DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Objections
Claims 5, 7, 8, 12, 18, and 20 are objected to because of the following informalities:
Claim 5 is objected to because of the following informalities: 1) “using Kriging technique” where there is a missing article; it should be “using a Kriging technique”, 2) “at unmeasured location” where there is a missing article; it should be “at an unmeasured location”.
Claim 7 is objected to because of the following informalities: “uses pointwise learn to rank algorithm” where there is a missing article and incorrect tense; it should be “uses a pointwise learning to rank algorithm”.
Claim 8 is objected to because of the following informalities: “determining a corrosion severity rank using a machine learning model and based on the obtained well corrosion values and the obtained well barrier parameters” where there is incorrect tense leading to confusing meaning; suggested change would be “determining a corrosion severity rank using a machine learning model based on the obtained well corrosion values and the obtained well barrier parameters”
Claim 12 is objected to because of the following informalities: “generated using Kriging technique that generates” where there is a missing article; it should be “generated using a Kriging technique that generates”
Claim 18 is objected to because of the following informalities: “generated using Kriging technique that generates” where there is a missing article; it should be “generated using a Kriging technique that generates”
Claim 20 is objected to because of the following informalities: “uses pointwise learn to rank algorithm” where there is a missing article and incorrect tense; it should be “uses a pointwise learning to rank algorithm”.
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 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea (mental processes and mathematical relationships) without significantly more. Claim 1 recites:
A method for predicting well corrosion, comprising: (this falls within the statutory categories of invention)
obtaining, using a computer processor, well corrosion values and well barrier parameters, the well barrier parameters including properties of cement and casing; (obtaining this data is insignificant extra-solution activity in the form of mere data gathering, as per MPEP 2106.05(g), and the data itself is numerical values for use in calculations that are only generally linked to the technical field of wellbore management by virtue of what the numerical values are intended to represent, as per MPEP 2106.05(h). The use of the computer processor is mere instructions to apply the exception with generic computer components as per MPEP 2106.05(f).)
determining, using the computer processor, a corrosion severity rank using a machine learning model and based on the obtained well corrosion values and the obtained well barrier parameters; (a person could mentally generate a corrosion severity rank by observing well data and evaluating it based on their professional expertise. The use of a machine learning model is described in black-box manner, defined in terms of its inputs and outputs with no hint as to how it operates or functions. Put another way, the claim recites only the idea of a solution or outcome and fails to recite details of how a solution to a problem is accomplished. The machine learning model is being invoked merely as a tool to carry out the process. It therefore amounts to mere instructions to apply the exception with a generic machine learning model, as per MPEP 2106.05(f).)
determining, using the computer processor, a well priority rank based on the determined corrosion severity rank and well criticality features, (a person can make a judgement to mentally prioritize and rank possible wells based on the information about those wells they observe and evaluate.)
the well criticality features indicating an amount of damage caused by a deterioration of a well; and (this is within the scope of what a person could consider mentally during their observations, evaluations, and judgements.)
generating, using the computer processor, a wellbore drilling plan based on the determined well priority rank. (a person can mentally generate a wellbore drilling plan and then record it on paper based on their evaluations and judgements using professional expertise.)
This judicial exception is not integrated into a practical application. In particular, the claim only recites the following additional elements: 1) mere instructions to apply the exception using generic computer components (the processor) and a generic machine learning model, 2) generally linking the use of the exception to the technical field of wellbore management, and 3) insignificant extra-solution activity in the form of mere data gathering (obtaining data values). The processor is recited at a high-level of generality (i.e., as a generic processor performing a generic computer function of executing instructions and storing data) such that it amounts no more than mere instructions to apply the exception using a generic computer component. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. Limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception cannot integrate a judicial exception into a practical application. The specification that data is obtained is only tangentially linked to the calculation and analysis steps, and does not meaningfully limit the claim. The claim is directed to an abstract idea.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using a processor to perform the claimed steps amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. Limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not amount to significantly more than the exception itself. The addition of insignificant extra-solution activity does not amount to an inventive concept. The claim is not patent eligible.
Claims 2-6 recite only further details that fall within the scope of mental processes and mathematical relationships (e.g. the mathematical algorithm of Kriging recited in claim 5). They remain ineligible for the above reasons.
Claim 7 additionally recites “wherein the machine learning model uses pointwise learn to rank algorithm.” This still does not describe how the machine learning model functions in a meaningful manner, only invoking a broadly defined generic machine learning algorithm that is a term of the art and is no less generic than the “machine learning model”. The feature remains within the scope of MPEP 2106.05(f)’s discussion of “mere instructions to apply an exception”, and remains ineligible.
Claims 8-13 are substantially similar to claims 1-6, and are rejected under the same grounds.
Claims 14-20 are substantially similar to claims 1-7, and are rejected under the same grounds.
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.
Examiner notes that due to the substantial similarity of claims 1-7 with claims 8-13 and 14-20 respectively, they are being grouped together in the grounds of rejection below.
Claims 1, 2, 4, 6, 8, 9, 11, 13, 14, 15, 17, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Zahacy (Zahacy, T. A., & Demirdal, B. (2019, September). Risk-ranking approach for thermal well integrity using readily available application, well and operational parameters. In SPE Annual Technical Conference and Exhibition? (p. D012S064R001). SPE.) in view of Pang (US 20220112799 A1) and Lang (US 20220372846 A1).
Regarding Claims 1, 8, and 14:
Zahacy teaches:
obtaining, using a computer processor, well corrosion values and well barrier parameters, (SBI Model Development, the SBI risk model was to focus on the loss of the subsurface barrier elements, which included the surface and intermediate casing strings and associated cement sheaths. The risk estimation approach and categorization of the levels of severity and acceptance would be based on the operator's semi-quantitative five-by-five likelihood and consequence risk matrix.; Top Level Hazards, a number of potential damage mechanisms were identified, including near-surface oxidative corrosion; Step 1: Populating the Model, casing deformation and corrosion logs; To incorporate monitoring data, such as the interpreted results of multi-finger caliper logs, corrosion logs and the presence and severity of SCVF and GM events into the model as condition indicators;)
the well barrier parameters including properties of cement and casing; (Introduction, the key damage mechanisms and some of the static and dynamic parameters that this tool considers, including geologic (e.g., formations susceptible to movement), well design (e.g., casing diameter, material and connection type), construction (e.g., cement sheath quality); key inputs, such as downhole completion equipment condition (e.g., tubular connection sealability or seepage rates and the permeability or potential flow paths of the cement sheath))
determining, using the computer processor, a well priority rank based on the determined corrosion severity rank and well criticality features, (Abstract, application of a combination of reliability and risk methods, parameter-based damage models and available field data can be used to develop a tool used by asset integrity and operations personnel to risk-rank wells by the probability of failure and associated consequences. Additionally, this paper illustrates how the approach and models developed are adaptable to both the damage mechanisms specific to the application and to the data and parameters that are currently being measured or readily obtained, or other related variables that can used as suitable proxy parameters. As experience and history build (adding to the understanding and prioritization of damage mechanisms and key parameters), and to improve estimated values of the associated probability of failure due to these mechanisms, the knowledge is fed back into the model to improve its predictive capabilities ... how the tool is being used to prioritize injection and production wells by relative risk.)
the well criticality features indicating an amount of damage caused by a deterioration of a well; and (Abstract, identify which wells amongst their diverse well inventory may be prone to damage and failure, the mechanisms and influential factors responsible for the potential damage and failures, and the reason why certain wells may pose the greatest risk; Abstract, the application of a combination of reliability and risk methods, parameter-based damage models and available field data can be used to develop a tool used by asset integrity and operations personnel to risk-rank wells by the probability of failure and associated consequences; Abstract, models developed are adaptable to both the damage mechanisms specific to the application and to the data and parameters that are currently being measured or readily obtained, or other related variables that can used as suitable proxy parameters. As experience and history build (adding to the understanding and prioritization of damage mechanisms and key parameters), and to improve estimated values of the associated probability of failure due to these mechanisms, the knowledge is fed back into the model to improve its predictive capabilities)
Zahacy does not teach in particular, but Pang teaches:
determining, using the computer processor, a corrosion severity rank using a machine learning model and based on the obtained well corrosion values and the obtained well barrier parameters; (¶14 the multi-objective optimization combines Bayesian optimization with either machine learning models or empirical models to optimize scaling and corrosion.; ¶49 At step 212, a “real” corrosion rate Vbase is calculated at points along the wellbore. Vbase is considered to be the “real” corrosion rate because it takes into account both corrosion and calcite scaling; ¶61 using machine learning to determine Vbase and Is, wherein the step of using machine learning comprises using a Deep Neural Network.; ¶58 electing optimization points from the ranges of Vbase and Is obtained from the base calculation, and performing a multi-objective optimization for the selected optimization points of Vbase and Is. The method further comprises controlling an alkalinity and flow rate of the fluid based on the multi-objective optimization.)
It would have been obvious to one of ordinary skill in the art at the time the invention was filed to apply the machine learning based corrosion analysis methodology of Pang to the risk tool of Zahacy, specifically to augment Zahacy's corrosion modeling, in order to provide better accuracy than empirical models (¶50 of Pang explicitly identifies this as an advantage in those words).
Zahacy does not teach in particular, but Lang teaches:
generating, using the computer processor, a wellbore drilling plan based on the determined well priority rank. (Abstract, identifying a wellsite target for drilling; ¶26 ranking competing well targets, recommending well targets for a reservoir simulation model, well placement for ensemble models (e.g., uncertainty and optimization workflows), and in complex reservoir structures; ¶61 supervised machine learning model used to predict a target by learning decision rules from features of the reservoir properties.; see also Pang ¶58 "controlling an alkalinity and flow rate of the fluid based on the multi-objective optimization.")
It would have been obvious to one of ordinary skill in the art at the time the invention was filed to apply the drillsite identification and selection of Lang to the prioritized production well result of Zahacy as modified by Pang, in order to enable the system to identify well targets in a faster, less labor intensive, more comprehensive, and automated manner (Lang, ¶2).
Regarding Claims 2, 9, and 15:
Zahacy teaches:
wherein a plurality of wells is ranked based on the well priority rank, and wherein an action plan is generated based on the ranking of the plurality of wells. (Abstract, identify which wells amongst their diverse well inventory may be prone to damage and failure, the mechanisms and influential factors responsible for the potential damage and failures, and the reason why certain wells may pose the greatest risk; Abstract, the application of a combination of reliability and risk methods, parameter-based damage models and available field data can be used to develop a tool used by asset integrity and operations personnel to risk-rank wells by the probability of failure and associated consequences; Abstract, models developed are adaptable to both the damage mechanisms specific to the application and to the data and parameters that are currently being measured or readily obtained, or other related variables that can used as suitable proxy parameters. As experience and history build (adding to the understanding and prioritization of damage mechanisms and key parameters), and to improve estimated values of the associated probability of failure due to these mechanisms, the knowledge is fed back into the model to improve its predictive capabilities; also see citations to Lang and Pang for the last limitation of claim 1.)
Zahacy does not teach in particular, but Pang teaches:
It would have been obvious to one of ordinary skill in the art at the time the invention was filed to apply the machine learning based corrosion analysis methodology of Pang to the risk tool of Zahacy, specifically to augment Zahacy's corrosion modeling, in order to provide better accuracy than empirical models (¶50 of Pang explicitly identifies this as an advantage in those words).
Zahacy does not teach in particular, but Lang teaches:
It would have been obvious to one of ordinary skill in the art at the time the invention was filed to apply the drillsite identification and selection of Lang to the prioritized production well result of Zahacy as modified by Pang, in order to enable the system to identify well targets in a faster, less labor intensive, more comprehensive, and automated manner (Lang, ¶2).
Regarding Claims 4, 11, and 17:
Zahacy teaches:
wherein the well corrosion values may be historical well corrosion values that are obtained over time or predicted well corrosion values. (examiner notes that this is phrased as an optional limitation ("may be") and is not actually limited, but is being mapped to the art anyway for compact prosecution; Conclusions, The weighted factor approach used as the basis for estimating the individual damage mechanism and failure rates is highly adaptable, with weighting factors based on historical data of the specific scenario; examiner notes that in the combination of references, historical data would include historical corrosion data due to the combination of the teachings of Pang as discussed above for claim 1.)
Regarding Claims 6, 13, and 19:
Zahacy does not teach in particular, but Pang teaches:
wherein the well corrosion values and the well barrier parameters are preprocessed before being inputted into the machine learning model. (¶14 the multi-objective optimization combines Bayesian optimization with either machine learning models or empirical models to optimize scaling and corrosion.; ¶49 At step 212, a “real” corrosion rate Vbase is calculated at points along the wellbore. Vbase is considered to be the “real” corrosion rate because it takes into account both corrosion and calcite scaling; ¶61 using machine learning to determine Vbase and Is, wherein the step of using machine learning comprises using a Deep Neural Network.; ¶58 electing optimization points from the ranges of Vbase and Is obtained from the base calculation, and performing a multi-objective optimization for the selected optimization points of Vbase and Is. The method further comprises controlling an alkalinity and flow rate of the fluid based on the multi-objective optimization.)
Claims 3, 10, and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Zahacy (Zahacy, T. A., & Demirdal, B. (2019, September). Risk-ranking approach for thermal well integrity using readily available application, well and operational parameters. In SPE Annual Technical Conference and Exhibition? (p. D012S064R001). SPE.) in view of Pang (US 20220112799 A1) and Lang (US 20220372846 A1), and further in view of Halabi (US 20180321421 A1)
Regarding Claims 3, 10, and 16:
Zahacy does not teach in particular, but Lang teaches:
wherein the wells are classified into predetermined groups based on the well criticality features, (¶66 a domain informed classification that “poor” targets are close (in the embedding space) to a slice of all-zeros opportunity index, “acceptable” targets are close to a slice of all-ones opportunity indexes, and “good” targets are close to a slice of all-twos opportunity indexes.)
It would have been obvious to one of ordinary skill in the art at the time the invention was filed to apply the drillsite identification and selection of Lang to the prioritized production well result of Zahacy as modified by Pang, in order to enable the system to identify well targets in a faster, less labor intensive, more comprehensive, and automated manner (Lang, ¶2).
Zahacy does not teach in particular, but Halabi teaches:
wherein, a multiplier is assigned to each predetermined group, and (¶86 objective function accounted for according to product of weightages; ¶131 an objective function can accounts for equipment condition. In such an example, the objective function can be penalized for equipment failure. In such an example, the objective function can account for time, which may be, for example, a period of years. In such an example, where one or more pieces of equipment deteriorate in their condition, failure may occur, which can then penalize the objective function such that an optimization process may seek alternatives where equipment failure does not occur, does not occur to such an extent, is delayed in time (e.g., to a lower production rate period of time), etc. As an example, data and/or models of equipment condition may be received and utilized as part of a method.)
wherein, the well priority rank is calculated by multiplying the corrosion severity rank and the multiplier. (examiner notes that in the combination of references, the Pang reference in combination with the Zahacy reference renders it obvious to consider corrosion as part of equipment condition over time, and that the Halabe reference explicitly identifies corrosion as a consideration (¶113 corrosion analysis), and in the resulting combination the groups of Lang would be analyzed in the objective function of Halabe, with the penalty terms of Halabe applying at least in part to the corrosion analysis of Zahacy in view of Pang - see Halabe ¶131 an objective function can accounts for equipment condition. In such an example, the objective function can be penalized for equipment failure. In such an example, the objective function can account for time, which may be, for example, a period of years. In such an example, where one or more pieces of equipment deteriorate in their condition, failure may occur, which can then penalize the objective function such that an optimization process may seek alternatives where equipment failure does not occur, does not occur to such an extent, is delayed in time (e.g., to a lower production rate period of time), etc. As an example, data and/or models of equipment condition may be received and utilized as part of a method.; see also Halabi ¶86 objective function accounted for according to product of weightages)
It would have been obvious to one of ordinary skill in the art at the time the invention was filed to apply the objective function analysis of Halabi to the analysis system of Zahacy as modified above, specifically by integrating the above combination's corrosion analysis within Halabi's equipment condition terms in the objective function, in order to achieve more accurate forecasts (¶83 Halabi) and thereby generate better field operations plans (Halabi, Abstract).
Claims 5, 12, and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Zahacy (Zahacy, T. A., & Demirdal, B. (2019, September). Risk-ranking approach for thermal well integrity using readily available application, well and operational parameters. In SPE Annual Technical Conference and Exhibition? (p. D012S064R001). SPE.) in view of Pang (US 20220112799 A1) and Lang (US 20220372846 A1), and further in view of Kim (KR 20180047073 A)
Regarding Claims 5, 12, and 18:
Zahacy does not teach in particular, but Kim teaches:
wherein the predicted well corrosion values are generated using Kriging technique that generates corrosion log values at unmeasured location within a spatial domain based on measured values at similar locations. (It is an object of the present invention to provide a method for easily and accurately predicting the corrosion rate by predicting the corrosion rate using a kriging model used in geostatistics based on actual plant data.)
It would have been obvious to one of ordinary skill in the art at the time the invention was filed to apply the Kriging based corrosion determination of Kim to the corrosion analysis of Zahacy as modified above, specifically by applying it to the wellbore under consideration by Zahacy and Pang, in order to better anticipate the extent of corrosion (Kim, third paragraph).
Claims 7 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Zahacy (Zahacy, T. A., & Demirdal, B. (2019, September). Risk-ranking approach for thermal well integrity using readily available application, well and operational parameters. In SPE Annual Technical Conference and Exhibition? (p. D012S064R001). SPE.) in view of Pang (US 20220112799 A1) and Lang (US 20220372846 A1), and further in view of Yang (US 11715151 B2)
Regarding Claims 7 and 20:
Zahacy does not teach in particular, but Yang teaches:
wherein the machine learning model uses pointwise learn to rank algorithm. (col 11 line 60-70, n many embodiments, a learning-to-rank algorithm can rank items using a pointwise algorithm. In some embodiments, a pointwise algorithm can determine a similarity score for one embedding at a time. In various embodiments, a pointwise algorithm can comprise training a binary classifier or a regressor on user engagement data to determine a similarity score for an embedding. A final ranking of embeddings can then be determined using the similarity score as compared to an embedding for a specific item.)
It would have been obvious to one of ordinary skill in the art at the time the invention was filed to apply the pointwise algorithm and learning to rank algorithm of Yang to the risk tool of Zahacy as modified above, specifically to the combination's machine learning, in order to avoid recurring inaccurate predictions and therefore a degradation in system quality (Yang, col 1 line 40-45)
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BIJAN MAPAR whose telephone number is (571)270-3674. The examiner can normally be reached Monday - Thursday, 11:00-8:30.
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, Rehana Perveen can be reached at 571-272-3676. 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.
/BIJAN MAPAR/ Primary Examiner, Art Unit 2189
Prosecution Insights