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 .
Specification
The title of the invention is not descriptive. A new title is required that is clearly indicative of the invention to which the claims are directed.
The following title is suggested: "Hybrid Physics-Based Simulation and Machine Learning Forecasting of Hydrocarbon Production Using Decline Curve Analysis and Estimated Ultimate Recovery"
The disclosure is objected to because of the following informalities: (1) the specification refers to the same element as both a "synthetic database" (¶[0003], [0007], [0008]) and a "universal database" (¶[0022], [0029], [0031], [0032], [0036]) without indicating that the terms are used interchangeably; (2) ¶[0039] recites "method 204" where "method 200" is intended, consistent with ¶[0037], [0038], [0040], and [0041]; (3) ¶[0037] incorrectly states that method 200 can be performed by computer system 900 "of FIG. 2," whereas computer system 900 is described in FIG. 9 (¶[0066]); (4) ¶[0034] recites "the hybrid obtains initial production data," which appears to omit a word (e.g., "the hybrid forecasting system"); and (5) ¶[0064] introduces "a settling pit 836, and a suction pit 838" but later refers to "the settling pit 836 to the suction pit 836," where the second occurrence should read "suction pit 838."
Appropriate correction is required.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitation(s) is/are: “an optimizer” that performs the function of “select[ing] a plurality of simulation scenarios described by the respective simulation data,” in claims 5, 12, and 19. Specifically, Claim 5 (and, identically, claims 12 and 19) recites, "using an optimizer to select a plurality of simulation scenarios described by the respective simulation data".
Claimed function: selecting a plurality of simulation scenarios described by the respective simulation data
Corresponding structure: None disclosed. The specification's only description of the optimizer is at ¶[0031] ("an optimizer that controls each simulation for the given parameters and ranges (e.g., time ranges)"), which restates the function; ¶[0007] and ¶[0044] repeat the claim language. No algorithm is disclosed, and the disclosed computing platform (FIG. 9; ¶ [0066], [0074]) is a general-purpose computer.
Interpretation: No 35 U.S.C. 112(f) construction can be reached because no corresponding structure is disclosed. For purposes of applying prior art, the limitation is treated as reading on any structure that performs the recited function.
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Written Description
Claims 1-20 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
Per claims 1, 8, and 15, each recite identical operative limitations and are addressed together. Two limitations lack written description support.
(A) Generating the target DCA from the input parameters. Each of claims 1, 8, and 15 recites “generating, based on the input parameters, a target DCA for the target wellbore that forecasts the decline curve for the target wellbore”, where the “input parameters” are those obtained in the first recited step as “describing a target wellbore for hydrocarbon production analysis.” The specification identifies those parameters as static reservoir, completion, and stimulation properties: “porosity, permeability, frac conductivity, number of stages, fracture length, fracture height, hydrocarbon saturation, cluster spacing, stage spacing, and reservoir pressure” (¶[0028]), repeated for the target case at ¶[0032], and recited as a closed list in claims 2, 9, and 16. None of these is production-rate-versus-time data.
However, every substantive passage in which the specification actually produces a target DCA produces it from initial production data, not from those parameters. At ¶[0034]: “the hybrid obtains initial production data, e.g., gas rate in million standard cubic feet per day (MSCFD), for the target case. The initial production data can include the gas rate for a specified period, e.g., 30 days, 60 days, 180 days, or 360 days. The computer system then applies a predictive analysis to the initial production data. For instance, the computer system applies DCA to the initial production data. Applying DCA can involve determining a decline curve, e.g., exponential decline, harmonic decline, or hyperbolic decline, that can be used to fit the data points of the initial production data.” The same is true at ¶[0040], which states that the step “involves plotting production rates against time and applying forecasting techniques (e.g., curve fitting to the plotted data),” and at ¶[0050] with FIGS. 5A–5C, where the disclosed forecasts are fitted to 30-day, 180-day, and 360-day windows of production data.
The specification therefore discloses generating a target DCA from production history, while the claims require generating it from static formation and completion properties. No passage discloses any correlation, type curve, transfer function, or model by which a decline-curve forecast is obtained from porosity, permeability, frac conductivity, stage count, fracture geometry, hydrocarbon saturation, spacing, or reservoir pressure. The only recitations matching the claim language are at ¶[0003] and ¶¶[0038]–[0041], each of which restates the claim step verbatim without describing how it is performed. The specification accordingly fails to convey to one of ordinary skill in the art that the inventors had possession of the claimed parameters-to-DCA relationship at the time of filing. See MPEP § 2163.
(B) The machine learning model. Each of claims 1, 8, and 15 further recites “generating, based on the input parameters and a synthetic database of a plurality of simulated decline curve analysis (DCA) - estimated ultimate recovery (EUR) sets, a machine learning model for generating a target EUR for the target wellbore” and “providing the target DCA as input to the machine learning model, wherein the machine learning model outputs the target EUR for the target wellbore.”
The specification recites the result these steps are to achieve but discloses no algorithm by which they are achieved. At ¶[0032], the specification states only that “the computer system uses the parameters and data from the universal database to train a machine learning model tailored to the target case.” At ¶[0033], it adds that “the generated database is utilized by a ML algorithm to establish the relationship between the inputs and the outputs. Then, the ML model is generated by fitting the relationship, e.g., adjusting the model’s parameters so that it can accurately predict the output (or target) from the input data,” followed by a list of algorithm family names: “Artificial Neural Networks, Genetic Algorithms, random forests, support vectors machines, generative adversarial networks, among other examples.” At ¶[0035], it states that “the machine learning model can use its training to identify a EUR that corresponds to the DCA.”
These passages describe supervised learning in the abstract and name algorithm families; they do not describe the claimed invention. The specification does not disclose how a decline curve — a fitted function, or a series of rate-versus-time points — is represented so as to serve as an input to the model; what the model’s output variable is or how it is mapped to an EUR; any architecture, layer count, kernel, tree count, or hyperparameter for any of the five named families; any training, validation, or convergence criterion; any error or loss metric; or what it means for a model to be “tailored to the target case.” For a computer-implemented invention, the specification must disclose the algorithm — by flowchart, step-by-step prose, or mathematical formula — that performs the claimed function; a statement that a model “uses its training” to produce the claimed output discloses only the desired result. See Vasudevan Software, Inc. v. MicroStrategy, Inc., 782 F.3d 671, 681-82 (Fed. Cir. 2015); MPEP § 2163.
Considered as a genus, the recited “machine learning model” is defined solely by the function it performs. The specification names five disparate algorithm families and expressly leaves the list open (“among other examples”), but applies none of them, discloses no implemented species, and identifies no structural feature common to the genus that would allow a person of ordinary skill to visualize or recognize its members. A genus claimed by function alone, without representative species or common structural features, is not adequately described. See Abbvie Deutschland GmbH & Co. v. Janssen Biotech, Inc., 759 F.3d 1285, 1300-01 (Fed. Cir. 2014); Ariad Pharmaceuticals, Inc. v. Eli Lilly & Co., 598 F.3d 1336, 1351 (Fed. Cir. 2010) (en banc); MPEP § 2163.
The sole example in the specification does not supply what is missing. FIGS. 3A-6E are described in four caption-length at ¶¶[0047]-[0050]: a single-well synthetic shale model at five permeability multiples (FIGS. 3A-3C, 4A-4E), decline curve forecasts fitted to 30-, 180-, and 360-day data windows (FIGS. 5A-5C), and actual-versus-predicted gas rate plots (FIGS. 6A-6E). The predicted traces in FIGS. 6A-6E are labeled by data window — “qg prediction well 1 (data-30),” “(data-60),” “(data-180),” “(data-360)” — identifying them as decline-curve extrapolations from differing lengths of production history rather than outputs of any machine learning model. No figure and no passage discloses the contents or size of the synthetic database, the training of a machine learning model, any EUR value output by such a model, or any accuracy value.
Per claims 5, 12, and 19, in addition to the deficiencies inherited from claims 1, 8, and 15, each of claims 5, 12, and 19 recites “using an optimizer to select a plurality of simulation scenarios described by the respective simulation data.” Outside the verbatim restatements of this limitation at ¶[0007] and ¶[0044], the specification refers to an optimizer exactly once, at ¶[0031]: “The process is then repeated (e.g., on the order of tens or hundreds of thousands of times) to capture different input parameter combinations using an optimizer that controls each simulation for the given parameters and ranges (e.g., time ranges) to generate the universal database.”
That sentence ascribes to the optimizer a function different from the one claimed. The specification’s optimizer controls the execution of simulations for parameters and ranges already given; the claim requires an optimizer that selects which simulation scenarios are to be run. The specification does not disclose what the optimizer optimizes, what objective or cost function it evaluates, what constraints or parameter ranges bound its search, what sampling or design-of-experiments scheme it applies, or how its selection terminates — across a process the same paragraph states is repeated “on the order of tens or hundreds of thousands of times.” The only scenario set the specification exhibits, the five-point permeability sweep of ¶[0047] (1x, 5x, 10x, 25x, and 100x, corresponding to 10, 50, 100, 250, and 1000 nanodarcy), is enumerated by hand, with nothing to indicate it was produced by an optimizer.
Possession of the claimed scenario-selecting optimizer is therefore not conveyed. See MPEP § 2163.
Claims 2-4, 6, 7, 9-11, 13, 14, 16-18, and 20 are rejected as depending from, and therefore incorporating every limitation of, a claim rejected above. The limitations these claims add do not cure the deficiencies of the claims from which they depend.
Claims 2, 9, and 16 aggravate rather than cure deficiency (A): by confining the “input parameters” to a closed list of static formation and completion properties, they foreclose any reading under which those parameters could encompass the initial production data from which ¶[0034] actually generates the target DCA.
Claims 6, 13, and 20 further incorporate the undescribed optimizer of claims 5, 12, and 19, because the recited “for each simulation scenario” presupposes the scenario set that optimizer selects.
It is noted that the limitations added by claims 3, 10, and 17 (identifying a subset of the simulated DCA-EUR sets by comparison score against a predetermined threshold — ¶[0006]; ¶[0043]), by claims 4, 11, and 18 (generating the synthetic database with a physics-based reservoir simulator — ¶[0029]; ¶[0031]), by claims 6, 13, and 20 (calculating an EUR accuracy by continuing the simulation to a predetermined stopping point and comparing the simulated ultimate recovery to the expected ultimate recovery — ¶[0030]), and by claims 7 and 14 (adopting the accuracy of the most similar stored DCA-EUR set as the accuracy of the target —¶[0035]) are, considered in isolation, adequately described. Those claims are rejected solely because of the limitations they incorporate from claims 1, 8, and 15, and, in the case of claims 6, 13, and 20, from claims 5, 12, and 19.
It is acknowledged that claims 1-20 were present in the application as filed, and that claims as originally filed form part of the original disclosure and may constitute their own written description. That presumption is rebuttable, and is rebutted here. See In re Koller, 613 F.2d 819, 823 (CCPA 1980); MPEP § 2163(I)(B). The passages of the specification that recite the deficient limitations — ¶¶[0003] and [0007]; ¶¶[0038]-[0041]; ¶[0044] — restate the claim language word for word and add no description of how the recited operations are carried out. The substantive disclosure, at ¶¶[0028]-[0035], is narrower than what is claimed and, as to the generation of the target DCA, is inconsistent with it. A description that merely repeats the claim, or that states a result without describing the means of achieving it, does not convey possession of the claimed invention. See Ariad, 598 F.3d at 1349-51; MPEP § 2163.
Enablement
Claims 1-20 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the enablement requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to enable one skilled in the art to which it pertains, or with which it is most nearly connected, to make and/or use the invention.
The factors to be considered in determining whether a disclosure meets the enablement requirement of 35 U.S.C. 112(a) have been described in In re Wands, 858 F.2d 731, 737 (Fed. Cir. 1988). See MPEP § 2164.01. Those factors are applied below to claims 1, 8, and 15, whose operative limitations are identical, and to the claims depending therefrom.
(1) Breadth of the claims: Claims 1, 8, and 15 read on any machine learning model, generated from any synthetic database of two or more simulated DCA-EUR sets, for any target wellbore in any hydrocarbon reservoir, using any technique for producing the target DCA, with the “input parameters” bounded only by the requirement that they describe the target wellbore. The full scope includes producing a decline-curve forecast from static reservoir and completion properties alone, and includes each of the five algorithm families named at ¶[0033] together with the open-ended “among other examples.” Claims 5, 12, and 19 add an optimizer bounded only by the function of selecting simulation scenarios. The breadth to be enabled is accordingly very great, and greater breadth requires a correspondingly greater enabling disclosure.
(2) Nature of the invention: The invention is a coupled workflow in which a full-physics reservoir simulator generates a training corpus that a machine learning model then consumes in order to forecast estimated ultimate recovery, and the uncertainty in that forecast, from limited early production data (¶[0022). The specification presents this coupling as the advance over the prior art: it states that “existing methods face difficulty in forecasting well performance with limited initial data, which may generally range from 30 days to 360 days, especially for unconventional reservoirs,” and that “existing methods do not provide an accurate assessment of uncertainty in the calculated EUR” (¶[0021]). The subject matter left undescribed is thus the asserted advance itself, not peripheral detail.
(3) State of the prior art: The constituent techniques were well developed as of the effective filing date, and the specification says so. Decline curve analysis, including Arps’ empirical model, Fetkovich type curves, and segmental analysis for unconventional reservoirs, is described as known at ¶¶[0017]-[0018]. Physics-based reservoir and fracture-propagation simulation is described as known at ¶¶[0025]-[0026] and ¶[0031]. The named machine learning algorithm families are described as known at ¶[0033]. A person having ordinary skill could therefore practice each component in isolation. However, the prior art does not supply the two couplings the claims require: obtaining a decline-curve forecast from static reservoir and completion parameters, and representing a decline curve as the input to a model whose output is an EUR.
(4) Level of one of ordinary skill: A person of ordinary skill in this art is a reservoir or petroleum engineer holding an advanced degree, with working experience in numerical reservoir simulation, decline curve analysis, and applied machine learning.
(5) Level of predictability in the art: The computational arts are generally predictable in that a disclosed algorithm, once specified, behaves reproducibly. The particular question the claims address is not. Whether a model trained on simulator output will yield an accurate EUR, and an accurate uncertainty for that EUR, from 30 to 360 days of production data in ultra-low-permeability reservoirs is an empirical question, and the specification identifies it as the unsolved problem in the art (¶[0021]). The specification’s own example varies permeability across two orders of magnitude — 10 nanodarcy to 1000 nanodarcy — and reports that “SRV permeability alterations impact the production directly” (¶¶[0047], [0049]). Model selection and input representation cannot be presumed to transfer across that range without empirical validation, and none is reported.
(6) Amount of direction provided by the inventor: The direction supplied is block-level. ¶¶[0027]-[0035] and FIG. 1 walk through five numbered stages — 102 selecting global parameters, 104 generating the universal database, 106 generating the machine learning model, 108 applying predictive analytics, 110 forecasting the target EUR — and descend below the level of the stage name only for stages 102, 104, and 108. For the machine learning stages the specification does not disclose: how a decline curve is encoded as an input feature representation; what the model’s output variable is or how it maps to an EUR; any architecture, layer count, kernel, tree count, or hyperparameter for any named algorithm family; any training, cross-validation, or convergence criterion; any loss or error metric; or what is done to “tailor” the model to the target case beyond the assertion that it is tailored (¶[0032]). Nor does it disclose any algorithm for generating the target DCA from the recited input parameters, or any algorithm for the optimizer of claims 5, 12, and 19. The statement at ¶[0033] that the database “is utilized by a ML algorithm to establish the relationship between the inputs and the outputs” and that “the ML model is generated by fitting the relationship, e.g., adjusting the model’s parameters” is a definition of supervised learning, not direction specific to the claimed invention.
(7) Existence of working examples: The specification contains one example, FIGS. 3A-6E, described in four caption-length paragraphs at ¶¶[0047]-[0050]. It comprises a single-well synthetic shale model at five permeability multiples (FIGS. 3A-3C and 4A-4E), decline curve forecasts fitted to 30-, 180-, and 360-day data windows (FIGS. 5A-5C), and actual-versus-predicted gas rate plots (FIGS. 6A-6E). The predicted traces in FIGS. 6A-6E are labeled by data window — “qg prediction well 1 (data-30),” “(data-60),” “(data-180),” “(data-360)” — identifying them as decline-curve extrapolations from differing lengths of production history, that is, the output of stage 108, and not of the machine learning model of stages 106 and 110. No example discloses the contents or size of the synthetic database, the training of any machine learning model, any EUR value produced by such a model, any accuracy or uncertainty value, or any optimizer-selected scenario set. As to the limitations that carry the claims the disclosure is prophetic, and it is not identified as prophetic.
(8) Quantity of experimentation needed to make or use the invention: To practice the full scope of the claims a person having ordinary skill in the art would have to independently devise, and then empirically validate, at least the following: a technique for producing a decline-curve forecast for the target wellbore from static reservoir and completion parameters, for which the specification supplies no starting point; a feature representation of a decline curve suitable as input to a regression model; a model architecture, training protocol, and validation scheme, selected by trial across at least the five disparate algorithm families named at ¶[0033] and re-validated across the permeability range the specification’s own example shows to be determinative of well behavior; and, for claims 5, 12, and 19, a scenario-selection optimizer capable of populating a database over the “tens or hundreds of thousands” of full-physics simulation runs contemplated at ¶[0031]. That is open-ended research directed at the very problem the specification identifies as unsolved in the prior art. It is not the routine filling-in of implementation detail that a person of ordinary skill may be expected to supply.
Considering the above factors, the specification does not enable a person of ordinary skill in the art to make and use the full scope of the claimed invention without undue experimentation. Factors (6) and (7) weigh most heavily against enablement: the specification provides no direction for the machine learning steps beyond naming algorithm families, and contains no working example in which a machine learning model is trained or in which a target EUR or its accuracy is produced. Factors (1), (2), (5), and (8) reinforce that conclusion. Factors (3) and (4) weigh in favor and are sufficient to enable a person of ordinary skill to run a physics-based reservoir simulator and to fit a decline curve to production data — but not to supply the two mechanisms the claims require and the specification omits, namely producing a target DCA from the recited input parameters and producing a target EUR by supplying a DCA to a machine learning model. The scope of the enabling disclosure is therefore materially narrower than the scope of the claims. See Amgen Inc. v. Sanofi, 598 U.S. 594, 610-14 (2023); Liebel-Flarsheim Co. v. Medrad, Inc., 481 F.3d 1371, 1379-80 (Fed. Cir. 2007); AK Steel Corp. v. Sollac, 344 F.3d 1234, 1244 (Fed. Cir. 2003); MPEP §§ 2164.01, 2164.08.
Claims 2-7, 9-14, and 16-20 are rejected for the same reasons, as each incorporates every limitation of the independent claim from which it depends and none narrows the claim to the enabled portion of the disclosure. Claims 5, 12, and 19 are additionally not enabled as to the recited optimizer, for which the specification supplies no objective, constraint set, sampling strategy, or stopping criterion, and no working example.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 2, 5, 6, 9, 12, 13 16, 19 and 20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claims 2, 9, and 16 each recite "a porosity of a reservoir in which the wellbore is drilled." There is insufficient antecedent basis for "the wellbore" in these claims. Claims 1, 8, and 15, respectively, from which claims 2, 9, and 16 depend, introduce only "a target wellbore," not "a wellbore." For purposes of examination, "the wellbore" is interpreted under BRI to refer to the previously-recited "target wellbore".
Claims 2, 9, and 16 each recite that the input parameters "comprises" a list of ten items joined by a single "or" before the final item. It is unclear whether the input parameters must include all of the listed items, only one, or some subset/combination, rendering the scope of the limitation uncertain. For purposes of examination, the limitation is interpreted under BRI to require that the input parameters comprise at least one of the recited items, as the specification at ¶[0032] describes these parameters as non-exhaustive examples ("include, but are not limited to") selected depending on the target case's specifications, indicating the list identifies alternative candidate parameters rather than a mandatory conjunctive set.
Claims 5, 12, and 19 each recite the limitation "using an optimizer to select a plurality of simulation scenarios described by the respective simulation data." This limitation invokes 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph: "optimizer" is a generic placeholder that is coupled with the functional language "to select a plurality of simulation scenarios described by the respective simulation data," is not preceded by a structural modifier, and is not accompanied by any recitation of sufficient structure for performing that function.
The claimed function is selecting a plurality of simulation scenarios described by the respective simulation data. This is a specialized computer-implemented function, not one coextensive with the inherent capability of a general-purpose computer, so an algorithm must be disclosed. In re Katz Interactive Call Processing Patent Litigation, 639 F.3d 1303, 1316 (Fed. Cir. 2011).
The written description fails to disclose the corresponding structure, material, or acts for performing the entire claimed function, and fails to clearly link any structure, material, or acts to that function. The specification's only reference to the optimizer beyond a restatement of the claim is at ¶[0031], which states that the simulation process "is then repeated (e.g., on the order of tens or hundreds of thousands of times) to capture different input parameter combinations using an optimizer that controls each simulation for the given parameters and ranges (e.g., time ranges) to generate the universal database." This describes the result to be achieved, not a procedure for achieving it: no objective or fitness function, sampling or search procedure, design-of-experiments scheme, constraint set, or convergence criterion is disclosed. Then at ¶[0007] and [0044] repeat the claim language verbatim. FIG. 1 and FIG. 2 contain no optimizer block, and ¶[0028]–[0029] attribute the selection of global parameters to "the computer system" generally. The genetic algorithms named at ¶[0033] are disclosed as candidate machine learning algorithms for generating the machine learning model at FIG. 1 step 106, a different function, and are not linked to scenario selection; structure not clearly linked to the claimed function cannot serve as corresponding structure. B. Braun Medical, Inc. v. Abbott Laboratories, 124 F.3d 1419, 1424 (Fed. Cir. 1997).
The specification therefore discloses, at most, a general-purpose computer for performing the claimed function. Simply reciting that a computer performs the function is not adequate. See MPEP § 2181, subsection IV; Aristocrat Technologies Australia Pty Ltd. v. Int'l Game Technology, 521 F.3d 1328, 1333 (Fed. Cir. 2008); Williamson v. Citrix Online, LLC, 792 F.3d 1339, 1351-52 (Fed. Cir. 2015) (en banc).
Accordingly, claims 5, 12 and 19 are indefinite and are rejected under 35 U.S.C. 112(b) or pre-AIA 35 U.S.C. 112, second paragraph.
Claims 6, 13, and 20 depend from claims 5, 12, and 19 respectively and incorporate the limitation "using an optimizer to select a plurality of simulation scenarios described by the respective simulation data," which is interpreted under 35 U.S.C. 112(f) and for which no corresponding structure is disclosed. They are rejected as indefinite for the same reason, by virtue of their dependency.
Appropriate correction is required.
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.
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 USC 103 as being unpatentable over US Pat. Pub. No. 2023/0111179 to Lam et al. (hereinafter Lam) in view of US Pat. Pub. No. 2021/0224669 to Chung et al. (hereinafter Chung).
Per claim 1, Lam discloses A computer-implemented method (Lam: ¶[0015]…Lam sets out a computerized method for determining well performance that a program carries out by processing data with machine learning and neural networks, which constitutes the computer-implemented method under BRI, "The present disclosure provides a computerized method for determining well performance, in which the program is capable of processing data using machine learning/neural network(s) to create deep learning models learning from pre-run simulations, to provide reliable production/reserves estimates") comprising:
obtaining input parameters describing a target wellbore for hydrocarbon production analysis (Lam: ¶[0068]…Lam receives, for the well the user wants analyzed, a request carrying that user-defined set of well parameters, which constitutes obtaining input parameters describing a target wellbore for hydrocarbon production analysis under BRI, "When a user wants to perform an analysis, a request is sent to the system with the user’s defined well parameters, well count, landing targets, vertical spacing and lateral spacing"; ¶[0054]…the specified parameters Lam collects are reservoir and completion attributes of the well under analysis and therefore describe the target wellbore for purposes of hydrocarbon production analysis, "Examples of specified parameters pertinent to the present disclosure include but are not limited to the following: initial reservoir pressure, reservoir depth, bottom-hole flowing pressure, bubble point pressure, dew point pressure, shear stress gradient, pressure gradient, reservoir temperature, reservoir thickness, oil density, gas gravity, rock matrix and natural fracture permeability, non-fracture zone matrix permeability multiplier, vertical and horizontal permeability multipliers, rock matrix/natural fracture porosity, natural fracture spacing, rock matrix/hydraulic fracture initial water saturation, water-oil contact depth, matrix/natural fracture compressibility, well lateral length, cluster spacing, well spacing, number of clusters, hydraulic fracture half-length/height/width/conductivity/permeability, number of fracture stages, hydraulic fracture compaction/relative permeability tables, and Pressure-Volume-Temperature (PVT) tables");
generating, based on the input parameters and a synthetic database of a plurality of simulated decline curve analysis (DCA) - estimated ultimate recovery (EUR) sets, a machine learning model for generating a target EUR for the target wellbore (Lam: ¶[0007]…Lam builds its machine learning and neural network model on pre-run numerical simulations rather than on measured field production, which constitutes generating the model based on a synthetic database under BRI, "The present disclosure relates to a method for predicting oil and gas reservoir production including a production analysis system using machine learning/neural network model(s) on pre-run numerical simulations for the evaluation of petroleum reservoir production performance"; ¶[0072]…the model Lam generates for the well under analysis is built from the stored simulated cases the system retrieves by matching the user-submitted parameter object, so the generation of the model is itself driven by the input parameters and not by the database at large, "The API reads through the object request, then finds the matching cases, and returns the matching cases to the software as a data file, such as a json file"; ¶[0109]…the simulation curves the reservoir simulator produces are downloaded into a database and that database is what supplies the training data for the neural network, which constitutes the synthetic database of simulated sets on which the machine learning model is generated, "The processor is also configured to download the plurality of simulation curves into a database to prepare training data for training the neural network model"; ¶[0064]…the output layer of Lam’s trained network emits EUR for the well under analysis, which constitutes a machine learning model for generating a target EUR for the target wellbore, "The training parameters are entered in an input layer, the input layer having up to 27 nodes representing up to 20 to 50 input features; an output layer having up to 359 nodes representing up to 359 months of EUR; and hidden layers to find the optimal number(s) of nodes in each of the layers"), wherein each of the plurality of simulated DCA-EUR sets comprises: (i) a simulated DCA generated based on respective simulation data, and (ii) a corresponding EUR for the simulated DCA (Lam: ¶[0084]…each stored simulation case is fitted to a decline curve model by adjusting decline curve parameters, so the database holds a simulated decline curve analysis derived from the simulation run that produced it, which constitutes a simulated DCA generated based on respective simulation data, "A plurality of decline curve models is created containing the outcome 215. The outcome from the plurality of matching simulation curves is matched to the plurality of decline curve models by adjusting a plurality of decline curve parameters 216"; ¶[0085]…Lam’s future-well flow likewise fits decline curve models to the simulation curves themselves by adjusting decline curve parameters, confirming that the decline curve stored for a case is generated from that case’s simulation data rather than from measured production, "A plurality of decline curve models is then created with the outcome 230. The plurality of simulation curves and the probabilistic type wells are matched to the plurality of decline curve models by adjusting a plurality of decline curve parameters 231"; ¶[0069]…each such case is retained in the database as a full 30-year simulated time series, confirming that the decline curve stored for a case is fitted to that case’s own simulation data, "Each simulated case is a 30 years’ time-series of information associated with a well saved in a database"; ¶[0056]…the wellsite parameters carried with each simulated case are what determine that case’s estimated ultimate recovery, so an EUR is paired with each simulated decline curve, which constitutes a corresponding EUR for the simulated DCA, "The various parameters include aforementioned actual wellsite parameters which are able to be selected for a single well or family of wells to determine the estimated ultimate recovery (EUR) of each well");
generating, based on the input parameters, a target DCA for the target wellbore that forecasts the decline curve for the target wellbore (Lam: ¶[0068]…Lam loads the model with the user-defined parameters for the well under analysis and then performs decline curve analysis on the result returned for that well, which constitutes generating a target DCA for the target wellbore based on the input parameters, "The model is loaded from the cloud server/virtual machine with the user’s defined parameters, and a result is returned. Decline curve analysis is performed on the result, where the curves are drawn using an application, such as Spotfire© referred to above"; ¶[0084]…the decline curve models Lam creates are fitted to that well by adjusting decline curve parameters and exported as the well’s forecast, which constitutes a target DCA that forecasts the decline curve for the target wellbore, "A plurality of decline curve models is created containing the outcome 215. The outcome from the plurality of matching simulation curves is matched to the plurality of decline curve models by adjusting a plurality of decline curve parameters 216"); and …
Lam does not expressly disclose, but Chung does teach:
…providing the target DCA as input to the machine learning model, wherein the machine learning model outputs the target EUR for the target wellbore, and wherein the target DCA and the target EUR form a target DCA-EUR set (Chung: ¶[0056]…Chung’s prediction modification engine takes the well’s predicted production decline curve as its input and applies machine learning techniques to it, which constitutes providing the target DCA as input to the machine learning model under BRI, "In still other examples of this description, the prediction modification engine 112 receives both the predicted production decline curve (e.g., from the production prediction engine 106) and the prediction accuracy metric (e.g., from the backtesting engine 108)…The prediction modification engine 112 may leverage machine learning techniques to improve the accuracy of the decline curves generated by the production prediction engine 106"; ¶[0058]…that machine learning technique returns the estimated ultimate recovery for the same well, and the returned EUR is thereafter carried with that same decline curve as a boundary condition on it, which constitutes the machine learning model outputting the target EUR and the target DCA and the target EUR forming a target DCA-EUR set, "For example, the prediction modification engine 112 may utilize a gradient boost decision tree machine learning technique to predict the EUR for a given well. This predicted EUR is then used as the additional boundary condition for wells with less than a certain amount of available historical production data (e.g., 24 months or less) to further improve the accuracy of the predicted decline curve generated by the production prediction engine 106").
Lam and Chung are analogous art because they are from the same field of endeavor, specifically computer-implemented forecasting of hydrocarbon well production and reserves using decline curve analysis and machine learning. Each is also reasonably pertinent to the same problem with which the inventor was involved, namely obtaining a reliable estimated ultimate recovery for a well whose own production history is too short to support a conventional decline curve extrapolation.
Before the effective filing date of the claimed invention, it would have been obvious to a PHOSITA to feed the decline curve analysis that Lam performs for the well under analysis back into Lam’s trained neural network model so that the model returns the estimated ultimate recovery for that well, as claim 1 recites.
The suggestion/motivation for doing so would have been provided by Chung itself, which teaches that applying a machine learning technique to a well’s predicted production decline curve yields that well’s estimated ultimate recovery and thereby improves forecast accuracy precisely where the well’s own production history is sparse, "For example, the prediction modification engine 112 may utilize a gradient boost decision tree machine learning technique to predict the EUR for a given well. This predicted EUR is then used as the additional boundary condition for wells with less than a certain amount of available historical production data (e.g., 24 months or less) to further improve the accuracy of the predicted decline curve generated by the production prediction engine 106" (Chung: ¶[0058]). Lam already trains its neural network on a simulation-derived database whose output layer emits EUR (Lam: ¶[0064]) and already performs decline curve analysis on the result the model returns for the well under analysis (Lam: ¶[0068]), so routing that decline curve into the model to obtain the EUR employs components Lam already has in hand and yields the reserves estimate Lam already seeks. The combination applies Chung’s technique to Lam’s own model: the decline curve Lam already produces for the well under analysis is routed into the simulation-trained network of Lam ¶[0109], which already emits EUR at its output layer (Lam: ¶[0064]), so no new model need be built and the modification is confined to the direction in which data already present in Lam is passed. A PHOSITA would therefore have had a reasonable expectation of success, and the results would have been predictable, because both references operate on the same quantities (a decline curve and an EUR) and Chung reports the technique already working on wells whose production history is sparse (Chung: ¶[0058]). Furthermore, this is the use of a known technique to improve a similar method in the same way, the rationale of MPEP § 2143(C).
Per claim 2, Lam combined with Chung discloses claim 1.
Lam further teaches wherein the input parameters comprises a location of the target wellbore, a porosity of a reservoir in which the wellbore is drilled, a permeability of the reservoir, a frac conductivity of the reservoir, a number of hydraulic fracturing stages in a hydraulic fracturing operation in the reservoir, a fracture length, a fracture height, hydrocarbon saturation, cluster spacing between perforation clusters in the hydraulic fracturing operation, stage spacing, or reservoir pressure (Lam: ¶[0054]…Lam’s specified parameters expressly include reservoir porosity and permeability, hydraulic fracture conductivity, number of fracture stages, fracture half-length and height, initial water saturation, cluster spacing and initial reservoir pressure, "Examples of specified parameters pertinent to the present disclosure include but are not limited to the following: initial reservoir pressure, reservoir depth, bottom-hole flowing pressure, bubble point pressure, dew point pressure, shear stress gradient, pressure gradient, reservoir temperature, reservoir thickness, oil density, gas gravity, rock matrix and natural fracture permeability, non-fracture zone matrix permeability multiplier, vertical and horizontal permeability multipliers, rock matrix/natural fracture porosity, natural fracture spacing, rock matrix/hydraulic fracture initial water saturation, water-oil contact depth, matrix/natural fracture compressibility, well lateral length, cluster spacing, well spacing, number of clusters, hydraulic fracture half-length/height/width/conductivity/permeability, number of fracture stages, hydraulic fracture compaction/relative permeability tables, and Pressure-Volume-Temperature (PVT) tables").
Per claim 3, Lam combined with Chung discloses claim 1.
Lam further teaches wherein generating the machine learning model comprises: identifying a subset of the plurality of simulated DCA-EUR sets that corresponds to the input parameters (Lam: ¶[0072]…Lam matches the user’s submitted parameter object against the stored simulation cases and returns only the matching cases, which constitutes identifying a subset of the simulated sets that corresponds to the input parameters under BRI, "The API reads through the object request, then finds the matching cases, and returns the matching cases to the software as a data file, such as a json file"; ¶[0083]…the same selection step appears in Lam’s workflow as the selection of a plurality of matching simulation curves once the well’s actual parameter data has been entered, "The actual wellsite parameter data is inputted, and a user selects a plurality of matching simulation curves 210"); and using the subset of the plurality of simulated DCA-EUR sets as training data for the machine learning model (Lam: ¶[0109]…the simulation curves so retrieved into the database are what Lam prepares as the training data for the neural network, which constitutes using the subset as training data for the machine learning model, "The processor is also configured to download the plurality of simulation curves into a database to prepare training data for training the neural network model"; ¶[0065]…Lam then fits the model to that data set, expressly splitting it into training, validation and test partitions and training the model on the training partition, "Different combinations of parameters are adapted to fit the model, and the model is able to be trained multiple times, for example, a model is trained ten times (K=10, the data will be split 10 times into a training data set, validation data set, and test data set) using training data, the model undergoing k-fold cross-validation, then tested for accuracy using test data").
Per claim 4, Lam combined with Chung discloses claim 1.
Lam further teaches further comprising generating the synthetic database using a physics-based reservoir simulator (Lam: ¶[0053]…Lam generates its production forecast models with commercial reservoir simulation software, namely Computer Modelling Group and Petrel Reservoir Engineering Eclipse, each of which is a numerical simulator that solves the governing flow physics of the reservoir and therefore constitutes a physics-based reservoir simulator, "In analysis methods according to at least one embodiment of the present disclosure, production forecast models are generated using reservoir simulation software such as Computer Modelling Group™ reservoir simulation software or Petrel Reservoir Engineering Eclipse™ simulation software"; ¶[0082]…the curves those simulators produce are exported to and stored in the database that later supplies the model’s training data, which constitutes generating the synthetic database using the physics-based reservoir simulator, "The outcome is displayed in a plurality of simulation curves 206. The plurality of simulation curves is exported to a database 207 and stored in the database 208 for future use").
Per claim 5, Lam combined with Chung discloses claim 4.
Lam further teaches wherein generating the synthetic database using the physics-based reservoir simulator comprises: using an optimizer to select a plurality of simulation scenarios described by the respective simulation data (Lam: ¶[0045]…Lam defines the outcome that drives its parameter selection as the goal or objective of an optimization process, so the routine that drives the parameter ranges toward that outcome constitutes an optimizer under BRI, "“Outcome” includes a goal or objective of an optimization process"; ¶[0082]…that optimizer adjusts the ranges of the specified parameters until the outcome is reached, and each parameter set so chosen defines one simulation scenario, which constitutes using an optimizer to select a plurality of simulation scenarios described by the respective simulation data, "The ranges of the specified parameters and the base case are used to display a plurality of fluid production and reserves in the simulation software 204. The ranges of the specified parameters are adjusted to obtain an outcome 205"; ¶[0087]…Lam’s automated flow expressly repeats the parameter-selection steps until the outcome is obtained and adjusts the ranges of the specified parameters to optimize the outcome, so the scenario selection is performed by an optimizing routine rather than by ad hoc user choice, which constitutes using an optimizer to select a plurality of simulation scenarios, "Steps 236 and 237 are repeated until the outcome is obtained for the plurality of wells 238…The ranges of the specified parameters are adjusted to optimize the outcome 245"); for each simulation scenario, using the respective simulation data and the physics-based reservoir simulator to generate a corresponding simulated DCA-EUR set (Lam: ¶[0082]…Lam creates a case in the simulation software from the collected data, runs the simulation on it and adjusts its specified parameters, which constitutes running the physics-based simulator on each scenario’s own simulation data, "The base case is created 201 in a simulation software using the set of data collected 200. Simulation is run on the base case 202. The specified parameters for the base case are then adjusted 203"; ¶[0084]…the resulting simulation curves are then fitted to decline curve models by adjusting decline curve parameters, which yields for each scenario the corresponding simulated DCA and its associated reserves figure, "A plurality of decline curve models is created containing the outcome 215. The outcome from the plurality of matching simulation curves is matched to the plurality of decline curve models by adjusting a plurality of decline curve parameters 216"); and
storing the corresponding simulated DCA-EUR set in the synthetic database (Lam: ¶[0082]…Lam exports the resulting curves to a database and stores them there for future use, which constitutes storing the corresponding simulated DCA-EUR set in the synthetic database, "The outcome is displayed in a plurality of simulation curves 206. The plurality of simulation curves is exported to a database 207 and stored in the database 208 for future use").
Per claim 6, Lam combined with Chung discloses claim 5.
Lam further teaches further comprising: for each simulation scenario, calculating an EUR accuracy for the corresponding simulated DCA-EUR set (Lam: ¶[0085]…Lam expressly calculates a probability distribution of the simulation curves against the actual wellsite production data and drives the parameter ranges until the outcome is reached, which is a computed measure of how closely each simulated case matches real production and therefore constitutes calculating an EUR accuracy for the corresponding simulated DCA-EUR set, "Probability distribution of the plurality of simulation curves and the actual wellsite production data for the plurality of wells is calculated 225 and then compared by adjusting the ranges of the specified parameters until the outcome is reached 226"; ¶[0045]…the outcome Lam computes for a simulation scenario expressly includes the errors or uncertainty in that scenario’s predictions of future production, and since the prediction at issue is the scenario’s recoverable reserves, the error so computed constitutes an EUR accuracy for the corresponding simulated DCA-EUR set, "In at least some embodiments, an outcome includes the errors or uncertainty in predictions of future production, including specific parameter values over which the user is able to control"); and storing the EUR accuracy in the synthetic database such that the EUR accuracy is associated with the corresponding simulated DCA-EUR set (Lam: ¶[0082]…while Lam does not use the words store the accuracy, the association necessarily follows from the structure Lam discloses: the outcome is defined at ¶[0045] to include the errors or uncertainty in the predictions of future production, and the outcome is the very thing Lam displays in the simulation curves and exports to and stores in the database, so on Lam’s own architecture the uncertainty computed for a scenario cannot be stored apart from the simulated curve it was computed for, which constitutes storing the EUR accuracy in the synthetic database such that it is associated with the corresponding simulated DCA-EUR set, "The outcome is displayed in a plurality of simulation curves 206. The plurality of simulation curves is exported to a database 207 and stored in the database 208 for future use").
Per claim 7, Lam combined with Chung discloses claim 1.
Chung further teaches further comprising calculating, using the machine learning model, an accuracy of the target EUR (Chung: ¶[0044]…Chung’s backtesting engine computes an accuracy metric for the well’s predicted production decline curve by comparing that prediction against the well’s actual historical production over the same interval, "In the examples of this description, the backtesting engine 108 is configured to determine an accuracy metric for a predicted production decline curve (e.g., provided by the production prediction engine 106) for a well based on a comparison of a predicted production decline curve for a time period (e.g., in the past) with historical production data for that well for the same time period"; ¶[0058]…Chung defines the EUR metric as the well’s 30-year cumulative production, so the predicted decline curve and the predicted EUR are two representations of the same quantity, the curve being the rate profile whose integral over that period is the EUR, "In one example, an expected ultimate recovery (EUR) metric for a given well is useful. The EUR metric may refer to a 30-year cumulative production for that well"; ¶[0058]…it follows that the backtesting accuracy metric computed for the predicted decline curve is an accuracy of the cumulative production that curve implies, and the EUR that Chung’s machine learning technique predicts is carried as a boundary condition on that same curve, which constitutes calculating, using the machine learning model, an accuracy of the target EUR, "For example, the prediction modification engine 112 may utilize a gradient boost decision tree machine learning technique to predict the EUR for a given well. This predicted EUR is then used as the additional boundary condition for wells with less than a certain amount of available historical production data (e.g., 24 months or less) to further improve the accuracy of the predicted decline curve generated by the production prediction engine 106"). The rationale to combine Chung with Lam is the same as the parent claim.
Per claim 8, Lam discloses A system (Lam: ¶[0081]…Lam implements the disclosure on a data processing system of one or more computers, databases and networks, which constitutes the system under BRI, "The data processing system 160 includes one or more computers 168, one or more databases 161, and one or more networks 163. The one or more databases 161 contains a plurality of simulation curves 162") comprising:
one or more processors configured to perform operations comprising (Lam: ¶[0108]…the same computer device includes at least one processor that executes those instructions and is thereby configured to carry out the recited analysis steps, which constitutes one or more processors configured to perform operations under BRI, "A computer device of predicting an output of oil and gas production in a hydrocarbon reservoir of a current and future producing well using a neural network model, including a non-transitory computer readable medium configured to store computer executable instructions. The device also includes at least one processor, wherein in response to executing the computer executable instructions, the processor is configured to receive a data set, using a graphic user interface (GUI), comprising a plurality of parameters of the hydrocarbon reservoir at a wellsite"): …
The remaining limitations are of identical scope to claim 1. Therefore, the rejection of claim 1 is applied accordingly.
Claims 9-14 are substantially similar in scope and spirit as claims 2-7. Therefore the rejections of claims 2-7 are applied accordingly.
Per claim 15, Lam discloses A non-transitory computer storage medium encoded with instructions that, when executed by one or more computers, cause the one or more computers to perform operations comprising (Lam: ¶[0108]…Lam implements the disclosure on a computer device having a non-transitory computer readable medium that stores the computer executable instructions carrying out the analysis, which constitutes the non-transitory computer storage medium encoded with instructions that, when executed by one or more computers, cause the one or more computers to perform operations under BRI, "A computer device of predicting an output of oil and gas production in a hydrocarbon reservoir of a current and future producing well using a neural network model, including a non-transitory computer readable medium configured to store computer executable instructions. The device also includes at least one processor, wherein in response to executing the computer executable instructions, the processor is configured to receive a data set, using a graphic user interface (GUI), comprising a plurality of parameters of the hydrocarbon reservoir at a wellsite"): …
The remaining limitations are of identical scope to claim 1. Therefore, the rejection of claim 1 is applied accordingly.
Claims 16-20 are substantially similar in scope and spirit as claims 2-6. Therefore the rejections of claims 2-6 are applied accordingly.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ALAN CHEN whose telephone number is (571)272-4143. The examiner can normally be reached M-F 10-7.
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, Kamran Afshar can be reached at (571) 272-7796. 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.
/ALAN CHEN/ Primary Examiner, Art Unit 2125
Prosecution Insights