DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claims 1-20 are presented for examination based on the amended claims in the application filed on October 15, 2025.
Claims 1-6, 8-11, 14-18, and 20 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1, 3-8 of U.S. Patent No. 12,111,441 B2 and in view of US 2020/0132875 A1 Zhang et al. [herein “Zhang”].
Claim 7 is rejected on the ground of nonstatutory double patenting as being unpatentable over claim 6 of U.S. Patent No. 12,111,441 B2 and Zhang et al. as applied to claim 2 above, and further in view of US 20160328419 A1 Safonov et al. [herein “Safonov”].
Claims 12-13 and 19 are rejected on the ground of nonstatutory double patenting as being unpatentable over claim 1 of U.S. Patent No. 12,111,441 B2 and Zhang et al. as applied to claim 11 above, and further in view of Mahmoodpour, Soran, Ehsan Kamari, Mohammad Reza Esfahani, and Amir Karimi Mehr. “Prediction of cementation factor for low-permeability Iranian carbonate reservoirs using particle swarm optimization-artificial neural network model and genetic programming algorithm.” Journal of Petroleum Science and Engineering 197 (2021): 108102 [herein “Mahmoodpour”].
Claims 1-20 are rejected under 35 U.S.C. § 103 as being unpatentable over Mahmoodpour in view of US 2021/0326721 A1 Zhang et al. [herein “Zhang2”],
This action is made Final.
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 Amendment
The amendment filed October 15, 2025 has been entered. Claims 1-20 remain pending in the application. Applicant’s amendments to the Specification and Claims have overcome each and every objection and 112(b) rejection(s) previously set forth in the Non-Final Office Action mailed August 6, 2025.
Claim Objections
Claims 1-20 are objected to because of the following informality: Claim 1, which cites “the course of the downhole operation” in Ln. 7, is improper because there has been no previous recitation of “the course of the downhole operation”. For the purpose of examination, “the course of the downhole operation” will be interpreted as “a course of the downhole operation”. The examiner recommends that applicant amend the claim language from “the course of the downhole operation” to “a course of the downhole operation”, simply “the downhole operation”, or similar, as supported by the specification, when referring to the instance of the downhole operation. Claims 14 and 20, having similar limitations of claim 1, are also objected. Claims 2-13 and 15-19 are also objected to for incorporating the deficiency of its dependent claims 1 and 14, respectively.
Appropriate correction is required.
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 1-6, 8-11, 14-18, and 20 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1, 3-8 of U.S. Patent No. 12,111,441 B2 and in view of US 2020/0132875 A1 Zhang et al. [herein “Zhang”].
As per claim 1, Patent No. 12,111,441 teaches “A computer-implemented method comprising: performing, via a downhole tool, a downhole operation along a wellbore drilled within a reservoir formation, wherein the downhole operation comprises at least collecting training data for modeling the reservoir formation surrounding the wellbore; receiving, by a computing device via a network from the downhole tool, the training data during the course of the downhole operation” (Claim 1, A computer-implemented method comprising: receiving, by a computing device from one or more formation evaluation sensors, measurements of formation parameters during a first stage of a downhole operation within a reservoir formation and selecting, by the computing device, one or more of the formation parameters as input parameters for a symbolic regression model, based on the correlation determined for each formation parameter),
Patent No. 12,111,441 teaches “training, by the computing device using symbolic regression, a machine learning model to determine a formation model representing the reservoir formation, based on the training data received from the downhole tool” (Claim 1, training, by the computing device, a symbolic regression model to generate a plurality of candidate formation models representing the target parameter of the reservoir formation, based on the selected input parameters),
Patent No. 12,111,441 teaches “estimating, by the computing device, at least one property of the reservoir formation, based on the formation model” (Claim 1, estimating, by the computing device, values of the target parameter for at least one layer of the reservoir formation, based on the target petrophysical model),
Patent No. 12,111,441 teaches “[adjusting, via the downhole tool,] the downhole operation along the wellbore within the reservoir formation, based on the at least one estimated property” (Claim 1, wherein a second stage of the downhole operation is performed within the at least one layer of the reservoir formation, based on the estimated values of the target parameter).
Patent No. 12,111,441 fails to distinctly point out “adjusting, via the downhole tool, the downhole operation along the wellbore within the reservoir formation, based on the at least one estimated property”.
However, in the same field of endeavor namely modeling parameters of oil reservoirs, Zhang teaches “adjusting, via the downhole tool, the downhole operation along the wellbore within the reservoir formation, based on the at least one estimated property”. (Para. 0028, “the formation evaluation module 210 may utilize the data in a transformative or different way to evaluate and/or estimate one or more formation properties” [estimated property]. That is, data that may be generally processed using known or approximate formulations may be evaluated differently, or in combination with those formulations, in order to obtain improved results indicative of formation properties. These results may then be used to control or inform one or more physical operations at a well site. For example, an evaluation that determines low permittivity within a rock formation may lead to the use of enhanced recovery techniques or a classification of a wellbore that is unlikely to be productive, and as a result, should be shut in and decommissioned” [e.g., altering, via the downhole tool, the downhole operation along the wellbore within the reservoir formation, based on the at least one estimated property]. Further see Para. 0027-0030. The examiner has interpreted that estimated formation properties to control physical operations at a well site as performing a downhole operation along the wellbore within the reservoir formation, based on the at least one estimated property.)
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to add “adjusting, via the downhole tool, the downhole operation along the wellbore within the reservoir formation, based on the at least one estimated property” as conceptually seen from the teaching of Zhang, into that of Patent No. 12,111,441 because this modification of performing actions as a result of the obtained model for the advantageous purpose of keeping drilling operations productive when an undesirable simulation result is obtained through a remote simulation (Zhang, Para. 0040 and 0069). Further motivation to combine be that Patent No. 12,111,441 and Zhang are analogous art to the current claim are directed to modeling parameters of oil reservoirs.
As per claim 2, Patent No. 12,111,441 teaches “selecting one of the plurality of formation models, based on a predetermined fitness objective.” (Claim 6, selecting one of the candidate formation models from the set as the target petrophysical model for the corresponding facies, based on a predetermined fitness objective.)
Patent No. 12,111,441 also teaches “wherein the training comprises: training the machine learning model to generate a plurality of formation models [based on the logging data and the core sample data]”. (Claim 1, training, by the computing device, a symbolic regression model to generate a plurality of candidate formation models representing the target parameter of the reservoir formation, based on the selected input parameters).
Furthermore, regarding claim 2, Patent No. 12,111,441 fails to distinctly point out “wherein the training data includes logging data received from a logging tool positioned within the wellbore and core sample data received from a core analysis tool” and “wherein the training comprises: training the machine learning model to generate a plurality of formation models based on the logging data and the core sample data”.
However, in the same field of endeavor namely modeling parameters of oil reservoirs, Zhang teaches “wherein the training data includes logging data received from a logging tool positioned within the wellbore and core sample data received from a core analysis tool” and “wherein the training comprises: training the machine learning model to generate a plurality of formation models based on the logging data and the core sample data”. (Para. 0027, “computing device 202 may submit wellbore data captured by one or more tools of the BHA 108. For example, the computing device 202 may transmit information from the dielectric measurement unit 112 indicative of permittivity” [logging data received from a logging tool positioned within the wellbore]. Para. 0033, “the training database 222 may include previously obtained information that correlated core samples with dielectric information. That is, core samples that were extracted from a formation and evaluated, for example in a lab, and then associated along with dielectric information obtained proximate the location where the core samples were removed may be used as information to enable the machine learning system to correlate dielectric information with certain textural properties of the formation.” [trained data includes core sample data received from a core analysis tool]. Para. 0066, “downhole dielectric measurements are received (block 902), for example via an interface associated with a data processing service. In embodiments, the service may be provided by a wellbore services provider or, in various embodiments, as a standalone package or Software as a Service (SaaS) offering. The data may be processed using a trained machine learning system (block 904). For example, the system may be trained to perform a variety of classifications and determinations of the data (block 906)” [wherein the training data includes logging data]. Para. 0013, “automatically generate at least one additional machine learning model of a plurality of machine learning models” [generate a plurality of formation models]. Further see Para. 0026-0028, 0032-0035, and 0066.)
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to add “wherein the training data includes logging data received from a logging tool positioned within the wellbore and core sample data received from a core analysis tool” and “wherein the training comprises: training the machine learning model to generate a plurality of formation models based on the logging data and the core sample data” as conceptually seen from the teaching of Zhang, into that of Patent No. 12,111,441 because this modification of acquiring measurement data while in the wellbore with a logging tool and rock sample data for the advantageous purpose of correlating core sample properties to wellbore measurements for the positioning and classification of the wellbore (Zhang, Para. 0022). Further motivation to combine be that Patent No. 12,111,441 and Zhang are analogous art to the current claim are directed to modeling parameters of oil reservoirs.
As per claim 3, Patent No. 12,111,441 teaches “wherein selecting one of the plurality of formation models comprises: ranking the plurality of formation models according to the predetermined fitness objective” (Claim 7, ranking each candidate formation model of the plurality of candidate formation models according to the predetermined fitness objective) and “selecting one of the plurality of formation models, based on the ranking” (Claim 7, selecting the target petrophysical model from the plurality of candidate formation models, based on the ranking).
As per claim 4, Patent No. 12,111,441 teaches “wherein the predetermined fitness objective is defined by a fitness function based on a set of primitives representing measurement characteristics of the downhole tool and the core analysis tool” (Claim 3, wherein the set of primitives are selected for the symbolic regression model based on measurement characteristics of the one or more measurement tools, and Claim 8, calculating, for each of the candidate formation models in the set, a score for each of a plurality of factors associated with the predetermined fitness objective; and calculating, for each of the candidate formation models in the set, an overall score for the plurality of factors based on the score calculated for each factor, wherein at least one candidate formation model having a highest overall score is selected from the set as the target petrophysical model).
As per claim 5, Patent No. 12,111,441 teaches “wherein the training comprises: generating a parent population of formation models” (Claim 6, generating a parent population of formation models),
Patent No. 12,111,441 teaches “performing crossover and mutation operations over a plurality of iterations until a predetermined termination condition is reached, wherein a child population of formation models is generated at each iteration based on the parent population generated at a preceding iteration, and wherein one of the plurality of formation models is selected from the child population of formation models generated from the crossover and mutation operations” (Claim 6, performing at least one of a crossover operation or a mutation operation on the parent population to generate the plurality of candidate formation models over a plurality of iterations until a predetermined termination condition is reached; and selecting one of the candidate formation models from the set as the target petrophysical model for the corresponding facies, based on a predetermined fitness objective).
Regarding claim 6, Patent No. 12,111,441 fails to distinctly point out “wherein at least one of the logging data or the core sample data includes NMR data, resistivity data, induction data, acoustic, density data, PE data, SP data, natural gamma ray data, and neutron data.”
However, Zhang teaches “wherein at least one of the logging data or the core sample data includes nuclear magnetic resonance data, resistivity data, induction data, acoustic, density data, photoelectric data, spontaneous potential data, natural gamma ray data, and neutron data.” (Para. 0028, “inputs used to train a machine learning model such as a neural network may include a wide variety of information types, including seismic volumes (both pre- and post-stack), seismic geologic maps, seismic images, electromagnetic volumes, checkshots, gravity volumes, horizons, synthetic log data, well logs, mud logs, gas logs, well deviation surveys, isopachs, vertical seismic profiles, microseismic data, drilling dynamics data, initial information from wells, core data, gamma, temperature, torque, differential pressure, standpipe pressure, mud weight, downhole accelerometer data, downhole vibration data, and combinations thereof. In certain embodiments, inputs may include gamma, resistivity, neutron, density, compressional, and/or shear logs” [wherein at least one of the logging data or the core sample data includes resistivity data, density data, natural gamma ray data, and neutron data].)
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to add “wherein at least one of the logging data or the core sample data includes nuclear magnetic resonance data, resistivity data, induction data, acoustic, density data, photoelectric data, spontaneous potential data, natural gamma ray data, and neutron data” as conceptually seen from the teaching of Zhang, into that of Patent No. 12,111,441 because this modification of acquiring specific measurement data while in the wellbore for the advantageous purpose of characterizing the parameters of the wellbore (Zhang, Para. 0011-0014). Further motivation to combine be that Patent No. 12,111,441 and Zhang are analogous art to the current claim are directed to modeling parameters of oil reservoirs.
Regarding claim 8, Patent No. 12,111,441 fails to distinctly point out “wherein the at least one property is selected from a group consisting of: an electrical efficiency parameter of reservoir rock associated with the reservoir formation; a tortuosity of reservoir rock associated with the reservoir formation; and a cementation of reservoir rock associated with the reservoir formation.”
However, Zhang teaches “wherein the at least one property is selected from the group consisting of: an electrical efficiency parameter of reservoir rock associated with the reservoir formation; a tortuosity of reservoir rock associated with the reservoir formation; and a cementation of reservoir rock associated with the sub surf ace reservoir formation.” (Para. 0030, “Parameters output by the model may include, for example, rock properties and geo-mechanics, gamma, resistivity, neutron, density, acoustic impedance and velocity, stress, brittleness, Young's modulus and Poisson's ratio, mud weights, compressive strength, friction angle, pore pressure attributes, fracture gradients, wellbore stability, petro-physical properties, total organic content, water saturation, porosity, permeability, lithofacies classifications, and/or the like” [wherein the at least one property is selected from a group consisting of: a tortuosity of reservoir rock associated with the reservoir formation and a cementation of reservoir rock associated with the reservoir formation].)
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to add “wherein the at least one property is selected from a group consisting of: an electrical efficiency parameter of reservoir rock associated with the reservoir formation; a tortuosity of reservoir rock associated with the reservoir formation; and a cementation of reservoir rock associated with the reservoir formation” as conceptually seen from the teaching of Zhang, into that of Patent No. 12,111,441 because this modification of acquiring specific measurement data while in the wellbore for the advantageous purpose of characterizing the specific parameters of the wellbore (Zhang, Para. 0011-0014). Further motivation to combine be that Patent No. 12,111,441 and Zhang are analogous art to the current claim are directed to modeling parameters of oil reservoirs.
Regarding claim 9, Patent No. 12,111,441 fails to distinctly point out “wherein the at least one property of the reservoir formation is selected from a group consisting of porosity, permeability, capillary pressure, bound fluid volume, shale volume, rock saturation, productivity index, relative permeability, effective permeability, hydrocarbon properties, and formation salinity.”
However, Zhang teaches “wherein the at least one property of the reservoir formation is selected from a group consisting of porosity, permeability, capillary pressure, bound fluid volume, shale volume, rock saturation, productivity index, relative permeability, effective permeability, hydrocarbon properties, and formation salinity.” (Para. 0030, “Parameters output by the model may include, for example, rock properties and geo-mechanics, gamma, resistivity, neutron, density, acoustic impedance and velocity, stress, brittleness, Young's modulus and Poisson's ratio, mud weights, compressive strength, friction angle, pore pressure attributes, fracture gradients, wellbore stability, petro-physical properties, total organic content, water saturation, porosity, permeability, lithofacies classifications, and/or the like” [wherein the at least one property of the reservoir formation is selected a group consisting of porosity, permeability, rock saturation, relative permeability, and hydrocarbon properties].)
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to add “wherein the at least one property of the reservoir formation is selected from a group consisting of porosity, permeability, capillary pressure, bound fluid volume, shale volume, rock saturation, productivity index, relative permeability, effective permeability, hydrocarbon properties, and formation salinity” as conceptually seen from the teaching of Zhang, into that of Patent No. 12,111,441 because this modification of acquiring specific measurement data while in the wellbore for the advantageous purpose of characterizing the specific parameters of the wellbore (Zhang, Para. 0011-0014). Further motivation to combine be that Patent No. 12,111,441 and Zhang are analogous art to the current claim are directed to modeling parameters of oil reservoirs.
As per claim 10, Patent No. 12,111,441 teaches “wherein values of the at least one property are estimated for different portions of the reservoir formation based on the formation model and the method further comprises: determining, based on the estimated values, a variation of the at least one property over the different portions of the reservoir formation, identifying boundaries of the different portions based on the variation of the values of the at least one property, and determining different rock facies of the reservoir formation, based on the identified boundaries.” (Claim 5, wherein the plurality of candidate formation models correspond to a plurality of facies associated with the reservoir formation, the set of primitives further include a set of branching conditions, each candidate formation model is generated by the symbolic regression model using the set of branching conditions for a corresponding one of the plurality of facies, and the set of branching conditions includes one or more conditional operators for the symbolic regression model to generate the mathematical expression for each of ordinary skill in the art without departing from the scope candidate formation model.)
As per claim 11, Patent No. 12,111,441 teaches “wherein the formation model is represented by a target function.” (Claim 1, training, by the computing device, a symbolic regression model to generate a plurality of candidate formation models representing the target parameter of the reservoir formation, based on the selected input parameters, and claim 4, generating the target petrophysical model of the reservoir formation as an ensemble of the plurality of candidate formation models, based on the determination.)
Re Claim 14, it is a system claim, having similar limitations of claim 1. Thus, claim 14 is also rejected under the similar rationale as cited in the rejection of claim 1.
Furthermore, regarding claim 14, Patent No. 12,111,441 teaches “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 operations” (Claim 11, A system comprising: at least one processor; and a memory coupled to the at least one processor having instructions stored therein, which when executed by the processor, cause the at least one processor to perform a plurality of operations).
Re Claim 15, it is a system claim, having similar limitations of claim 4. Thus, claim 15 is also rejected under the similar rationale as cited in the rejection of claim 4.
Re Claim 16, it is a system claim, having similar limitations of claim 3. Thus, claim 16 is also rejected under the similar rationale as cited in the rejection of claim 3.
Re Claim 17, it is a system claim, having similar limitations of claim 5. Thus, claim 17 is also rejected under the similar rationale as cited in the rejection of claim 5.
Re Claim 18, it is a system claim, having similar limitations of claim 10. Thus, claim 18 is also rejected under the similar rationale as cited in the rejection of claim 10.
Re Claim 20, it is an articles of manufacture claim, having similar limitations of claim 1. Thus, claim 20 is also rejected under the similar rationale as cited in the rejection of claim 1.
Furthermore, regarding claim 20, Patent No. 12,111,441 teaches “A computer-readable storage medium having instructions stored thereon, which, when executed by a computer, cause the computer to perform a plurality of operations” (Claim 20, non-transitory computer-readable medium having instructions stored thereon, which, when executed by a computer, cause the computer to perform a plurality of operations).
Claim 7 is rejected on the ground of nonstatutory double patenting as being unpatentable over claim 6 of U.S. Patent No. 12,111,441 B2 and Zhang et al. as applied to claim 2 above, and further in view of US 20160328419 A1 Safonov et al. [herein “Safonov”].
As per claim 7, Patent No. 12,111,441 B2 nor Zhang specifically teach “wherein the core analysis tool comprises at least one of permeameter, a porosimeter, or an imaging device.”
However, in the same field of endeavor namely extracting data for the purpose of characterizing rocks, Safonov teaches “wherein the core analysis tool comprises at least one of permeameter, a porosimeter, or an imaging device.” (Para. 0025, “The data from core lab experiments comprise results of routine core analysis and results of special core analysis” [core analysis]. “The well logs data comprise well testing data and petrophysical reservoir characterization. The digital rock data could comprise a set of digital core images of rock samples, results of mineral mapping in the rock samples, results of representative elementary volume analysis of the rock samples, results of microporosity analysis, results of wettability mapping in the rock samples, results of microstructural and heterogeneity analysis by NMR/MRI, results of geomechanical analysis. Digital core images could be obtained via the X-ray microtomography” [an imaging device]. Further see Para. 0023-0025.)
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to add “wherein the core analysis tool comprises at least one of permeameter, a porosimeter, or an imaging device” as conceptually seen from the teaching of Safonov, into that of Patent No. 12,111,441 B2 and Zhang because this modification of acquiring core analysis data through an imaging device for the advantageous purpose of automatically and efficient capturing data for the core analysis without interrupting operations (Safonov, Para. 0002 & 0027). Further motivation to combine be that Mahmoodpour, Patent No. 12,111,441 B2, and Safonov are analogous art to the current claim are directed to extracting data for the purpose of characterizing rocks.
Claims 12-13 and 19 are rejected on the ground of nonstatutory double patenting as being unpatentable over claim 1 of U.S. Patent No. 12,111,441 B2 and Zhang et al. as applied to claim 11 above, and further in view of Mahmoodpour, Soran, Ehsan Kamari, Mohammad Reza Esfahani, and Amir Karimi Mehr. “Prediction of cementation factor for low-permeability Iranian carbonate reservoirs using particle swarm optimization-artificial neural network model and genetic programming algorithm.” Journal of Petroleum Science and Engineering 197 (2021): 108102 [herein “Mahmoodpour”].
As per claim 12, Patent No. 12,111,441 B2 nor Zhang specifically teach “wherein the target function is based on an Archie equation.”
However, in the same field of endeavor namely modeling parameters of oil reservoirs, Mahmoodpour teaches “wherein the target function is based on an Archie equation.” (Pg. 2 Sect. 1, “Archie provided the first insight into the cementation exponent (m) in 1942 (Archie, 1942a, 1942b). He figured out this exponent helped in the characterization of the empirical relation between formation factor (F) and porosity (ϕ), as follows (Eq. 2)” [target function is based on an Archie equation]. Further see Sect. 1-2 and Equation 2.)
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to add “wherein the target function is based on an Archie equation” as conceptually seen from the teaching of Mahmoodpour, into that of Patent No. 12,111,441 B2 and Zhang because this modification of utilizing an Archie equation as a base function for the advantageous purpose of determining a relation between cementation and porosity in reservoirs (Mahmoodpour, Sect. 1). Further motivation to combine be that Mahmoodpour, Patent No. 12,111,441 B2, and Mahmoodpour are analogous art to the current claim are directed to modeling parameters of oil reservoirs.
As per claim 13, Patent No. 12,111,441 B2 nor Zhang specifically teach “wherein the target function is derived directly from the training data without using a predefined base function.”
However, Mahmoodpour teaches “wherein the target function is derived directly from the training data without using a predefined base function.” (Pg. 5 Sect. 2, “In GP, to develop chromosome tree structures to be operated on data, an initial population of random functions are produced” [wherein the target function is derived directly from the training data]. Pg. 5 Sect. 2, “GP is recognized as ‘symbolic regression,’ wherein the algorithm itself aims to discover the model form and later adjusts the model parameters (Augusto and Barbosa, 2000; Searson et al., 2010). In contrast, in conventional regression methodologies, the form of the model should be fixed manually, and then the parameters of the model will be specified by the fitting” [e.g., without using a predefined base function]. Further see Sect. 2.)
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to add “wherein the target function is derived directly from the training data without using a predefined base function” as conceptually seen from the teaching of Mahmoodpour, into that of Patent No. 12,111,441 B2 and Zhang because this modification of only deriving a model from the training data for the advantageous purpose of allowing the model to be unrestricted by a fixed function and be a representation of the data only (Mahmoodpour, Sect. 2). Further motivation to combine be that Mahmoodpour, Patent No. 12,111,441 B2, and Mahmoodpour are analogous art to the current claim are directed to modeling parameters of oil reservoirs.
Re Claim 19, it is a system claim, having similar limitations of claims 12 and 13. Thus, claim 19 is also rejected under the similar rationale as cited in the rejection of claims 12 and 13.
Claim Rejections - 35 U.S.C. § 103
The following is a quotation of 35 U.S.C. § 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
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 1-20 are rejected under 35 U.S.C. § 103 as being unpatentable over Mahmoodpour in view of US 2021/0326721 A1 Zhang et al. [herein “Zhang2”],
As per claim 1, Mahmoodpour teaches “A computer-implemented method comprising: receiving, by a computing device [via a network from the downhole tool], the training data [during the course of the downhole operation]”. (Pg. 2 Sect. 1, “This study is a step to develop a correlation for carbonate reservoirs that related cementation factor with other petro-physical parameters such as rock porosity, permeability, and density” [a method]. “Carbonate reservoir cores are chosen from several Iranian oilfields with different mineralogy of carbonate rocks to carry out the experiments” [receiving data]. “To model the cementation factor, a model-based PSO-ANN is developed. In the second stage of simulation, an equation for the cementation factor is discovered by genetic programming (GP) algorithm. Both models are trained using petro-physical RCAL and SCAL data, including porosity, permeability, and rock density as input, and cementation factor as the output of the models” [training data]. Pg. 3 Sect. 2, “Before using the data in the models, the original raw data were prepared using related Matlab codes” [A computer-implemented method comprising: receiving, by a computing device]. Further see Sect. 2. The examiner has interpreted that obtaining cores in oilfields in addition to using regular and special core analyses data for training models to develop a correlation for carbonate reservoirs that are prepared using Matlab code as a computer-implemented method comprising: receiving, by a computing device, the training data.)
Mahmoodpour also teaches “training, by the computing device using symbolic regression, a machine learning model to determine a formation model representing the reservoir formation, based on the training data received [from the downhole tool]”. (Pg. 2 Sect. 1, “In the second stage of simulation, an equation for the cementation factor is discovered by genetic programming (GP) algorithm” [by the computing device using symbolic regression a machine learning model to determine a formation model representing the reservoir formation]. “Both models are trained using petro-physical RCAL and SCAL data, including porosity, permeability, and rock density as input, and cementation factor as the output of the models” [based on the training data received]. Furthermore, Sect. 2.3 “GP is recognized as “symbolic regression,” wherein the algorithm itself aims to discover the model form and later adjusts the model parameters” [GP is a machine learning algorithm, e.g. training, by the computing device using symbolic regression a machine learning model to determine a formation model representing the reservoir formation]. Further see Sect. 1 and 2. The examiner has interpreted that developing a model for a cementation factor of the reservoir using a genetic programming (GP) algorithm that is trained using regular and special core analyses data as training, by the computing device using symbolic regression, a machine learning model to determine a formation model representing the reservoir formation, based on the training data received from the one or more data sources.)
Mahmoodpour also teaches “estimating, by the computing device, at least one property of the reservoir formation, based on the formation model”. (Pg. 2 Sect. 1, “In the second stage of simulation, an equation for the cementation factor is discovered by genetic programming (GP) algorithm” [by the computing device based on the formation model]. “Both models are trained using petro-physical RCAL and SCAL data, including porosity, permeability, and rock density as input, and cementation factor as the output of the models” [estimating at least one property of the reservoir formation]. Further see Sect. 1 and 2. The examiner has interpreted that developing a model for a cementation factor of the reservoir using a genetic programming (GP) algorithm as estimating, by the computing device, at least one property of the reservoir formation, based on the formation model.)
Mahmoodpour does not specifically teach “performing, via a downhole tool, a downhole operation along a wellbore drilled within a reservoir formation, wherein the downhole operation comprises at least collecting training data for modeling the reservoir formation surrounding the wellbore”, “receiving, by a computing device via a network from the downhole tool, the training data during the course of the downhole operation”, “training, a machine learning model to determine a formation model representing the reservoir formation, based on the training data received from the downhole tool” and “adjusting, via the downhole tool, the downhole operation along the wellbore within the reservoir formation based on the at least one estimated property.”
However, in the same field of endeavor namely modeling parameters of oil reservoirs, Zhang2 teaches “performing, via a downhole tool, a downhole operation along a wellbore drilled within a reservoir formation, wherein the downhole operation comprises at least collecting training data for modeling the reservoir formation surrounding the wellbore”. (Para. 0065, “the log data can be measured using a logging while drilling (LWD) tool. In other embodiments, the log data can be measured using another logging tool suspended in the wellbore on wireline” [performing, via a downhole tool, a downhole operation along a wellbore drilled, wherein the downhole operation comprises at least collecting data]. “In certain embodiments, the logging tool may include one or more induced nuclear sondes, such as a PNC sonde (aka pulsed neutron lifetime (PNL) sonde and/or carbon/oxygen sonde), a density (aka gamma-gamma) sonde, a neutron porosity sonde, or combinations thereof. As is known in the art, induced nuclear sondes, density sondes, and neutron porosity sondes are tools that contain radioactive sources. The logging tool may also include one or more passive (aka natural) nuclear sondes that do not contain radioactive sources, such as a gamma ray sonde, a spectral gamma ray sonde, or combinations thereof. The logging tool may also include one or more nonnuclear sondes, such as a spontaneous potential (SP) sonde, a resistivity sonde, a sonic sonde, a nuclear magnetic resonance sonde, a caliper sonde, a temperature sonde, and combinations thereof” [tools for measuring data, e.g., collecting data]. Para. 0046, “For example, the training inputs may include one or more attributes related to a wellbore that have been measured or determined based on measured data, and the labels may comprise different properties related to the wellbore that are to be output by a machine learning model. It is noted that “labels” are only included as one example for training a machine learning model, and other techniques may be used to train a machine learning model based on attributes at depth points and adjacent waveforms. In certain embodiments, the attributes are captured by various sensors during a drilling or reservoir stimulation operation” [within a reservoir formation and training data for modeling the reservoir formation surrounding the wellbore]. Para. 0037, “an earth model is created by finding non-linear ties between well log data and a seismic image volume in a statistical fashion. The process preserves realistic output without the specification of somewhat arbitrary constraints as in done in traditional seismic inversion, as the machine learning model is able to learn the underlying physics as a part of the network training process” [training data for modeling the reservoir formation surrounding the wellbore]. Further see Para. 0023, 0037, 0046, 0065, and 0090. The examiner has interpreted that using a logging while drilling (LWD) tool including logging sonde tools for density, porosity, spontaneous potential (SP), a resistivity, a sonic, and nuclear magnetic resonance to measure logging data suspended in the wellbore on wireline as training inputs captured during a drilling or reservoir stimulation operation to training a machine learning model to create an earth model as performing, via a downhole tool, a downhole operation along a wellbore drilled within a reservoir formation, wherein the downhole operation comprises at least collecting training data for modeling the reservoir formation surrounding the wellbore.)
Zhang2 teaches “receiving, by a computing device via a network from the downhole tool, the training data during the course of the downhole operation”. ( Para. 0046, “For example, the training inputs may include one or more attributes related to a wellbore that have been measured or determined based on measured data, and the labels may comprise different properties related to the wellbore that are to be output by a machine learning model. It is noted that “labels” are only included as one example for training a machine learning model, and other techniques may be used to train a machine learning model based on attributes at depth points and adjacent waveforms. In certain embodiments, the attributes are captured by various sensors during a drilling or reservoir stimulation operation” [receiving the training data during the course of the downhole operation]. Para. 0091, “One or more of the model training engine 720, the modeling engine 722, the dynamic tying engine 724, the automatic input selection engine 726, the auto-ensemble engine 728, the computer vision engine 730, the earth modeling engine 732, and the drilling engine 734 in memory 708 may communicate with other devices (e.g., components of a drilling system) over a network 716 (e.g., the internet, a local area network, or the like) through network interface 706 (e.g., in order to receive measurements, provide output and instructions, and the like)” [receiving, by a computing device via a network from the downhole tool]. Further see Para. 0046 and 0091. The examiner has interpreted that having the training and various other engines of the system communicate with component of the drilling system over a network to receive measurement for training inputs as receiving, by a computing device via a network from the downhole tool, the training data during the course of the downhole operation.)
Zhang2 teaches “training, a machine learning model to determine a formation model representing the reservoir formation based on the training data received from the downhole tool”. Para. 0090, “the model training engine 720 can use the training data 740 and the measurement data 742 for training the one or more machine learning models 744, for example according to operations 200 of FIGS. 2A-2B” [training, a machine learning model based on the training data]. “In certain embodiments, the one or more machine learning models 744 can be simulated using the modeling engine 722. In certain embodiments, the dynamic tying engine 724 can enable utilization of the measurement data 742 in real-time, for example by relating seismic data in the time domain to log data in the depth domain according to operations 300 of FIG. 3. In certain embodiments, the measurement data 742 can be recorded during drilling and used in real-time” [based on the training data received from the downhole tool]. Para. 0037, “an earth model is created by finding non-linear ties between well log data and a seismic image volume in a statistical fashion. The process preserves realistic output without the specification of somewhat arbitrary constraints as in done in traditional seismic inversion, as the machine learning model is able to learn the underlying physics as a part of the network training process” [to determine a formation model representing the reservoir formation]. Further see Para. 0037, 0046, and 0090-0091. The examiner has interpreted that using measurement data measured in real-time of log data recorded during drilling to train a machine learning model to create an earth model of the well as training, a machine learning model to determine a formation model representing the reservoir formation based on the training data received from the downhole tool.)
Zhang2 also teaches “adjusting, via the downhole tool, the downhole operation along the wellbore within the reservoir formation based on the at least one estimated property.” (Para. 0032, “In certain reservoirs, the earth model can be used to optimize well placement, and as the well is being drilled, the earth model can be updated to ensure the well is landed in and staying in the desired zone” [adjusting, via the downhole tool, the downhole operation along the wellbore within the reservoir formation]. Para. 0043, “Once trained, the machine learning model 120 is used to produce an earth model 130, which models various parameters output by machine learning model 120, such as compressional, shear, density, neutron porosity, porosity, water saturation, gamma ray, and the like” [estimated at least one property]. “Parameters may be output by machine learning model 120 in real-time or near real-time, and may include parameters at various depth points as well as adjacent parameters (e.g., waveforms) in a plurality of directions with respect to each depth point. As such, techniques described herein provide real-time properties both at the bit position and ahead of the bit position. Accordingly, an earth model can be determined and continuously updated, allowing improved decisions to be made in real-time with respect to a given well” [adjusting based on the at least one estimated property]. Further see Para. 0032 and 0043. The examiner has interpreted that optimizing the well placement as the well is being drilled for a bit position using an earth model updated using real-time properties produced by a machine learning model as adjusting, via the downhole tool, the downhole operation along the wellbore within the reservoir formation based on the at least one estimated property.)
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to add “performing, via a downhole tool, a downhole operation along a wellbore drilled within a reservoir formation, wherein the downhole operation comprises at least collecting training data for modeling the reservoir formation surrounding the wellbore”, “receiving, by a computing device via a network from the downhole tool, the training data during the course of the downhole operation”, “training, a machine learning model to determine a formation model representing the reservoir formation, based on the training data received from the downhole tool” and “adjusting, via the downhole tool, the downhole operation along the wellbore within the reservoir formation based on the at least one estimated property,” as conceptually seen from the teaching of Zhang2, into that of Mahmoodpour because this modification of gathering the training data using a downhole tool and changing the drill position based on estimated properties as a result of a trained model for the advantageous purpose of improving production rates in real-time (Zhang2, Para. 0033). Further motivation to combine be that Mahmoodpour and Zhang2 are analogous art to the current claim are directed to modeling parameters of oil reservoirs.
As per claim 2, Mahmoodpour teaches “wherein the training data includes logging data received from a logging tool [positioned within the wellbore] and core sample data received from a core analysis tool”. (Pg. 2 Sect. 1, “Carbonate reservoir cores are chosen from several Iranian oilfields with different mineralogy of carbonate rocks to carry out the experiments” [core samples]. “To model the cementation factor, a model-based PSO-ANN is developed. In the second stage of simulation, an equation for the cementation factor is discovered by genetic programming (GP) algorithm” [by the computing device using symbolic regression a machine learning model to determine a formation model representing the reservoir formation]. “Both models are trained using petro-physical RCAL and SCAL data, including porosity, permeability, and rock density as input, and cementation factor as the output of the models” [wherein the training data includes core sample data received from a core analysis tool]. Pg. 2 Sect. 1, “In this equation, (Rw) formation water resistivity (Rt) real resistivity of the plug samples at the saturation Sw, and (ϕ) rock porosity is calculated from well logs” [logging data]. Pg. 3 Sect. 2, “Test formation water is synthesized (SFW) and its resistivity (Rw) is determined using a two-platinum electrode” [received from a logging tool]. Further see Sect. 1 and 2. The examiner has interpreted that choosing carbonate reservoir cores to gather data from a special core analysis and resistivity data collected using an electrode to train a genetic programming algorithm as wherein the training data includes logging data received from a logging tool and core sample data received from a core analysis tool.)
Mahmoodpour also teaches “wherein the training comprises: training the machine learning model to generate a plurality of formation models based on the logging data and the core sample data”. (Pg. 5 Sect. 2, “In GP, to develop chromosome tree structures to be operated on data, an initial population of random functions are produced” [training the machine learning model to generate a plurality of formation models based on the logging data and the core sample data]. Further see Sect. 2. The examiner has interpreted that developing as an initial population of functions on the data by the GP as wherein the training comprises: training the machine learning model to generate a plurality of formation models based on the logging data and the core sample data.)
Mahmoodpour also teaches “selecting one of the plurality of formation models, based on a predetermined fitness objective.” (Pg. 5-6 Sect. 2, “After producing a first parent population of a random configuration of functions and terminals of the problem, the fitness function is assigned to the primary models of parents that are determined by weighted summation of genes with a bias term” [based on a predetermined fitness objective]. “A schematic drawing of a typical model, including two genes is illustrated in Fig. 4. Then the structure of the best performing trees is modified through recombining randomly chosen parts of two existing tree structures (i.e., programs) using a cross over operations” [selecting one of the plurality of formation models]. Further see Sect. 2. The examiner has interpreted that modifying the best performing tree based on a fitness function as selecting one of the plurality of formation models, based on a predetermined fitness objective.)
Mahmoodpour does not specifically teach “wherein the training data includes logging data received from a logging tool positioned within the wellbore and core sample data received from a core analysis tool.”
However, Zhang2 teaches “wherein the training data includes logging data received from a logging tool positioned within the wellbore and core sample data received from a core analysis tool.” (Para. 0065, “the log data can be measured using a logging while drilling (LWD) tool. In other embodiments, the log data can be measured using another logging tool suspended in the wellbore on wireline” [logging data received from a logging tool positioned within the wellbore]. “In certain embodiments, the logging tool may include one or more induced nuclear sondes, such as a PNC sonde (aka pulsed neutron lifetime (PNL) sonde and/or carbon/oxygen sonde), a density (aka gamma-gamma) sonde, a neutron porosity sonde, or combinations thereof. As is known in the art, induced nuclear sondes, density sondes, and neutron porosity sondes are tools that contain radioactive sources. The logging tool may also include one or more passive (aka natural) nuclear sondes that do not contain radioactive sources, such as a gamma ray sonde, a spectral gamma ray sonde, or combinations thereof. The logging tool may also include one or more nonnuclear sondes, such as a spontaneous potential (SP) sonde, a resistivity sonde, a sonic sonde, a nuclear magnetic resonance sonde, a caliper sonde, a temperature sonde, and combinations thereof” [tools for measuring data, e.g., logging data]. Para. 0046, “For example, the training inputs may include one or more attributes related to a wellbore that have been measured or determined based on measured data, and the labels may comprise different properties related to the wellbore that are to be output by a machine learning model. It is noted that “labels” are only included as one example for training a machine learning model, and other techniques may be used to train a machine learning model based on attributes at depth points and adjacent waveforms. In certain embodiments, the attributes are captured by various sensors during a drilling or reservoir stimulation operation” [e.g., wherein the training data includes logging data received from a logging tool positioned within the wellbore]. Para. 0047, “the training data may include a wide variety of information types, including seismic volumes (both pre- and post-stack), seismic geologic maps, seismic images, electromagnetic volumes, checkshots, gravity volumes, horizons, synthetic log data, well logs, mud logs, gas logs, well deviation surveys, isopachs, vertical seismic profiles, microseismic data, drilling dynamics data, initial information from wells, core data” [e.g., core sample data received from a core analysis tool]. Further see Para. 0046-0047 and 0065. The examiner has interpreted that using a logging while drilling (LWD) tool including logging sonde tools for density, porosity, spontaneous potential (SP), a resistivity, a sonic, and nuclear magnetic resonance to measure logging data and core data while suspended in the wellbore on wireline for training inputs captured during a drilling or reservoir stimulation operation to training a machine learning model as wherein the training data includes logging data received from a logging tool positioned within the wellbore and core sample data received from a core analysis tool.)
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to add “a logging tool positioned within the wellbore” as conceptually seen from the teaching of Zhang2, into that of Mahmoodpour because this modification of acquiring measurement data while in the wellbore with a logging tool for the advantageous purpose of outputting real-time properties of the earth model based on the real position of the bit (Zhang2, Para. 0043). Further motivation to combine be that Mahmoodpour and Zhang2 are analogous art to the current claim are directed to modeling parameters of oil reservoirs.
As per claim 3, Mahmoodpour teaches “wherein selecting one of the plurality of formation models comprises: ranking the plurality of formation models according to the predetermined fitness objective and selecting one of the plurality of formation models, based on the ranking.” (Pg. 5-6 Sect. 2, “After producing a first parent population of a random configuration of functions and terminals of the problem, the fitness function is assigned to the primary models of parents that are determined by weighted summation of genes with a bias term. “A schematic drawing of a typical model, including two genes is illustrated in Fig. 4. Then the structure of the best performing trees is modified through recombining randomly chosen parts of two existing tree structures (i.e., programs) using a cross over operations” [modifying the tree that perform the best as weighted by a fitness function, e.g., ranking the plurality of formation models according to the predetermined fitness objective and selecting one of the plurality of formation models, based on the ranking]. Further see Sect. 2. The examiner has interpreted that modifying the best performing tree based on a fitness function as wherein selecting one of the plurality of formation models comprises: ranking the plurality of formation models according to the predetermined fitness objective and selecting one of the plurality of formation models, based on the ranking
As per 4, Mahmoodpour teaches “wherein the predetermined fitness objective is defined by a fitness function based on a set of primitives representing measurement characteristics of the downhole tool and the core analysis tool.” (Pg. 5-6 Sect. 2, “In GP, to develop chromosome tree structures to be operated on data, an initial population of random functions are produced. It mostly produces several genes instead of one that each one is a typical GP tree. This type of GP that it is known as “multi-gene GP” provide more accuracy and more straightforward mathematical relations compared with standard GP that deals with one gene [e.g., based on a set of primitives representing measurement characteristics of the downhole tool and the core analysis tool]. “After producing a first parent population of a random configuration of functions and terminals of the problem, the fitness function is assigned to the primary models of parents that are determined by weighted summation of genes with a bias term” [wherein the predetermined fitness objective is defined by a fitness function]. “A schematic drawing of a typical model, including two genes is illustrated in Fig. 4.” Further see Sect. 2. The examiner has interpreted that assigning a fitness function to parent population models that are a weighted summation of genes with a bias term produced by the functions which are operated on the data as wherein the predetermined fitness objective is defined by a fitness function based on a set of primitives representing measurement characteristics of the downhole tool and the core analysis tool.)
As per claim 5, Mahmoodpour teaches “wherein the training comprises: generating a parent population of formation models; and performing crossover and mutation operations over a plurality of iterations until a predetermined termination condition is reached, wherein a child population of formation models is generated at each iteration based on the parent population generated at a preceding iteration, and wherein one of the plurality of formation models is selected from the child population of formation models generated from the crossover and mutation operations”. (Pg. 5-6 Sect. 2, “After producing a first parent population of a random configuration of functions and terminals of the problem, the fitness function is assigned to the primary models of parents that are determined by weighted summation of genes with a bias term” [wherein the training comprises: generating a parent population of formation models]. Pg. 6 Sect. 2, “Then the structure of the best performing trees is modified through recombining randomly chosen parts of two existing tree structures (i.e., programs) using a cross over operations” [performing crossover and mutation operations]. Finally, the new tree structures (computer program) are created from existing trees using mutating a randomly selected part of the program” [and wherein one of the plurality of formation models is selected from the child population of formation models generated from the crossover and mutation operations]. “After creating the initial parent population, the fitness measurement, cross over, and mutation operations are repeatedly carried out” [wherein a child population of formation models is generated at each iteration based on the parent population generated at a preceding iteration] “until the stop criterion has been met” [until a predetermined termination condition is reached]. Further see Sect. 2. The examiner has interpreted that producing a first parent population of the models; recombing structures using crossover operations; mutating structures to create new structures; and repeating the fitness measurement, cross over and mutation operations until the stop criterion has been met as wherein the training comprises: generating a parent population of formation models; and performing crossover and mutation operations over a plurality of iterations until a predetermined termination condition is reached, wherein a child population of formation models is generated at each iteration based on the parent population generated at a preceding iteration, and wherein one of the plurality of formation models is selected from the child population of formation models generated from the crossover and mutation operations.)
As per claim 6, Mahmoodpour teaches “wherein at least one of the logging data or the core sample data includes nuclear magnetic resonance data, resistivity data, induction data, acoustic, density data, photoelectric data, spontaneous potential data, natural gamma ray data, and neutron data.” (Pg. 2 Sect. 1, “In this equation, (Rw) formation water resistivity (Rt) real resistivity of the plug samples at the saturation Sw, and (ϕ) rock porosity is calculated from well logs” [wherein at least one of the core sample data includes resistivity data]. Further see Sect. 1 and 2. The examiner has interpreted that real resistivity data of the plug samples as wherein at least one of the logging data or the core sample data includes nuclear magnetic resonance data, resistivity data, induction data, acoustic, density data, photoelectric data, spontaneous potential data, natural gamma ray data, and neutron data.)
As per claim 7, Mahmoodpour does specifically teach “wherein the core analysis tool comprises at least one of permeameter, a porosimeter, or an imaging device.”
However, Zhang2 teaches “wherein the core analysis tool comprises at least one of permeameter, a porosimeter, or an imaging device.” (Para. 0046, “For example, the training inputs may include one or more attributes related to a wellbore that have been measured or determined based on measured data, and the labels may comprise different properties related to the wellbore that are to be output by a machine learning model. It is noted that “labels” are only included as one example for training a machine learning model, and other techniques may be used to train a machine learning model based on attributes at depth points and adjacent waveforms. In certain embodiments, the attributes are captured by various sensors during a drilling or reservoir stimulation operation” [e.g., wherein the training data includes logging data received from a logging tool positioned within the wellbore]. Para. 0047, “the training data may include a wide variety of information types, including seismic volumes (both pre- and post-stack), seismic geologic maps, seismic images, electromagnetic volumes, checkshots, gravity volumes, horizons, synthetic log data, well logs, mud logs, gas logs, well deviation surveys, isopachs, vertical seismic profiles, microseismic data, drilling dynamics data, initial information from wells, core data” [e.g., training data include core sample data received from a core analysis tool]. Para. 0041, “Training data parameters 110 are based on a variety of training inputs, such as well logs, synthetic logs, pre and post stack data, horizons, seismic images” [received training data includes seismic images, e.g., the core analysis tool comprises an imaging device]. Further see Para. 0041 and 0046-0047. The examiner has interpreted that having training input such as core data captured during a drilling or reservoir stimulation operation to training a machine learning model that includes seismic images as wherein the core analysis tool comprises an imaging device.)
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to add “wherein the core analysis tool comprises at least one of permeameter, a porosimeter, or an imaging device” as conceptually seen from the teaching of Zhang2, into that of Mahmoodpour because this modification of acquiring core analysis data through an imaging device for the advantageous purpose of outputting real-time properties of the earth model based on the real position of the bit (Zhang2, Para. 0043). Further motivation to combine be that Mahmoodpour and Zhang2 are analogous art to the current claim are directed to modeling parameters of oil reservoirs.
As per claim 8, Mahmoodpour teaches “wherein the at least one property is selected from a group consisting of: an electrical efficiency parameter of reservoir rock associated with the reservoir formation; a tortuosity of reservoir rock associated with the reservoir formation; and a cementation of reservoir rock associated with the reservoir formation.” (Pg. 2 Sect. 1, “This study is a step to develop a correlation for carbonate reservoirs that related cementation factor with other petro-physical parameters such as rock porosity, permeability, and density” [cementation of reservoir rock associated with the subsurface reservoir formation]. “Carbonate reservoir cores are chosen from several Iranian oilfields with different mineralogy of carbonate rocks to carry out the experiments. To model the cementation factor, a model-based PSO-ANN is developed. In the second stage of simulation, an equation for the cementation factor is discovered by genetic programming (GP) algorithm. Both models are trained using petro-physical RCAL and SCAL data, including porosity, permeability, and rock density as input, and cementation factor as the output of the models”. Further see Sect. 1 and 2. The examiner has interpreted that output of the model is a cementation factor for carbonate reservoirs as wherein the at least one property is selected from a group consisting of: an electrical efficiency parameter of reservoir rock associated with the reservoir formation; a tortuosity of reservoir rock associated with the reservoir formation; and a cementation of reservoir rock associated with the reservoir formation.)
As per claim 9, Mahmoodpour teaches “wherein the at least one property of the reservoir formation is selected from a group consisting of porosity, permeability, capillary pressure, bound fluid volume, shale volume, rock saturation, productivity index, relative permeability, effective permeability, hydrocarbon properties, and formation salinity.” (Pg. 2 Sect. 1, “This study is a step to develop a correlation for carbonate reservoirs that related cementation factor with other petro-physical parameters such as rock porosity, permeability, and density. Carbonate reservoir cores are chosen from several Iranian oilfields with different mineralogy of carbonate rocks to carry out the experiments. To model the cementation factor, a model-based PSO-ANN is developed. In the second stage of simulation, an equation for the cementation factor is discovered by genetic programming (GP) algorithm. Both models are trained using petro-physical RCAL and SCAL data, including porosity, permeability, and rock density as input, and cementation factor as the output of the models”. Pg. 2 Sect. 1, “The cementation factor is greatly affected by many factors like pore geometry, pore size distribution, secondary porosity, surface-to-volume ratio, the conductivity of water and mineral, reservoir temperature, reservoir pressure, cement, and wettability of porous rocks” [wherein the at least one property of the reservoir formation is selected from the group consisting of porosity and hydrocarbon properties]. Further see Sect. 1 and 2. The examiner has interpreted that output of the model is a cementation factor for carbonate reservoirs that is a factor of pore geometry, pore size, porosity, surface to volume ratio, conductivity of mineral, and wettability of porous rocks as wherein the at least one property of the reservoir formation is selected from a group consisting of porosity, permeability, capillary pressure, bound fluid volume, shale volume, rock saturation, productivity index, relative permeability, effective permeability, hydrocarbon properties, and formation salinity.)
As per claim 10, Mahmoodpour teaches “wherein values of the at least one property are estimated for different portions of the reservoir formation based on the formation model”. (Pg. 2 Sect. 1, “In the second stage of simulation, an equation for the cementation factor is discovered by genetic programming (GP) algorithm. Both models are trained using petro-physical RCAL and SCAL data, including porosity, permeability, and rock density as input, and cementation factor as the output of the models” [estimating at least one property of the reservoir formation based on the formation model]. Pg. 2 Sect. 2, “A total number of 175 clean carbonate plug samples were collected from 21 Iranian oil fields” [e.g., different portions of the reservoir formation]. Further see Sect. 1 and 2. The examiner has interpreted that developing a model for a cementation factor of the reservoir using a genetic programming (GP) algorithm for different reservoirs as wherein values of the at least one property are estimated for different portions of the reservoir formation based on the formation model.)
Mahmoodpour also teaches “the method further comprises determining, based on the estimated values, a variation of the at least one property over the different portions of the reservoir formation; identifying boundaries of the different portions based on the variation of the values of the at least one property; and determining different rock facies of the reservoir formation, based on the identified boundaries.” (Pg. 2 Sect. 2, “Moreover, petrographic studies revealed several petro-facies (porosity and fabric), including pack-stone, wackestone, dolostone, dolopackstone, dolomudstone, and dolowackstone.” Further see Sect. 2. The examiner has interpreted that conducting the petrographic studies to reveal several petro-facies in the reservoir as the method further comprises determining, based on the estimated values, a variation of the at least one property over the different portions of the reservoir formation; identifying boundaries of the different portions based on the variation of the values of the at least one property; and determining different rock facies of the reservoir formation, based on the identified boundaries.)
As per claim 11, Mahmoodpour teaches “wherein the formation model is represented by a target function.” (Pg. 2 Sect. 1, “In the second stage of simulation, an equation for the cementation factor is discovered by genetic programming (GP) algorithm. Both models are trained using petro-physical RCAL and SCAL data, including porosity, permeability, and rock density as input, and cementation factor as the output of the models” [the formation model]. Pg. 2 Sect. 1, “Archie provided the first insight into the cementation exponent (m) in 1942 (Archie, 1942a, 1942b). He figured out this exponent helped in the characterization of the empirical relation between formation factor (F) and porosity (ϕ), as follows (Eq. 2)” [represented by a target function]. Further see Sect. 1 and 2. The examiner has interpreted that developing a model for a cementation factor of the reservoir using a genetic programming (GP) algorithm to characterize a relationship between formation factor and porosity as wherein the formation model is represented by a target function.)
As per claim 12, Mahmoodpour teaches “wherein the target function is based on an Archie equation.” (Pg. 2 Sect. 1, “Archie provided the first insight into the cementation exponent (m) in 1942 (Archie, 1942a, 1942b). He figured out this exponent helped in the characterization of the empirical relation between formation factor (F) and porosity (ϕ), as follows (Eq. 2)” [target function is based on an Archie equation]. Further see Sect. 1-2 and Equation 2. The examiner has interpreted that developing a model for a cementation factor of the reservoir using a genetic programming (GP) algorithm to characterize a relationship between formation factor and porosity such as Archie’s equation as wherein the target function is based on an Archie equation.)
As per claim 13, Mahmoodpour teaches “wherein the target function is derived directly from the training data without using a predefined base function.” (Pg. 5 Sect. 2, “In GP, to develop chromosome tree structures to be operated on data, an initial population of random functions are produced” [wherein the target function is derived directly from the training data]. Pg. 5 Sect. 2, “GP is recognized as ‘symbolic regression,’ wherein the algorithm itself aims to discover the model form and later adjusts the model parameters (Augusto and Barbosa, 2000; Searson et al., 2010). In contrast, in conventional regression methodologies, the form of the model should be fixed manually, and then the parameters of the model will be specified by the fitting” [e.g., without using a predefined base function]. Further see Sect. 2. The examiner has interpreted that developing structures from the data to produce random functions to find a model form in contrast to fitting a model in a fixed basis then specifying parameters for the fitting of the model as wherein the target function is derived directly from the training data without using a predefined base function.)
Re Claim 14, it is a system claim, having similar limitations of claim 1. Thus, claim 14 is also rejected under the similar rationale as cited in the rejection of claim 1.
Furthermore, regarding claim 14, Mahmoodpour does not specifically teach “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 operations”.
However, Zhang2 teaches “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 operations”. (Para. 0088, “FIG. 7 illustrates an example computer system 700 for implementing embodiments of the present disclosure” [A system]. “As shown, the system 700 includes a central processing unit (CPU) 702, one or more I/O device interfaces 704 that may allow for the connection of various I/O devices 714 (e.g., keyboards, displays, mouse devices, pen input, etc.) to the system 700, a network interface 706, memory 708, storage 710, and an interconnect 712.” [a processor and a memory]. Para. 0089, “The CPU 702 may retrieve and execute programming instructions stored in the memory” [memory coupled to the processor having instructions stored therein]. Para. 0099, “A computer-readable storage medium may be coupled to a processor such that the processor can read information from, and write information to, the storage medium” [memory coupled to the processor having instructions stored therein, which when executed by the processor, cause the processor to perform a plurality of operations]. Further see 0088-0089 and 0099. The examiner has interpreted that a computer system for implementing embodiments of the present disclosure that includes a central processing unit memory as a computer-readable storage medium coupled to a processor storing instructions in the memory such that the processor can read information from, and write information to, the storage medium as 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 operations.)
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to add “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 operations” as conceptually seen from the teaching of Zhang2, into that of Mahmoodpour because this modification of utilizing physical devices for the advantageous purpose of providing a means for the operation and analysis of the system (Zhang2, Para. 0088). Further motivation to combine be that Mahmoodpour and Zhang2 are analogous art to the current claim are directed to modeling parameters of oil reservoirs.
Re Claim 15, it is a system claim, having similar limitations of claim 4. Thus, claim 15 is also rejected under the similar rationale as cited in the rejection of claim 4.
Re Claim 16, it is a system claim, having similar limitations of claim 3. Thus, claim 17 is also rejected under the similar rationale as cited in the rejection of claim 3.
Re Claim 17, it is a system claim, having similar limitations of claim 5. Thus, claim 17 is also rejected under the similar rationale as cited in the rejection of claim 5.
Re Claim 18, it is a system claim, having similar limitations of claim 10. Thus, claim 18 is also rejected under the similar rationale as cited in the rejection of claim 10.
Re Claim 19, it is a system claim, having similar limitations of claims 12 and 13. Thus, claim 19 is also rejected under the similar rationale as cited in the rejection of claims 12 and 13.
Re Claim 20, it is an articles of manufacture claim, having similar limitations of claim 1. Thus, claim 20 is also rejected under the similar rationale as cited in the rejection of claim 1.
Furthermore, regarding claim 20, Mahmoodpour does not specifically teach “A computer-readable storage medium having instructions stored thereon, which, when executed by a computer, cause the computer to perform a plurality of operations”.
However, Zhang2 teaches “A computer-readable storage medium having instructions stored thereon, which, when executed by a computer, cause the computer to perform a plurality of operations”. (Para. 0088, “FIG. 7 illustrates an example computer system 700 for implementing embodiments of the present disclosure” [A computer]. “As shown, the system 700 includes a central processing unit (CPU) 702, one or more I/O device interfaces 704 that may allow for the connection of various I/O devices 714 (e.g., keyboards, displays, mouse devices, pen input, etc.) to the system 700, a network interface 706, memory 708, storage 710, and an interconnect 712.” [a processor]. Para. 0089, “The CPU 702 may retrieve and execute programming instructions stored in the memory” [storage medium having instructions stored thereon]. Para. 0099, “A computer-readable storage medium may be coupled to a processor such that the processor can read information from, and write information to, the storage medium” [a computer-readable storage medium having instructions stored thereon, which, when executed by a computer, cause the computer to perform a plurality of operations]. Further see 0088-0099. The examiner has interpreted that a computer system for implementing embodiments of the present disclosure that includes a central processing unit memory as a computer-readable storage medium coupled to a processor storing instructions in the memory such that the processor can read information from, and write information to, the storage medium as a computer-readable storage medium having instructions stored thereon, which, when executed by a computer, cause the computer to perform a plurality of operations.)
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to add “A computer-readable storage medium having instructions stored thereon, which, when executed by a computer, cause the computer to perform a plurality of operations” as conceptually seen from the teaching of Zhang2, into that of Mahmoodpour because this modification of utilizing physical devices for the advantageous purpose of providing a means for the operation and analysis of the system (Zhang2, Para. 0088). Further motivation to combine be that Mahmoodpour and Zhang2 are analogous art to the current claim are directed to modeling parameters of oil reservoirs.
Response to Arguments
Applicant's arguments filed on October 15, 2025 have been fully considered but they are not persuasive.
Applicant argues that the combination of references does not teach each and every limitation in the claims 1, 14, and 20 because cited references fail to teach “training, by the computing device using symbolic regression, a machine learning model to determine a formation model representing the reservoir formation, based on the training data received” (See Applicant’s response, Pg. 15-17).
MPEP § 2143.03 that “All words in a claim must be considered in judging the patentability of that claim against the prior art” and “Examiners must consider all claim limitations when determining patentability of an invention over the prior art.”
As original mapped in the previous Office Action in claim 1, Mahmoodpour discloses “training, by the computing device using symbolic regression, a machine learning model to determine a formation model representing the reservoir formation, based on the training data received” as developing a model for a cementation factor of the reservoir using a genetic programming (GP) algorithm that is trained using regular and special core analyses data. As add to the mapping in the rejection above, a GP algorithm is a machine learning algorithm where “GP is recognized as “symbolic regression,” wherein the algorithm itself aims to discover the model form and later adjusts the model parameters”. Therefore, the claimed limitation is taught. Additional emphasis has been added to this mapping in the rejection above to the amended limitation.
Therefore, all of the limitations of the independent claims are disclosed in Mahmoodpour or Zhang, and the combination of these references renders the claimed invention obvious. Thus, applicant’s arguments are not persuasive and rejection of independent claims as obvious over Zhang in view of Mahmoodpour is maintained.
Applicant’s arguments, see Pg. 9-15, filed October 15, 2025, with respect to the rejection(s) of claims 1-20 under 35 U.S.C. § 101 have been fully considered and are persuasive with regards to the amended independent claims having the limitation of “adjusting, via the downhole tool, the downhole operation along the wellbore within the reservoir formation based on the at least one estimated property” to integrate the claimed invention into a practical application. Therefore, the rejection has been withdrawn.
Applicant’s arguments, see Pg. 17-18, filed October 15, 2025, with respect to the rejection(s) of claims 1, 14, and 20 under 35 U.S.C. § 103 have been fully considered and are persuasive with regards to the amend claim limitations of “performing, via a downhole tool, a downhole operation along a wellbore drilled within a reservoir formation, wherein the downhole operation comprises at least collecting training data for modeling the reservoir formation surrounding the wellbore” and “receiving…during the course of the downhole operation”. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of the amended claims in the rejection above.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 7,657,494 B2 Wilkinson, David et al. teaches a method for utilizing genetic programming to construct history matching and forecasting proxies for reservoir simulators to evaluate a large number of reservoir models and predict future production forecasts for petroleum reservoirs.
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Examiner’s Note: The examiner has cited particular columns and line numbers in the reference that applied to the claims above for the convenience of the applicant. Although the specified citations are representative of the art and are applied to specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested from the applicant, to fully consider the references in their entirety as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by the prior art or disclosed by the examiner. In the case of amending the claimed invention, the applicant is respectfully requested to indicate the portion(s) of the specification which dictate(s) the structure relied on for the proper interpretation and also to verify and ascertain the metes and bound of the claimed invention.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Simeon P Drapeau whose telephone number is (571)-272-1173. The examiner can normally be reached Monday - Friday, 8 a.m. - 5 p.m. ET.
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 on (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.
/SIMEON P DRAPEAU/ Examiner, Art Unit 2188
/RYAN F PITARO/ Supervisory Patent Examiner, Art Unit 2188