DETAILED ACTION
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 .
Responses to Amendments and Arguments
The amendments filed 11/26/2025 have been entered. Claims 24 and 34 have been amended and claims 38 and 45 have been canceled. Claims 24-25, 28-31, 33-35, 39-41 and 43-44 remain pending.
Applicant's amendments filed 11/26/2025 have overcome the claim objection.
Applicant's amendments filed 11/26/2025 with respect to the rejection of Claim 45 under 35 U.S.C. 112(b) or 112 (pre-AIA ), 2nd paragraph have been fully considered and are persuasive. Thus, the rejections of claims 223-242 under 35 U.S.C. 112(b) or 112 (pre-AIA ), 2nd paragraph have been withdrawn.
Applicant's amendments and arguments filed 11/26/2025 with respect to the rejection of claims 24-25, 28-31, 33-34, 38-41 and 43 under 35 U.S.C. 103 have been fully considered but are not persuasive.
On pages 9-11 of the Remarks, Applicant alleges that the combination of Fredrich and SUNGKORN fails to teach or suggest the specific dual-path parallel processing architecture now recited by the amended independent claims
by stating that
the claimed limitation establishes a specific dual-path parallel processing architecture
that is not taught or suggested by the combination of Fredrich and SUNGKORN. Fredrich teaches only a single testing tool 130 … Fredrich's approach relies on sequential numerical methods and does not disclose or suggest parallel extraction of different types of features that are then combined. … Fredrich does not teach or suggest this parallel dual-path architecture where traditional feature extraction and deep learning vector representation occur simultaneously and are then combined. … SUNGKORN's texture analysis approach is fundamentally different from the claimed
petrophysical property estimation and is directed toward classification and identification rather than quantitative petrophysical property determination. … SUNGKORN does not teach or suggest combining its deep learning texture analysis approach with traditional 00TB feature extraction in a parallel workflow for petrophysical analysis. SUNGKORN's method is directed toward creating texture classification and formation characterization, not toward the quantitative estimation of petrophysical properties like porosity and permeability as recited by the amended claims. …. The combination of Fredrich and SUNG KORN fails to teach or suggest the specific parallel dual-path workflow recited by amended claims 24 and 34, where traditional 00TB feature extraction and deep learning vector representation are performed simultaneously on the same captured image, and where the different types of outputs are combined and provided to a neural network for quantitative petrophysical property estimation at the specified resolution range. The combination of Fredrich and SUNG KORN also fails to teach or suggest the use of
low-resolution medical CT images having a resolution in the range of 100 to 500 micrometers.
Examiner respectfully disagrees.
Under the broadest reasonable interpretation (BRI), the petrophysical properties of rock sample may be indicative of physical, geologic and/or chemical characteristics/formation such as different types of textures, as taught by Fredirick. Note that SUNGKORN teaches estimating/analyzing petrophysical property of a rock sample using a deep learning model. At least Abstract, Figs. 4-5, paragraphs 0027, 0040, 0067-0070 and 0071-0072 in SUNGKORN teach determining properties of subterranean/rock formations/textures and obtaining one or more vectors based on the captured textures of rocks (“determining properties of subterranean/rock formations/textures surrounding a wellbore in a manner of: receiving am image of receiving an image of a formation sample; partitioning the image into a plurality of patches; detecting, via a semantic extraction processor, textures captured in the plurality of patches; associating the textures to a location of the image of the formation sample; reducing a dimension of representation of the textures to obtain one or more vectors, the one or more vectors being based on the textures”). In other words, SUNGKORN teaches a neural network used for estimating or determining properties of a geologic formation sample (i.e., rock textures/formations) by performing deep learning over a captured image of the geologic formation sample to thereby provide a vector representation of the captured image. Under the broadest reasonable interpretation, the combination of the deep learning texture analysis approach along with traditional 00TB feature extraction as alleged may be “Obvious to try” to simply choose “testing tool 130 of computing device 120” of Fredrich along with a deep neural networks analysis, which taught by SUNGKORN, to thereby estimate/analyze a petrophysical property of a rock sample. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Fredrich’s feature extraction from the CT image to incorporate the teachings of SUNGKORN by providing the neural network for provides a vector representation of the captured image along with, or in parallel, the feature extraction engine (i.e., Fig. 1B, testing tool 130 of computing device 120) (see at least at Figs. 4-5, Abstract, paragraphs 0027, 0040, 0067-0070 and 0071-0072). If “dual-path parallel processing architecture” and/or “quantitative estimation of petrophysical properties” itself to process images through both an OOTB feature extractor and a deep feature extractor are key aspects for estimating process, as Applicant alleges, at a minimum the claims describe some specific features, structure and/or actions, for example, how and/or under what operations/features/structure the configuration of both OOTB feature extractor and the deep feature extractor in parallel provide analysis and process of the captured image. MPEP § 2145(VI). Accordingly, applicant’s arguments regarding the term “dual-path parallel processing architecture” and “quantitative estimation of petrophysical properties” are not persuasive and the rejection is maintained.
Regarding the remarks with respect to “capturing … at a resolution in the range of 100 micrometers to 500 micrometers”, under the broadest reasonable interpretation, note that the capturing resolution “in the range of 100 micrometers to 500 micrometers” may result in optimizing the resolution of the captured image and be determined in the realm of “routine optimization” or obviousness of similar and overlapping amounts resulted from preference or routine experimentation. Further, note that the capturing resolution “in the range of 100 micrometers to 500 micrometers” is not critical to be distinctly result-effective features but merely indicative of exemplary variable to estimate petrophysical property of a rock sample. (MEPE 2144.05 Obviousness of Ranges). Zang teaches a resolution range of Inter-Resolution Model by providing operations for capturing an image of the rock for throat aperture in the order of 100 nanometers, but length of 100 micrometers (Col. 24, lines 35-43 and Col. 8, lines 36-43). Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Fredrich in view of SUNGKORN to incorporate the teachings of Zhang’s exemplary resolution range of Inter-Resolution Model by providing operations for capturing an image of the rock at a resolution in a range of 100 micrometers to 500 micrometers, which is simply substituted from the Zhang’s exemplary resolution range of Inter-Resolution Model, taught by Zhang at least at Col. 24, lines 35-43 and Col. 8, lines 36-43. Accordingly, applicant’s arguments regarding the term “capturing … at a resolution in the range of 100 micrometers to 500 micrometers” are not persuasive and the rejection is maintained.
Claim Rejections - 35 USC § 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.
Claims 24-25, 28-31, 33-34, 38-41 and 43-44 are rejected under 35 U.S.C. 103 as being unpatentable over Fredrich et al. (US 20150043787 A1, hereinafter referred to as “Fredrich”) in view of SUNGKORN et al. (US 20200225177 A1, hereinafter referred to as “SUNGKORN”) and further in view of Zhang (US 10830713 B2, hereinafter referred to as “Zhang”).
Regarding Claim 24, Fredrich teaches a method of detecting a plurality of petrophysical properties of an uncleaned rock sample (Fig. 1B; Para 0003, “methods and systems for analyzing images of rock samples to determine petrophysical properties”), the method comprising the steps of:
capturing a medical CT image of the uncleaned rock sample at a resolution in the range of … (Fig. 1B and Para 0038 teaches imaging device 122 (CT scanner 122) configured to generate an image of interior structure and constituents of a rock sample) (Para 0038, “testing system 102 includes imaging device 122 for obtaining two-dimensional (2D) or three-dimensional (3D) images, …, of rock samples 104 ….An example of imaging device 122 is a X-ray computed tomography (CT) scanner … such as a micro CT scanner”);
passing the captured image through a feature extraction engine (Fig. 1B, testing tool 130 of computing device 120) (Para 0040, “imaging device 122 forwards images 128 to computing device 120”) comprising an Out of the Box (OOTB) feature extractor, wherein the OOTB feature extractor extracts features comprising porosity of the cleaned rock sample, pore volume distributions of the cleaned rock sample and pore size distributions of the cleaned rock sample (Para 0067, “These petrophysical properties may be estimated using an appropriate discretization of the deformed volume combined with appropriate numerical simulation, e.g. the direct numerical simulation of single phase fluid flow for computation of absolute permeability”; Para 0075, “testing tool 130 applies the desired numerical algorithm to compute the petrophysical properties”; Para 0076-0081, “by computing device 120 and testing tool 130 is a computation of absolute permeability of rock sample 104 … using other techniques such as finite difference, finite volume, Lattice-Boltzmann, network modeling, and the like to compute those properties as well as absolute permeability”; Note that the Out of the Box (OOTB) feature extractor may be indicative of functional entities used for extracting features comprising porosity, pore volume distributions and pore size distributions of rock sample and computing permeability of the uncleaned porous medium using an algorithm (see paragraphs 0033 and 0034 in the instant application). Therefore, under the broadest reasonable interpretation, Para 0067, 0075, 0076-0081 of Fredrich teaches testing tool 130 to compute/calculate permeability using an algorithm and/or network modeling);
passing the captured image through a deep feature extractor in parallel to passing the captured image through the feature extraction engine (Fig. 1B, testing tool 130 of computing device 120) (Para 0040, “imaging device 122 forwards images 128 to computing device 120”), the deep feature extractor comprising a deep neural network that provides a vector representation of the captured image;
providing an output from the feature extraction engine and the vector representation to a neural network (Fig. 1C, network interfaces 908) for estimating the petrophysical properties of the uncleaned rock sample (Para 0040, “these hardware and software components of computing device 120 include testing tool 130 that is configured to analyze images 128 to determine the petrophysical properties of rock sample 104 under one or more simulated deformation conditions, including stress and strain conditions that may be encountered by rock formations in the sub-surface … testing tool 130 is configured to analyze image volume 128 of rock sample 104 to perform numerical simulation of the petrophysical properties”); and
displaying the estimated petrophysical properties of the uncleaned rock sample on a display medium (Fig. 1C, peripheral interfaces 906; Para 0041, “One or more peripheral interfaces 906 are provided for coupling to corresponding peripheral devices such as displays”; Para 0044, “for display or output by peripherals coupled to computing device 120”; Note that, under the broadest reasonable interpretation, Figs. 3A – 4F teach petrophysical properties of the rock sample which are displayed or output on a display of peripheral interfaces 906).
Fredrich fails to explicitly teach the deep feature extractor comprising a deep neural network that provides a vector representation of the captured image. However, SUNGKORN teaches the deep feature extractor comprising a deep neural network (Fig. 5, a neural network 510) that provides a vector representation of the captured image. (Abstract; Figs. 4-5; Para 0027, “deep neural networks to extract semantic representations of textures, which can then be classified according to rock type, then simplified into vector components representing different types of textures …”; Para 0071-0072, “the extracted semantic representation of a texture and the extracted texture's associated vector, such as those output by output layer 506 of FIG. 5”; Para 0067-0070).
Fredrich and SUNGKORN are both considered to be analogous to the claimed invention because they are in the same field of analyzing images of rock samples and properties of subterranean formations. Under the broadest reasonable interpretation (BRI), the petrophysical properties of rock sample may be indicative of physical, geologic and/or chemical characteristics/formation such as different types of textures. Note that SUNGKORN teaches estimating/analyzing petrophysical property of a rock sample using a deep learning model, and determining properties of subterranean/rock formations/textures and obtaining one or more vectors based on the captured textures of rocks. In other words, SUNGKORN teaches a neural network used for estimating or determining properties of a geologic formation sample (i.e., rock textures/formations) by performing deep learning over a captured image of the geologic formation sample to thereby provide a vector representation of the captured image. Under the broadest reasonable interpretation, the combination of the deep learning texture analysis approach along with traditional 00TB feature extraction as alleged may be “Obvious to try” to simply choose “testing tool 130 of computing device 120” of Fredrich along with a deep neural networks analysis, which taught by SUNGKORN, to thereby estimate/analyze a petrophysical property of a rock sample. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Fredrich’s feature extraction from the CT image to incorporate the teachings of SUNGKORN by providing the neural network for provides a vector representation of the captured image along with, or in parallel, the feature extraction engine (i.e., Fig. 1B, testing tool 130 of computing device 120), taught by SUNGKORN at least at Abstract, Figs. 4-5, paragraphs 0027, 0040, 0067-0070 and 0071-0072.
Fredrich in view of SUNGKORN fails to explicitly teach capturing … at a resolution in the range of 100 micrometers to 500 micrometers. However, Zhang teaches capturing … at a resolution in the range of 100 micrometers to 500 micrometers (Col. 24, lines 35-43, “E. Inter-Resolution Model … Micro-porosity domains are connected by small fractures, which can have throat aperture in the order of 100 nanometers, but length of 100 micrometers …”; Col. 8, lines 36-43, “Type 2, porous microstructure REV is captured with MicroCT at low resolution, while two fractal micro-porosity are captured with FIB-SEM at high (b.1) and intermediate resolution (b.2). (c).”).
Zhang is considered to be analogous to the claimed invention because it is in the same field of computing physical Properties of materials using imaging data. Under the broadest reasonable interpretation, note that the capturing resolution “in the range of 100 micrometers to 500 micrometers” may result in optimizing the resolution of the captured image and be determined in the realm of “routine optimization” or obviousness of similar and overlapping amounts resulted from preference or routine experimentation. Further note that the capturing resolution “in the range of 100 micrometers to 500 micrometers” is not critical to be distinctly result-effective features but merely indicative of exemplary variable to estimate petrophysical property of a rock sample. (MEPE 2144.05 Obviousness of Ranges). Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Fredrich in view of SUNGKORN to incorporate the teachings of Zhang’s exemplary resolution range of Inter-Resolution Model by providing operations for capturing an image of the rock at a resolution in a range of 100 micrometers to 500 micrometers, which is simply substituted from the Zhang’s exemplary resolution range of Inter-Resolution Model, taught by Zhang at least at Col. 24, lines 35-43 and Col. 8, lines 36-43.
Regarding Claim 25, Fredrich teaches wherein the image of the uncleaned rock sample is a three-dimensional (3D) image (Para 0038, “testing system 102 includes imaging device 122 for obtaining two-dimensional (2D) or three-dimensional (3D) images, as well as other representations, of rock samples 104”).
Regarding Claim 28, Fredrich teaches wherein the micro-CT image is
captured from a core-flooding equipment (Para 0075, “Lattice-Boltzmann (LB) models) through a fluid displacement test (Para 0075, testing tool 133) (Para 0009, “a three-dimensional tomographic image of the rock sample is obtained, for example by way of a computer tomographic (CT) scan. ... Numerical simulation of fluid flow or”; Para 0067, “These petrophysical properties may be estimated using an appropriate discretization of the deformed volume combined with appropriate numerical simulation, e.g. the direct numerical simulation of single phase fluid flow for computation of absolute permeability”; Para 0075, “testing tool 130 applies the desired numerical algorithm to compute the petrophysical properties, in process 422. For example, following the conversion into structured grids in process 420, computing device 120 (executing testing tool 130) may utilize existing Lattice-Boltzmann (LB) models to simulate single phase fluid flow in the pore space”).
Regarding Claim 29, Fredrich teaches wherein the petrophysical properties
comprise porosity, permeability, elastic property, relative permeability or capillary pressure (Para 0009, “estimating physical properties, such as porosity, absolute permeability, relative permeability, formation factor, elastic moduli, and the like of rock samples”; Para 0067, “petrophysical properties of interest such as porosity, formation factor, absolute and relative permeability, electrical properties (such as formation factor, cementation exponent, saturation exponent, tortuosity factor), capillary pressure properties”).
Regarding Claim 30, Fredrich teaches wherein the feature extraction engine
is a porosity-permeability predictor engine (testing tool 130) (Para 0070-0071, “Examples of such porosity-correlated properties include permeability, formation factor. In process 414, testing tool 130 estimates one or more of these correlated properties from the porosity calculated in process 412”).
Regarding Claim 31, Fredrich teaches wherein the feature extraction engine comprise a pore network correction engine (PNCE) (testing tool 130) (Para 0067, “These petrophysical properties may be estimated using an appropriate discretization of the deformed volume combined with appropriate numerical simulation, e.g. the direct numerical simulation of single phase fluid flow for computation of absolute permeability”; Para 0075, “testing tool 130 applies the desired numerical algorithm to compute the petrophysical properties”; Para 0076-0081, “by computing device 120 and testing tool 130 is a computation of absolute permeability of rock sample 104 … using other techniques such as finite difference, finite volume, Lattice-Boltzmann, network modeling, and the like to compute those properties as well as absolute permeability”). Note that the pore network Correction Engine (PNCE) may be indicative of functional entities used for extracting features comprising porosity, pore volume distributions and pore size distributions of rock sample and computing permeability of the uncleaned porous medium using an algorithm (see paragraphs 0033 and 0034 in the instant application). Therefore, under the broadest reasonable interpretation, Para 0067, 0075, 0076-0081 of Fredrich teaches testing tool 130 to compute/calculate permeability using an algorithm and/or network modeling.
Regarding Claim 33, Fredrich teaches wherein the pore network Correction
Engine (PNCE) computes permeability of the uncleaned rock sample using a machine-learning algorithm (Para 0067, “These petrophysical properties may be estimated using an appropriate discretization of the deformed volume combined with appropriate numerical simulation, e.g. the direct numerical simulation of single phase fluid flow for computation of absolute permeability”; Para 0075, “testing tool 130 applies the desired numerical algorithm to compute the petrophysical properties”; Para 0076-0081, “by computing device 120 and testing tool 130 is a computation of absolute permeability of rock sample 104 … using other techniques such as finite difference, finite volume, Lattice-Boltzmann, network modeling, and the like to compute those properties as well as absolute permeability”). Note that, under the broadest reasonable interpretation, Para 0067, 0075, 0076-0081 of Fredrich teaches testing tool 130 to compute/calculate permeability using an algorithm and/or network modeling.
Regarding Claim 34, it is a process type claim having similar limitations as of claim 1 above. Therefore, it is rejected under the same rationale as of claim 1 above. The additional limitations of predicting phase saturation within a reservoir (Para 0050, “testing tool 130 is configured to segment image volume 128 into more than two significant elastic phases, representing such material constituents as pore space, clay fraction, quartz fraction, and other various mineral types”; Para 0067, “In the context of oil and gas exploration and production, petrophysical properties of interest such as porosity, formation factor, absolute and relative permeability, electrical properties (such as formation factor, cementation exponent, saturation exponent, tortuosity factor), capillary pressure properties (such as mercury capillary injection)”; Claim 13), a porous medium (Para 0003, “rock samples”), and wherein estimating the petrophysical properties of the porous medium leads to prediction of the saturation of oil within the reservoir (Para 0071, “The porosity value and any such correlated petrophysical properties are then stored in a memory resource of computing device 120 or a networked memory resource, as desired, for use in further analysis of the reservoir in the conventional manner”; Para 0082; Para 0088).
Regarding Claim 35, it is dependent on claim 34 and has similar limitations as of claim 25 above. Therefore, it is rejected under the same rationale as of claim 25 above.
Regarding Claim 39, it is dependent on claim 34 and has similar limitations as of claim 29 above. Therefore, it is rejected under the same rationale as of claim 29 above.
Regarding Claim 40, it is dependent on claim 34 and has similar limitations as of claim 30 above. Therefore, it is rejected under the same rationale as of claim 30 above.
Regarding Claim 41, it is dependent on claim 40 and has similar limitations as of claim 31 above. Therefore, it is rejected under the same rationale as of claim 31 above.
Regarding Claim 43, it is dependent on claim 41 and has similar limitations as of claim 33 above. Therefore, it is rejected under the same rationale as of claim 33 above.
Regarding Claim 44, Fredrich teaches wherein the step of providing an output from the feature extraction engine and the vector representation to a neural network for estimating the petrophysical properties of the uncleaned rock sample further comprises
providing an output from the feature extraction engine and the vector representation to a neural network for estimating the petrophysical properties of the uncleaned rock sample … as presented above in the rationale of Claim 24. Regarding the limitation of “for an actual core plug measuring 1.5 inches in diameter”, Fredrich teaches a drilling core sample to measure petrophysical properties in pore throat diameter (Para 0004, “Traditionally, samples of the rock formation, such as from core samples or drilling cuttings, are subjected to physical laboratory tests to measure petrophysical properties such as permeability, porosity, formation factor, elastic moduli, and the like”; Para 0084, “Examples of these geometrical properties include measures such as surface-to-volume ratio of the grains or pores, the critical pore throat diameter recoverable from topological measures extracted from a deformed volumetric mesh of the pore space”). However, Fredrich does not explicitly teach wherein the core plug measures 1.5 inches in diameter. It has been held that "[W]here the general conditions of a claim are disclosed in the prior art, it is not inventive to discover the optimum or workable ranges by routine experimentation." In re Aller, 220 F.2d 454, 456, 105 USPQ 233, 235 (CCPA 1955).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the pore throat diameter taught by Fredrich to be in the claimed diameter in order to estimate the petrophysical properties of the rock sample as per a user’s interest and routine experimentation.
Citation of Pertinent Art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
KHODJA et al. (US 20210116354 A1) teaches scanning estimating a permeability of a carbonate rock using low and high resolutions X-ray scanning within a range of 25 cubic micrometers (μm.sup.3)-35 μm.sup.3, 28 μm.sup.3-32 μm.sup.3, with a preferable voxel volume of 30 μm.sup.3. (Para 0050-0051 and 0061).
Conclusion
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.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BYUNG RO LEE whose telephone number is (571)272-3707. The examiner can normally be reached on Monday-Friday 8:30am-4:00pm.
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, Lee Rodak can be reached on (571) 270-5628. The fax phone number for the organization where this application or proceeding is assigned is 571-273-2555.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see https://ppair-my.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/BYUNG RO LEE/Examiner, Art Unit 2858
/LEE E RODAK/Supervisory Patent Examiner, Art Unit 2858