamic data.
The input data may comprise real-time well borehole data, including well header data, well drilling status information, well logs, datasets for various well and core samples, and information relating to well tests. Tawil at [0110].
“Input data” (analogous to “wellsite data”) can include “real-time” (i.e., “dynamic”) data.
Claim 4
Tawil discloses:
wherein the wellsite data includes production data, well completion data, and
The input data may comprise real-time well borehole data, including well header data, well drilling status information, well logs, datasets for various well and core samples, and information relating to well tests.
“Well header data” is analogous to “well completion data” because both are well-specific information.
“Well and core samples” and “well borehole data” are analogous to “production data” (e.g., “wellsite production data may include, for example, production system measurements from various downhole devices or surface sensors/meters, as described above.” Spec. at [0032], “Examples of such downhole tools include, but are not limited to, a LWD tool, a MWD tool, and any of various sensors for measuring various downhole conditions and formation properties.” Spec. at [0029]).
geologic data associated with the one or more existing production wells.
The method includes obtaining, by the integrated multi-dimensional geological model, seismic data describing an underground formation in the subterranean region of a geological area… Tawil at [0009].
Claim 5
Tawil, Anifowose, and Jagnnathan do not appear to disclose:
wherein the parameters of the first well model include a porosity, a permeability, and a fluid saturation of an underlying reservoir formation associated with the one or more existing production wells.
Fornel discloses:
wherein the parameters of the first well model include a porosity, a permeability, and
Parameterization 11 of the geostatistical models is a fundamental point for guaranteeing success of the stage of data integration in the geologic models. In fact, updating the geologic models by means of the dynamic data is based on the solution of an inverse problem. Selection of the parameters to be calibrated thus appears to be essential to minimization of the objective function, which measures the difference between the data observed in the field and the simulation results. Fornel at col. 9, lines 10-19.
a fluid saturation of an underlying reservoir formation associated with the one or more existing production wells.
The dynamic data can be reservoir production, pressure and saturation data. Fornel at col. 4, lines 64-65.
Claim 6
Tawil does not appear to disclose:
Each of the predictive models 264, 266, 268 is operable to employ adaptive analytics that are based on the iterative processing of new seismic data at a prior trained neural network data model that forms the computational basis for the predictive model. Tawil at [0060].
See also FIG. 2.
Tawil teaches multiple machine learning models that are neural networks, although not necessarily machine learning models that perform the same functions as the first and second ML models.
Anifowose discloses:
wherein
Processes involved in using the ML model 208 that can be used in the workflow 200 are further illustrated in FIG. 3. ML models can use techniques such as Artificial Neural Network (ANN)… Anifowose at [0024].
Jagnnathan discloses:
wherein
The deep learning model is preferably implemented as a deep neural network (DNN) (i.e., a neural network having two or more layers between input and output). Jagnnathan at [0039].
Claim 8
Tawil discloses:
A system comprising: a processor; and a memory coupled to the processor having instructions stored therein, which when executed by the processor, cause the processor to perform a plurality of functions, including functions to:
FIG. 17 is a block diagram of an example computer system 1700 used to provide computational functionalities associated with described algorithms, methods, functions, processes, flows, and procedures described in the present disclosure, according to some implementations of the present disclosure. Tawil at [0205].
The computer 1702 includes a processor 1705. Tawil at [0213].
The computer 1702 also includes a memory 1707 that can hold data for the computer 1702 or a combination of components connected to the network 1730 (whether illustrated or not). Tawil at [0215].
perform a method substantially the same as the method recited in claim 1.
Accordingly, for at least the same reasons and based on the same prior art as claim 1, claim 8 is rejected under 35 U.S.C. 103 as being obvious over Tawil in view of Anifowose and Jagnnathan.
Claims 9-13, 16, and 19
Claims 9-13, 16, and 19 recite limitations that are substantially the same as the method disclosed in claim 2-6. Accordingly, for at least the same reasons and based on the same prior art as claims 2-6, claims 9-13, 16, and 19 are rejected under 35 U.S.C. 103 as being obvious over Tawil in view of Anifowose, Jagnnathan, and Fornel.
Claim 15
Tawil discloses:
A computer-readable storage medium having instructions stored therein, which when executed by a computer cause the computer to perform a plurality of functions, including functions to:
The computer 1702 also includes a memory 1707 that can hold data for the computer 1702 or a combination of components connected to the network 1730 (whether illustrated or not). Memory 1707 can store any data consistent with the present disclosure. In some implementations, memory 1707 can be a combination of two or more different types of memory (for example, a combination of semiconductor and magnetic storage) according to particular needs, desires, or particular implementations of the computer 1702 and the described functionality. Tawil at [0215].
perform a method substantially the same as the method recited in claim 1.
Accordingly, for at least the same reasons and based on the same prior art as claim 1, claim 15 is rejected under 35 U.S.C. 103 as being obvious over Tawil in view of Anifowose and Jagnnathan.
Claims 17-18
Claims 17-18 recite limitations that are substantially the same as the method disclosed in claim 3-4. Accordingly, for at least the same reasons and based on the same prior art as claims 3-4, claims 17-18 are rejected under 35 U.S.C. 103 as being obvious over Tawil in view of Anifowose and Jagnnathan.
Claims 7, 14, and 20 are rejected under 35 U.S.C. 103 as being obvious over Tawil, in view Anifowose, Fornel, Jagnnathan, and further in view of Chandra, et al. (“Improving Reservoir Characterization and Simulation With Near-Wellbore Modeling”), hereinafter Chandra.
Claim 7
Tawil, Anifowose, Fornel, and Jagnnathan do not appear to disclose:
wherein each of the first and second well models is a near wellbore model.
Chandra, which is analogous art, discloses:
wherein each of the first and second well models is a near wellbore model.
In this paper, we illustrate a novel workflow involving high-resolution near-wellbore modeling (NWM), which allows us to accurately include seismic, wireline data, image logs, and well core logs from highly heterogeneous reservoirs in field-scale reservoir simulations. We demonstrate that an NWM-enhanced geoengineering workflow has the potential to improve reservoir characterization by applying it to a realistic clastic reservoir with high variance at small scale…. Our results show that the use of NWM tools for reservoir modeling yields more precise flow calculations… Chandra at Summary.
“Flow calculations” is analogous to “production,” which is what is estimated by both the “first well model” and the “second well model.”
Chandra is analogous art to the claimed invention because both are directed to performing well simulations based on wellsite data. It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the application, to combine the near-wellbore model of Chandra with the models of Tawil, Anifowose, and Jagnnathan to result in a well-planning process that is directed to near-wellbore data. Motivation to combine includes improved characterization of a reservoir based on the limited data from wells within in the field that includes the reservoir. Thus, a model of other new wells and/or potential wells in the same field is more accurate.
Claim 14
Claim 14 recites limitations that are substantially the same as the limitations recited in claim 7. Accordingly, for at least the same reasons and based on the same prior art as claim 7, claim 14 is rejected under 35 U.S.C. 103 as being obvious over Tawil in view of Anifowose, Jagnnathan, and Chandra.
Claim 20
Claim 20 recites limitations that are substantially the same as the limitations recited in claims 6 and 7. Accordingly, for at least the same reasons and based on the same prior art as claims 6 and 7, claim 20 is rejected under 35 U.S.C. 103 as being obvious over Tawil in view of Anifowose, Jagnnathan, and Chandra.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
From the previous Office Action:
U.S. Pat. Pub No. 2023/0063424 (Zeghlache, et al.): “AUTOMATED WELL LOG DATA QUICKLOOK ANALYSIS AND INTERPRETATION”
U.S. Pat. Pub No. 2021/0355805 (Rangarajan, et al.): “AI/ML BASED DRILLING AND PRODUCTION PLATFORM”
U.S. Pat. Pub No. 2021/0388714 (Katterbauer, et al.): “FORECASTING HYDROCARBON RESERVOIR PROPERTIES WITH ARTIFICIAL INTELLIGENCE
Additional pertinent prior art not relied upon:
U.S. Pat. Pub No. 2021/0270998 (Madasu, et al.): “Automated production history matching using bayesian optimization
U.S. Pat. No. 12,241,339 (Gunnerud, et al.): “Method of modelling a production well”
Y. Chen and D. Zhang, “Physics-Constrained Deep Learning of Geomechanical Logs ”, IEEE Transactions on Geoscience and Remote Sensing, Vol. 58, No.8.
Yates, et al., U.S. Pat. Pub. No. 2019/0102693: “Optimizing parameters for machine learning models.”
Communication
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JOSEPH MORRIS whose telephone number is (703)756-5735. The examiner can normally be reached M-F 8:30-5:00.
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, Ryan Pitaro can be reached at (571) 272-4071. 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.
JOSEPH MORRIS
Examiner
Art Unit 2188
/JOSEPH P MORRIS/Examiner, Art Unit 2188 /RYAN F PITARO/Supervisory Patent Examiner, Art Unit 2188
1 This is not provided as an indication that amendments including this language will necessarily overcome any pending rejections. However, by reciting specific training data (as already recited in the claims), what is generically provided and generated by the models, and for a given instance, what data is specifically provided and what output is specifically generated will limit the prior art references that teach such models.
2 The limitation is not being examiner because of the 35 U.S.C. 112(b) rejection for indefiniteness. Examiner suggests amending to recite “executing the first ML model to generate one or more predicted well logs; and generating an initial version of the second well model based on the one or more predicted well logs.
3 “a set of updated parameters” does not technically have an antecedent basis issue; however, the “updated parameters” are not directly related to the second ML output. Thus, Examiner suggests amending to recite “executing the second ML model to generate a set of updated parameters;
adjusting the initial version of the second well model by automatically applying a set of updated parameters to the initial version of the second well model;”
Prosecution Insights