DETAILED ACTION
Notices to Applicant
This communication is a non-final rejection. Claims 1-29, as filed 07/03/2024, are currently pending and have been considered below.
Foreign priority is acknowledged to UNITED KINGDOM 2200184.6 (01/07/2022).
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon and the rationale supporting the rejection would be the same under either status.
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Long!, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969)
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP §§ 706.02(l)(1) - 706.02(l)(3) for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/process/file/efs/guidance/eTD-info-l.jsp
US 12,241,339 B2 (‘392 patent) and US 11,795,787 B2 (‘787 patent) each name Gunnerud and Grimstad as common inventors and are assigned to Solution Seeker AS.
Claims 1, 7-11, 16, 17, 21-24, and 26-28 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-32 of the ‘339 patent in view of Zhang (CN111460625A). Although the claims at issue are not identical, they are not patentably distinct from each other for the reasons set forth in the table below.
Pending claim
‘339 claim(s)
Explanation (where needed)
1
1, 18, 19, 28, 30, 31
Patented claim 1 generates a “first data-driven well model” that is “parameterized”; claim 19 adds iterative training and claim 30 adds a neural network.
The ‘339 claims do not teach unlabeled production data and minimizing an unsupervised loss function, but this is disclosed by Zhang as described in the 103 rejections. It would have been obvious to a POSITA before the effective filing date to combine Zhang and the ‘339 patent because this would allow the model to be trained on a larger portion of production data and avoid “waste of a large amount of sample data” (Zhang p. 4).
7
1
8
31
9, 10
22, 25, 27
11
2, 3, 7
16
1, 32
17
15
21
10
22
11
23, 24
12
26
23
27
24
28
1
Claims 1, 4, 5, 7, and 25-28 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-6 of the ‘787 patent in view of Zhang (CN111460625A). Although the claims at issue are not identical, they are not patentably distinct from each other for the reasons set forth in the table below.
Pending claim
‘787 claim(s)
Explanation (where needed)
1
1,2
Patented claim 1 generates a model using measurement data and trains a model under constraints, a modelled flow rate for the flow path is encouraged toward zero when a valve is closed, and claim 2 adds machine learning models.
The ‘787 claims do not teach unlabeled production data and minimizing an unsupervised loss function, but this is disclosed by Zhang as described in the 103 rejections. It would have been obvious to a POSITA before the effective filing date to combine Zhang and the ‘787 patent because this would allow the model to be trained on a larger portion of production data and avoid “waste of a large amount of sample data” (Zhang p. 4).
4
1
5
1
7
1
25
4
26
5
27
6
28
1
Claim Objections
Claims 5 and 10 are objected to because of the following informalities. The claims begin with “in the method of claim” instead of “The method of claim”. This appears to be a typographical mistake since the other claims use proper preamble structure.
Appropriate correction is required.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-29 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. The claim(s) does/do not fall within at least one of the four categories of patent eligible subject matter because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Step 1
Claims 1-14 and 16-29 recite(s) subject matter within a statutory category as a process, machine, and/or article of manufacture.
Claim 15 is directed to “a parametric model” which is software per se rather than one of the statutory categories. See MPEP 2106.03(I): Non-limiting examples of claims that are not directed to any of the statutory categories include: Products that do not have a physical or tangible form, such as information (often referred to as “data per se”) or a computer program per se (often referred to as “software per se”) when claimed as a product without any structural recitations. For purposes of compact prosecution, the claim will be analyzed in the other 101 steps as with the other claims.
Step 2A Prong One
Claim 1 is analyzed in detail but the analysis applies to the other claims. Claim 1 recites:
--training a parametric model for describing, for one or more production wells, a relationship between one or more flow parameters, and/or one or more well parameters and/or an associated status of at least one control point associated with the one or more production wells (additional element - field-of-use limitation that generally links the abstract idea to a particular technical environment),
--wherein the training uses unlabeled production data relating to the one or more production wells, (additional element – selecting a particular data source to be manipulated which is insignificant, extra-solution activity in MPEP 2106.05(g)) and comprises:
--minimizing an unsupervised loss function for the parametric model based on the unlabeled production data (abstract idea – mathematical concept, namely, minimizing a function); and
--estimating model parameters of the parametric model based on the minimizing of the unsupervised loss function (abstract idea – mathematical concept, namely, computing the arguments that minimize the function).
The broadest reasonable interpretation of these italicized steps includes mathematical concepts grouping of MPEP 2106.04(a)(2)(I). The specification confirms that the invention here is directed to math, e.g., “Using parametric models, e.g. neural networks, optimization is typically performed by a gradient descent method” ([0105] as published).
Dependent claims recite additional subject matter which further narrows or defines the abstract idea embodied in the claims. For example, claims 2, 3, 5, 6, 8, 9, 11, 13, and 29 add further mathematical detail.
Step 2A Prong Two
This judicial exception is not integrated into a practical application. In particular, the additional elements do not integrate the abstract idea into a practical application, other than the abstract idea per se, because the additional elements amount to mere instructions to apply an exception (MPEP 2106.05(f)), add insignificant extra-solution activity to the abstract idea (MPEP 2106.05(g)), or generally link the abstract idea to a particular technological environment (MPEP 2106.05(h)) as indicated above in Prong One.
Dependent claims recite additional subject matter which amount to limitations consistent with the additional elements in the independent claims. For example, claims 7, 12, 14, and 28 provide field-of-use limitations that generally link the abstract idea to a particular technical environment and claims 16-24 recite uses of the calculated results that amount to merely applying the abstract idea with a computer.
Looking at the limitations as an ordered combination, the elements amount to performing a mathematical optimization on production well data and nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely provide conventional computer implementation and do not impose a meaningful limit to integrate the abstract idea into a practical application.
Step 2B
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to discussion of integration of the abstract idea into a practical application, the additional elements amount to no more than mere instructions to apply an exception, add insignificant extra-solution activity to the abstract idea, and generally link the abstract idea to a particular technological environment or field of use. Additionally, the additional limitations, other than the abstract idea per se amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields such as receiving or transmitting data over a network, Symantec, MPEP 2106.05(d)(II)(i), performing repetitive calculations, Flook, MPEP 2106.05(d)(II)(ii), electronic recordkeeping, Alice Corp., MPEP 2106.05(d)(II)(iii), and/or storing and retrieving information in memory, Versata Dev. Group, MPEP 2106.05(d)(II)(iv).
Dependent claims recite additional subject matter which, as discussed above with respect to integration of the abstract idea into a practical application, amount to invoking computers as a tool to perform the abstract idea. Dependent claims recite additional subject matter which amount to limitations consistent with the additional elements in the independent claims. Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely provide conventional computer implementation.
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 set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied 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.
Claims 1, 3, 4, 6-8, 12-29 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang (CN111460625A) in view of Bello (US20160356125A1).
Regarding claim 1, Zhang discloses: A method of training a parametric model, the method comprising:
--training a parametric model for describing, for one or more production wells, a relationship between one or more flow parameters, and/or one or more well parameters and/or an associated status of at least one control point associated with the one or more production wells (“coding-decoding deep learning mode is adopted, x is defined as an input signal, r is an output signal, h ═ f (x) is represented as an encoder, r ═ g (h) is defined as a decoder,” p. 5; “artificial intelligence model for online real-time measurement of the multiphase flow, a direct AI (artificial intelligence) modeling mode from a measuring end (Venturi, ECT and microwave measuring signals) to an output end (gas phase flow, oil phase flow and water phase flow) is adopted, errors in the traditional modeling intermediate process are reduced, and the measurement precision of the model is improved,” p. 3),
--wherein the training uses unlabeled production data relating to the one or more production wells (“extracting the most basic constituent unit signals in the Venturi, electrical tomography and microwave measurement signals in a depth coding-decoding mode under the condition of no real flow sample label,” p. 5; “mass unlabeled original Venturi,” p. 4; “only a small number of real flow labels calibrated through a separation tank are provided in the field test process of an oil field, and in most cases, only sensor measurement signals acquired by a three-phase flowmeter (Venturi, ECT and microwave) are provided,” p. 4), and comprises:
--minimizing an unsupervised loss function for the parametric model based on the unlabeled production data (“And secondly, Model _ run.compound (optimizer: ' adam ' and loss ═ mse '), adopting ' adam ' as an optimization algorithm in a Model training process, and adopting ' mse ' as a Model global loss function,” p. 5). Zhang’s recitation of an optimization function acting on a named loss function during training is recitation of minimizing that loss function. The specification uses the same equivalence in [0104]: “The model parameter estimates may be found by any optimization scheme which minimizes the total loss.”
--estimating model parameters of the parametric model based on the minimizing of the unsupervised loss function (“mass unlabeled original Venturi, ECT and microwave input data are respectively substituted into a Model for training, and then the characteristic extraction models corresponding to the Venturi, ECT and microwave sensors can be respectively obtained,” p. 5).
While Zhang discloses training a parametric encoder-decoder model on unlabeled multiphase-flow sensor signals by minimizing an unsupervised loss function and estimating the model’s parameters from that minimization, Zhang does not expressly disclose that the unlabeled data on which the model is trained is production data relating to one or more production wells because Zhang’s signals are acquired by a three-phase flowmeter “in the field test process of an oil field”. Bello teaches this limitation in [0081]: “an initial model calibration is performed using historical data, which includes any measurement data generated in the borehole during pervious production operations, such as daily historical monitoring data” which is obtained from “one or more production logging tools (PLTs)” in [0028].
It would have been obvious to a POSITA before the effective filing date to expand the training data set of Zhang to include the production well data of Bello because doing so would yield a model of the production well itself which would allow for “predicting and optimizing flow control device settings to improve hydrocarbon recovery and mitigate water/gas breakthrough risk, and managing sensor data for improved production monitoring and characterization (pressure and temperature transient detection) based on pattern recognition,” [0033].
Additionally, each element is taught by either Zhang or Bello. The features of Bello do not affect the normal functioning of the elements of the claim which are taught by Zhang and Bello. Because the elements do not affect the normal functioning of each other, the results of their combination would have been predictable. Therefore, before the effective filing date of the claimed invention, it would have been obvious to combine the teachings of Zhang and Bello since the result is merely a combination of old elements, and, since the elements do not affect the normal functioning of each other, the results of the combination would have been predictable.
Regarding claim 3, Zhang further discloses: wherein the unsupervised loss function and the parametric model are part of an autoencoder (“coding-decoding deep learning mode is adopted, x is defined as an input signal, r is an output signal, h ═ f (x) is represented as an encoder, r ═ g (h) is defined as a decoder…adopting ' mse ' as a Model global loss function” p. 5).
Regarding claim 4, Zhang further discloses: wherein the training further uses labeled production data relating to the one or more production wells, and comprises:
--minimizing a supervised loss function for the parametric model based on the labelled production data (“the artificial intelligent identification model construction of the measurement signal, the gas phase flow, the oil phase flow and the water phase flow is carried out on a small amount of samples with flow labels,” p. 5; “using adam ' as an optimization function of the model, using ' mse ' and ' mae ' as loss functions of a training process of the model,” p. 6); and
--estimating model parameters of the parametric model based on the minimizing of the supervised loss function (“And eighthly, training a model, namely model _ Qgas.fit (x _ train, y _ gas _ train), training a constructed model, wherein a training sample label is a real gas phase flow label,” p. 6).
Regarding claim 6, Zhang does not expressly disclose but Bello further teaches: where the step of minimizing the unsupervised loss function and the step of estimating model parameters of the parametric model form part of a regression problem (“for PDG and PLT simulations, a standard L2 norm-based (least squares type) objective function is used,” [0073]).
The motivation to combine is the same as in claim 1.
Regarding claim 7, Zhang does not expressly disclose but Bello further teaches: wherein the parametric model is for describing for a plurality of production wells a relationship between one or more flow parameters, one or more well parameters and/or an associated status of the at least one control point (“wherein the field source includes a plurality of production boreholes” claim 4).
The motivation to combine is the same as in claim 1.
Regarding claim 8, Zhang does not expressly disclose but Bello further teaches: wherein the step of minimizing the unsupervised loss function comprises a gradient descent method (“A variety of approaches can be taken, which typically fall into two categories: gradient based algorithms (such as variations of Levenberg-Marquardt, Bayesian analysis, interval analysis, and others), and non-gradient search algorithms (such as genetic algorithms, particle swarm optimization and differential evolution),” [0072]; “The algorithm is a blend of first derivative and second derivative (e.g. Hessian) searching; a first derivative search is used when far from the minimum,” [0074]).
The motivation to combine is the same as in claim 1.
Regarding claim 12, Zhang further discloses: wherein the parametric model is for describing, for the one or more production wells, a plurality of relationships between flow parameters, and/or well parameters, and/or an associated status of the at least one control point (“3) constructing an artificial intelligent identification model of the measurement signal, the gas phase flow, the oil phase flow and the water phase flow by adopting a multilayer fully-connected deep neural network from an input end to an output end,” p. 2).
Regarding claim 13, Zhang further discloses: wherein the parametric model comprises a plurality of task-specific model parameters that are each representative of one or more properties common to a respective task to which the task-specific model parameter relates (“constructing a Model input and output framework by a Model training framework, wherein Model _ Qgas is Model (inputs are [ Fn Venturi, FECT ], outputs are [ Qgas _ output ], the input adopts Fn Venturi and FECT double input parameters, and the output adopts Qgas _ output single output parameter,” p. 6; Qgas_output, Qoil_output, and Qwater_output on pp. 6-7).
Regarding claim 14, Zhang further discloses: wherein each task is flow-rate estimation and the model comprises flow-rate-estimation-specific parameters (“Model1 models of coding processes trained in coding-decoding processes are respectively Model _ Venturi, Model _ ECT and Model _ microwave and used as feature extraction models of sample training samples with labels,” p. 6; Qgas_output, Qoil_output, and Qwater_output on pp. 6-7 are all flow rates).
Claims 15- 17, 20, 26, and 27 are substantially similar to claim 1 and are rejected with the same reasoning. The Examiner further notes that Bello teaches in [0033]: “estimating formation properties and production properties (e.g., fluid production rates, also referred to as well rates), performing automatic virtual well test analyses, forecasting of future production performance, automatically calibrating devices such as downhole flow meters (DFMs) by integrating production data, monitoring inflow control devices, predicting and optimizing flow control device settings to improve hydrocarbon recovery and mitigate water/gas breakthrough risk, and managing sensor data for improved production monitoring and characterization (pressure and temperature transient detection) based on pattern recognition” and in [0117] various computer implementations.
Regarding claims 18 and 19, Zhang does not expressly disclose but Bello teaches: estimating, for a point of time in the past, one or more flow parameters, and/or one or more well parameters, and/or the status of at least one control point, for the one or more production wells (“measurement data generated in the borehole during pervious production operations, such as daily historical monitoring data,” [0081]; “Various computational algorithms, referred to collectively as virtual flow metering (VFM) algorithms, perform processes including estimation of multi-phase flow rates and production allocation from single and multi-zonal wells using a coupled thermal reservoir-borehole model, and automatic and/or online production prediction and model calibration,” [0032]).
The motivation to combine is the same as in claim 1.
Regarding claim 21, Zhang does not expressly disclose but Bello further teaches: wherein the modelling comprises predicting one or more potential future flow parameters, and/or one or more potential future well parameters, and/or a potential future status of the at least one control point, for the one or more production wells (“the thermal reservoir model employed by the application may be used to generate forecasts of production output for one or more production wells,” [0045]).
The motivation to combine is the same as in claim 1.
Claim 22 is substantially similar to claim 21 and is rejected with the same reasoning. The Examiner further notes that Bello teaches in [0045]: “’what-if’ forecasting that predicts production output in response to multiple scenarios” and in [0090]: “Each scenario represents a different estimate of conditions, such as rate and/or composition of injection fluid and downhole vale settings”.
The motivation to combine is the same as in claim 1.
Regarding claims 23 and 24, Zhang does not expressly disclose but Bello teaches: wherein steps (i) to (iii) are repeated until a desired improvement in production performance (or optimized production performance) is determined (“the forecasting process can be used to optimize various production parameters, such as injection rates, injection fluid types, flow rates and valve settings,” [0091]).
The motivation to combine is the same as in claim 1.
Claim 25 is substantially similar to claim 22 and is rejected with the same reasoning. The Examiner further notes that Bello teaches in [0091]: “the forecasting process can be used to optimize various production parameters, such as injection rates, injection fluid types, flow rates and valve settings” and in [0033]: “monitoring inflow control devices, predicting and optimizing flow control device settings to improve hydrocarbon recovery and mitigate water/gas breakthrough risk, and managing sensor data for improved production monitoring and characterization (pressure and temperature transient detection) based on pattern recognition.”
The motivation to combine is the same as in claim 1.
Regarding claim 28, Zhang does not expressly disclose but Bello teaches: wherein the one or more production wells are one or more hydrocarbon production wells (“wherein the field source includes a plurality of production boreholes, and receiving the field data includes receiving individual field data from each of the plurality of field sources,” claim 4; “improve hydrocarbon recovery,” [0033]).
The motivation to combine is the same as in claim 1.
Regarding claim 29, Zhang does not expressly disclose but Bello teaches:29. The method of claim 1, wherein the minimizing of the unsupervised loss function is terminated when a termination condition is met (“If the objective function value is within a selected range, e.g., within some selected minimum of the objective function or error value (block 134), the model parameters are considered to be acceptable and the calibration or update process ends. If the objective function value is not within the selected range, the forward model is run again (block 135) and a new objective function value is calculated. This process is repeated using the above-described inversion until the objective function value is minimized or within the selected range,” [0085]).
The motivation to combine is the same as in claim 1.
Claims 2 and 5 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang (CN111460625A) in view of Bello (US20160356125A1) and Luong (WO2020219971A1).
Regarding claim 2, Zhang does not expressly disclose but Luong teaches: wherein the unsupervised loss function is set-up such that it can be used to conduct consistency training (“wherein the unsupervised objective is based on a K-L divergence between (i) the model output generated by the machine learning model for the given unlabeled training input and (ii) the model output generated by the machine learning model for the augmented training input generated from the unlabeled training input,” claim 2; “the unsupervised objective can be based on a Kullback- Leibler (K-L) divergence between (i) the model output generated by the machine learning model for the given unlabeled training input and (ii) the model output generated by the machine learning model for the corresponding augmented unsupervised training input,” p. 4).
A POSITA before the effective filing date would have been motivated to expand Zhang and Bello’s unsupervised objective to include the consistency objective and single loss function of Luong because this would improve the model when labeled data is scarce, allowing a large amount of unlabeled data to be used while reducing the variation resulting from input noise. See Qizhe Xie et al., "Unsupervised Data Augmentation for Consistency Training", Abstract.
Additionally, each element is taught by either Zhang, Bello, or Luong. The consistency training of Luong does not affect the normal functioning of the elements of the claim which are taught by Zhang and Bello. Because the elements do not affect the normal functioning of each other, the results of their combination would have been predictable. Therefore, before the effective filing date of the claimed invention, it would have been obvious to combine the teachings of Luong with the teachings of Zhang and Bello since the result is merely a combination of old elements, and, since the elements do not affect the normal functioning of each other, the results of the combination would have been predictable.
Regarding claim 5, Zhang does not expressly disclose but Luong teaches: wherein the steps of minimizing the supervised loss function and minimizing the unsupervised loss function are performed by minimizing a total loss function, and wherein the steps of estimating model parameters based on the minimizing of the unsupervised loss function and based on the minimizing of the supervised loss function are performed by estimating model parameters based on the minimizing of the total loss function (“the system trains the model to optimize an objective, e.g., minimize a loss, that is a combination, e.g., a sum, an average, or a weighted sum, of an unsupervised objective and a supervised objective,” p. 4).
The motivation to combine is the same as in claim 2.
Claims 9-11 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang (CN111460625A) in view of Bello (US20160356125A1) and Boe (US20180010430A1).
Regarding claims 9 and 10, Zhang does not expressly disclose but Boe teaches: wherein the parametric model comprises context-specific model parameters that are each representative of one or more properties common to a respective context to which the context-specific model parameter relates (“where the software products are adapted for said computing hardware to analyze said measurement signals to abstract at least one parametric representation of said configuration of oil and/or gas wells comprising the following parameters: one instantaneous productivity parameter for each production well; one instantaneous injectivity parameter for each injection well; one instantaneous storativity parameter for each deposit; and one instantaneous connectivity parameter for the hydraulic communication between each pair of deposits in hydraulic communication with each other and to employ said at least one parametric representation for monitoring the configuration of oil and/or gas wells,” [0043]).
A POSITA before the effective filing date would have been motivated to expand Zhang and Bello’s unsupervised objective to include the per-well productivity parameter and per-deposit storativity parameter of Boe because it would allow “some important parameters may be estimated continuously along a timeline with no need to interrupt production” in Boe [0021].
Additionally, each element is taught by either Zhang, Bello, or Boe. The per-well and per-deposit parameters of Boe do not affect the normal functioning of the elements of the claim which are taught by Zhang and Bello. Because the elements do not affect the normal functioning of each other, the results of their combination would have been predictable. Therefore, before the effective filing date of the claimed invention, it would have been obvious to combine the teachings of Boe with the teachings of Zhang and Bello since the result is merely a combination of old elements, and, since the elements do not affect the normal functioning of each other, the results of the combination would have been predictable.
Regarding claim 11, Zhang does not expressly disclose but Boe teaches: wherein each context is a respective set of production wells and each context-specific parameter is a parameter specific to a respective set of production wells (“one storativity parameter for each deposit,” claim 1; “(ii) storage characteristics and/or change in average reservoir pressure of the geological formation 30; (iii) interactivities between wells 80 of the system,” [0076]; “wherein said at least one parametric representation comprises one of more deposits not penetrated by wells, in addition to the plurality of deposits comprising production and injection wells,” claim 4).
The motivation to combine is the same as in claim 9.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Jansen (Jan-Dirk Jansen, "Model-based control of multiphase flow in subsurface oil reservoirs" Journal of Process Control 18 (2008) 846–855) discloses techniques “to better control the multiphase flow in the reservoir over the entire production period,” (Abstract).
Ahmed (Amr Ahmed et al., "Training Hierarchical Feed-forward Visual Recognition Models Using Transfer Learning from Pseudo-Tasks" Proceeding of the 10th European Conference of Computer Vision (ECCV) (2008)) discloses “focusing the pseudo-tasks on interesting parts of the images by using our prior knowledge in the form of a set of Gabor filters,” p. 76. This particularly relevant to specification page 21 lines 7-11.
Weston (US20090204558A1) discloses a joint supervised/unsupervised training structure (e.g., claim 1).
Weston (“Deep learning via semi-supervised embedding”) discloses “We note that an alternative multi-task learning scheme is presented in (Ando & Zhang, 2005) and applied to neural networks in (Ahmed et al., 2008) which instead constructs auxiliary supervised tasks from unlabeled data by constructing tasks with labels y*. This is useful when p(y*|x) is correlated to p(y|x), however an expert must engineer a useful target y*,” p. 1172.
Gao (US20170032035A1) discloses “process 400 includes unshared operational layers L0, L1, L2, and L3 that individually represent task-specific outputs,” [0064].
Zhai (“S4L: Self-Supervised Semi-Supervised Learning”) discloses in the methods section:
PNG
media_image1.png
264
1066
media_image1.png
Greyscale
Gunnerud (US20180320504A1) has a similar inventive entity and discloses “Meaning that for the time horizon of the decision (e.g. 12 hours to 2 weeks), the reservoir conditions can be considered fixed i.e. modelled by a constant PI, GOR and WC for each well, and the dynamics of the pipeline system can be neglected and considered steady state,” [0215].
Sandnes (Anders Sandnes et al., "Multi-task learning for virtual flow metering") discloses “Virtual flow metering (VFM) is a cost-effective and non-intrusive technology for inferring multiphase flow rates in petroleum assets.”
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JOSHUA BLANCHETTE whose telephone number is (571)272-2299. The examiner can normally be reached on Monday - Thursday 7:30AM - 6:00PM, EST.
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, Shahid Merchant, can be reached on (571) 270-1360. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
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 http://pair-direct.uspto.gov. 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.
/JOSHUA B BLANCHETTE/Primary Examiner, Art Unit 3624
Prosecution Insights