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 .
Responsive to communications filed 1/12/2024
Claims under examination 1-20 are pending in this application
Claims 1-20 are rejected
Claims 1, 2, and 13 are objected to
Priority
No claims for foreign or domestic priority made in Application data sheet filed on 8/22/2022. Application given priority date of 8/22/2022
Information Disclosure Statement
IDS forms filed on 8/22/2022 and 1/12/2024 were reviewed by examiner and taken into consideration.
Drawings
The drawings are objected to as failing to comply with 37 CFR 1.84(p)(4) because reference character “123” in fig 1. has been used to designate in par 42 both “a sensor assembly” as well as “a processor assembly”. Examiner notes that while these may be intended to be the same device, it would promote clarity to explain as such in the specification.
The drawings are objected to as failing to comply with 37 CFR 1.84(p)(4) because reference character “900” in fig 9 has been used to designate both a “computational graph” in par 81 as well as a “network” in par 82. Examiner again notes that while these may be intended to be the same device, since the computational graph was given as an example of a network diagram, the specifications should be clearer since “950” is also referred to as “the network”.
Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Specification
Abstract received on 08/22/2022 is 7 lines long with 95 words and does not contain any legal phraseology.
The disclosure is objected to because of the following informalities:
Paragraph 14 refers to an ontological framework as (OF). Paragraph 101 also refers to the objective function as (OF) when discussing the misfit OF. While the use of OF as objective function is precluded by the term misfit, it will be beneficial for clarity to specific or change the acronym accordingly.
In paragraph 68, the specification states “muti-rate test points 368,” this was likely supposed to be “multi-rate test points (368).”
Appropriate correction is required.
Claim Objections
Claims 1,2 and 13 objected to because of the following informalities:
In claim 2, “render statically accurate success failure decision,” was likely meant to be written as “render statistically accurate success failure decisions.” The examiner is interpreting the claim as “statistically accurate”
Claims 1 and 13 reference “as instructed by the decision information” in the final limitation of the claim without specifying that it is the decision information from the “updated knowledge graph.” Examiner recommends specifying where the decision information comes from for clarity. Examiner is interpreting the decision information as coming from the updated knowledge graph logic.
Claims 1 and 13 reference “the decision information from the updated knowledge graph.” It is unclear as to where the antecedent basis is coming from in “the decision information”, as the applicant likely is not referring to the earlier incomplete knowledge graph logic. Examiner recommends specifying that this is new updated decision information to provide clarity for what is being referred to. Examiner is interpreting this line to be “obtaining
Appropriate correction is required.
Claim Interpretation
The examiner would like to make note of how terms in the claims are interpreted with respect to the specification and as understood by one of ordinary skill in the art before the effective filing date.
Knowledge graph logic: Par 149:” the KG logic represents an exhaustive library or sequence of steps related to reservoir engineering tasks.”
Knowledge graph logic for failure/ success: “par: 149 The KG logic for failure, updated in Step 2016, may represent an exhaustive library or sequence of steps that lead to an increase (examiner note: or decrease for success) of a (global) misfit objective function.”
Completeness: Can be determined by many criteria, but is ultimately “ par 131: based on the ability to render a statistically accurate success/failure decision or prediction. “
Parameterization: Table 6 depicts parametrization. Parameterization is interpreted in light of specifications as well as the art as the tuning of parameters to help achieve a result. For example, in table 6, “fracture orientation” was parameterized into Variogram_Major, Variogram_minor, and Variogram_Vertical. This can be achieved by modifying weights, splitting up parameters, etc.
sensitivity analysis: A sensitivity analysis is done to determine how sensitive the model is to changes from certain input parameters. For example, in fig 23A it was shown through a sensitivity analysis that is it “par 138: matrix compressibility which affects the field pressure response the most”
stochastically sampled full parameter sets: Using a stochastic sampling technique to determine the set of parameters to be tested.
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 recites a judicial exception, an abstract idea, which has not been integrated into practical application and the claims further do not recite significantly more than the judicial exception.
Claim 1:
Step 1: Is the claimed invention one of the four statutory categories? YES. Claim 1 recites “A method for reservoir simulation, the method comprising:” which is a process.
Step 2:
Step 2A Prong 1, inquiry "does the claim recite a law of nature, a natural phenomenon or an abstract idea?": YES.
Claim 1 recites: "examining a knowledge graph logic associated with a reservoir simulation model for completeness”
As stated in the claim interpretation. An examination for completeness involves determining
whether or not a knowledge graph logic (which is a series of steps) has any missing steps that may lead to an inaccurate prediction by the knowledge graph logic. A knowledge graph may be presented in pen and paper alongside decision making such as in figures 22A – 22E of this application. For example par 166: “FIG. 22D shows an example of reasoning/decision making using sub-KGs. In the example(2230), geo&fracture model and a stratigraphic model provide multiple outputs. However, the outputs of the geo&fracture model are incomplete. The missing 3D permeability and 3D porosity are substituted using the corresponding outputs of the stratigraphic model.” This evaluation for completeness for a knowledge graph logic associated with a reservoir simulation model was done mentally with a pen and paper. Therefore this is an examination which can reasonably be performed in the mind by one ordinarily skilled in the art. This examination involves observing the KG logic and evaluating it for its completeness. “Accordingly, the "mental processes" abstract idea grouping is defined as concepts performed in the human mind, and examples of mental processes include observations, evaluations, judgments, and opinions. “ MPEP 2106.04(a)(2)(III). Because the limitation pertains to an evaluation, it recites the abstract idea of a mental process.
making a determination, (an evaluation) based on the examination, that the knowledge graph logic is incomplete; (a mental process) based on the determination, generating an updated knowledge graph logic; obtaining the decision information from the updated knowledge graph;
As stated above, the determination that a knowledge graph logic is incomplete is the mental processes of observation and evaluation. Generating an updated knowledge graph logic is the process of modifying the steps of an existing knowledge graph logic. For example, “decrease variable x in step 1” may become “increase variable x in step 1.” This involves making a determination based on examination (an evaluation), making a decision (a judgement) on what the updated knowledge graph logic (sequence of steps) should be. “Accordingly, the "mental processes" abstract idea grouping is defined as concepts performed in the human mind, and examples of mental processes include observations, evaluations, judgments, and opinions.” Lastly, obtaining the decision information from the updated knowledge graph is the process of following a sequence of steps and utilizing logic to get an answer. This is the mental process of deduction, which is when someone evaluates a series of logical steps to reach a conclusion. This is a mental process pertaining to an evaluation.
Step 2A Prong 2, Does the claim recite additional elements that integrate the judicial exception into a practical application? NO.
Claim 1 additionally recites wherein the knowledge graph logic comprises decision information that governs an execution of the reservoir simulation model;
As stated previously, the examination of a knowledge graph logic associated with a reservoir simulation model for completeness was found to be a mental process. The MPEP 2106.05(h) states that “ 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, and cannot integrate a judicial exception into a practical application.” One example given in the MPEP 2016.05(h) as merely indicating a field of use is “ Limiting the abstract idea of collecting information, analyzing it, and displaying certain results of the collection and analysis to data related to the electric power grid, because limiting application of the abstract idea to power-grid monitoring is simply an attempt to limit the use of the abstract idea to a particular technological environment.”
In this claim, limiting the abstract idea of examining a knowledge graph logic for completeness, by stating that wherein the knowledge graph logic comprises information that governs the execution of a reservoir simulation model, is merely indicating a field of use to apply a judicial exception, because it is simply an attempt to limit the use of the abstract idea to the particular technological environment of reservoir modeling, and therefore does not apply the judicial exception into a practical application nor does it amount to significantly more than the exception itself.
Claim 1 additionally recites executing the reservoir simulation model as instructed by the decision information.
As stated previously, the decision information is information gleaned via the mental process of deduction. The MPEP 2106.05(g) states that “The term "extra-solution activity" can be understood as activities incidental to the primary process or product that are merely a nominal or tangential addition to the claim.“ With one example of insignificant extra-solution activity being “Cutting hair after first determining the hair style.” MPEP 2106.05(g).
Cutting hair after first determining hair style can be understood as executing the process of hair cutting as instructed by the hair style decision information. Executing the reservoir simulation model as instructed by the decision information is therefore insignificant extra-solution activity and does not meaningfully limit the claim as it is a process that is tangentially related to the rest of the claim which pertains to generating knowledge graph logic and does not purpose a significant limitation to that process. This limitation does not integrate a judicial exception into a practical application.
Step 2B, does the claim recites additional elements that amount to significantly more than the judicial exception. NO.
According to the MPEP 2106.05(g) “ the addition of insignificant extra-solution activity does not amount to an inventive concept, particularly when the activity is well-understood or conventional.” As stated, the insignificant extra-solution activity of “executing the reservoir simulation model as instructed by the decision information “ is by definition conventional, as the decision information is defined as “decision information that governs an execution of the reservoir simulation model.” Whereas it is obvious and well understood that decision information that governs an execution of a reservoir simulation model would be used to govern the execution of a simulation model.
Secondly, The MPEP 2106.05(h) states that “ 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, and cannot integrate a judicial exception into a practical application.”
Based off of the above facts the office concludes that claim 1 is not eligible under 35 USC 101.
Claim 2:
Step 1: Is the claimed invention one of the four statutory categories? YES. This claim depends on Claim 1 which recites “A method for reservoir simulation, the method comprising:” which is a process.
Step 1: Is the claimed invention one of the four statutory categories? YES. This claim depends on claim 13 which recites “A non-transitory machine-readable medium”: which is a manufacture.
Step 2:
Step 2A Prong 1, inquiry "does the claim recite a law of nature, a natural phenomenon or an abstract idea?": YES.
, wherein the examination of the knowledge graph logic for completeness is performed based on one selected from a group consisting of an ability to render statically accurate success failure decisions and an ability to render statistically accurate predictions, by the reservoir simulation model.
As stated under claim 1, the examination for completeness is a mental process. en.et al in “Knowledge Graph Completion: A Review” (Chen_2020) discusses information relating to knowledge graph completion. Chen_2020 states in page 16 col 2 par 2 “Commonly used knowledge graph completion task evaluation indicators include Hits@k, Mean Rank (MR), and Mean Reciprocal Rank (MRR) .” Chen_2020 then outlines these methodologies as equations (12, 13, and 14) for example page 16 col 2 par 4: “Mean Reciprocal Rank scores the predicted triples based on whether they are true or not. If the first predicted triple is true, its score is 1, and the second true score is 1/2, and so on. When
the n-th triplet is established, it is scored 1/n, and the final MRR value is the sum of all the scores. The calculation formula is shown in Equation (14). “(examiner note: this is the ability to render statistically accurate predictions)
PNG
media_image1.png
89
533
media_image1.png
Greyscale
As outlined, this method for completeness performed based on one selected from a group consisting of an ability to render statically accurate success failure decisions and an ability to render statistically accurate prediction is adding a mathematic calculation to be performed as outlined to an existing mental process. Therefore this limitation further recites an abstract idea.
Step 2A Prong 2, Does the claim recite additional elements that integrate the judicial exception into a practical application? NO. This limitation does not recite additional elements beyond the abstract idea.
Step 2B, does the claim recites additional elements that amount to significantly more than the judicial exception. NO. This limitation does not recite additional elements beyond the abstract idea.
Based off of the above facts the office concludes that claim 2 is not eligible under 35 USC 101.
Claim 3:
Step 1: Is the claimed invention one of the four statutory categories? YES. This claim depends on Claim 1 which recites “A method for reservoir simulation, the method comprising:” which is a process.
Step 2:
Step 2A Prong 1, inquiry "does the claim recite a law of nature, a natural phenomenon or an abstract idea?": YES.
wherein the knowledge graph logic comprises knowledge graph logic for success and knowledge graph logic for failure.
As stated under claim 1, the examination and determination for completeness/incompleteness, as well as the updating of the knowledge graph logic are all mental processes under observations and deductions. The knowledge graph logic for success is the list of steps that lead to a successful predication, while the knowledge graph logic for failure is the list of steps that led to an inaccurate prediction. As stated in claim 1, it is reasonable for one to follow a knowledge graph logic with a pen and paper to make deductions. It would also be reasonable for one in the art to draw two separate knowledge graph logic (series of steps) which led to success or failure. Therefore this limitation does not take claim 1 outside the realm of a mental process.
Step 2A Prong 2, Does the claim recite additional elements that integrate the judicial exception into a practical application? NO. This limitation does not recite additional elements beyond the abstract idea.
Step 2B, does the claim recites additional elements that amount to significantly more than the judicial exception. NO. This limitation does not recite additional elements beyond the abstract idea.
Based off of the above facts the office concludes that claim 3 is not eligible under 35 USC 101.
Claim 4:
Step 1: Is the claimed invention one of the four statutory categories? YES. This claim depends on Claim 1 which recites “A method for reservoir simulation, the method comprising:” which is a process.
Step 2:
Step 2A Prong 1, inquiry "does the claim recite a law of nature, a natural phenomenon or an abstract idea?": YES.
wherein the reservoir simulation model is one selected from a group consisting of a classifier model and a regression model.
A classifier and a regression model are simply mathematical models. As stated in claim 1, the recitation of “executing the reservoir simulation model as instructed by the decision information” was simply applying the mental process for its obvious use. The reservoir simulation model being a classifier or regression model does claim a more particular way to achieve an outcome, i.e.: a regression calculation will be applied; however, it is noted that a regression and classification model is simply the use of a mathematical equation to compute a value. Bobbitt in the article “How to Perform a Linear Regression by Hand (Bobbitt_2020) outlines how a regression model calculation can be performed with a pen and paper. Therefore, a linear regression can be easily calculated by hand to determine decision information based on the output. Because this limitation pertains to mathematic calculations that can easily be performed in the mind, the limitation does not take claim 1 outside the realm of a mental process.
Step 2A Prong 2, Does the claim recite additional elements that integrate the judicial exception into a practical application? NO. This limitation does not recite additional elements beyond the abstract idea.
Step 2B, does the claim recites additional elements that amount to significantly more than the judicial exception. NO. This limitation does not recite additional elements beyond the abstract idea.
Based off of the above facts the office concludes that claim 4 is not eligible under 35 USC 101.
Claim 5:
Step 1: Is the claimed invention one of the four statutory categories? YES. This claim depends on Claim 1 which recites “A method for reservoir simulation, the method comprising:” which is a process.
Step 2:
Step 2A Prong 1, inquiry "does the claim recite a law of nature, a natural phenomenon or an abstract idea?": YES.
executing, using a parameterization, the reservoir simulation model to reduce a misfit;
The reservoir simulation model under its broadest reasonable interpretation can include a regression model. Executing a regression model to reduce a misfit (delta between calculated and expected value) by using parameterization (modifying parameters and weights) is simply a recitation of math which can be performed with pen and paper. Therefore this claim pertains to an abstract idea.
and when the execution of the reservoir simulation model fails to result in a reduction of the misfit, updating the knowledge graph logic with knowledge graph logic for failure, based on the parameterization.
Updated a knowledge graph logic based on parameterization can include changing the weights of the regression model, which can be done with pen and paper. For instance, we can take the regression model done by hand as taught by Bobbitt_2020 page 3: “y=32.783 + 0.2001x” and change the weight to “y=32 + 0.3x” which effectively changes the logic. Updating the knowledge graph for failure means simply updating the graph with steps which led to the failure. Therefore this limitation pertains to a mental process.
Step 2A Prong 2, Does the claim recite additional elements that integrate the judicial exception into a practical application? NO. This limitation does not recite additional elements beyond the abstract idea.
Step 2B, does the claim recites additional elements that amount to significantly more than the judicial exception. NO. This limitation does not recite additional elements beyond the abstract idea.
Based off of the above facts the office concludes that claim 5 is not eligible under 35 USC 101.
Claim 6:
Step 1: Is the claimed invention one of the four statutory categories? YES. This claim depends on Claim 1 which recites “A method for reservoir simulation, the method comprising:” which is a process.
Step 2:
Step 2A Prong 1, inquiry "does the claim recite a law of nature, a natural phenomenon or an abstract idea?": YES.
wherein the parameterization is determined using a sensitivity analysis.
A sensitivity analysis involves a statistical method that observes how a change in one variable impacts the outcome of the model. For a model built on regression for example, this sensitivity analysis is a mathematical procedure (i.e.: changing variable x and observing change in output y). This is similar to what was discussed in claim 5. This claim limitation recites math which is an abstract idea and does not limit the scope of the claim beyond that abstract idea.
Step 2A Prong 2, Does the claim recite additional elements that integrate the judicial exception into a practical application? NO. This limitation does not recite additional elements beyond the abstract idea.
Step 2B, does the claim recites additional elements that amount to significantly more than the judicial exception. NO. This limitation does not recite additional elements beyond the abstract idea.
Based off of the above facts the office concludes that claim 6 is not eligible under 35 USC 101.
Claim 7:
Step 1: Is the claimed invention one of the four statutory categories? YES. This claim depends on Claim 1 which recites “A method for reservoir simulation, the method comprising:” which is a process.
Step 2:
Step 2A Prong 1, inquiry "does the claim recite a law of nature, a natural phenomenon or an abstract idea?": YES.
executing, using a parameterization, the reservoir simulation model to reduce a misfit;
If the reservoir simulation model includes a regression or classification model, then the usage of that model to reduce a misfit using a parametrization is simply a mathematical calculation. For instance, modifying parameter x results in predicted value y. The misfit can be interpreted as the delta between y and real-world historic data. Modifying parameter x to reduce the delta is the execution of the reservoir simulation model to reduce a misfit. For the example of Bobbitt_2020, this would be plugging in a test value into the equation in page 3: y = 32.784 + 0.2001x (which describes a relationship between height and weight) and drawing a comparison to a real individual’s height and weight, with the purpose of minimizing that difference. This process as described is the mathematical recitation of equation finding to reduce a delta y, which is an abstract math recitation and does not limit the scope of the claim beyond an abstract idea.
and when the execution of the reservoir simulation model results in a reduction of the misfit, updating the knowledge graph logic with knowledge graph logic for success, based on the parameterization.
As stated earlier in claim 5, updating a knowledge graph logic can be simply changing the weights of the regression model, which can be done with pen and paper. Updating a knowledge graph logic for success is changing the steps the reservoir model takes to produce a successful result. Both these processes as described are mental processes as stated earlier, and therefore do not limit the scope of the claim beyond a mental process
Step 2A Prong 2, Does the claim recite additional elements that integrate the judicial exception into a practical application? NO. This limitation does not recite additional elements beyond the abstract idea.
Step 2B, does the claim recites additional elements that amount to significantly more than the judicial exception. NO. This limitation does not recite additional elements beyond the abstract idea.
Based off of the above facts the office concludes that claim 7 is not eligible under 35 USC 101.
Claim 8:
Step 1: Is the claimed invention one of the four statutory categories? YES. This claim depends on Claim 1 which recites “A method for reservoir simulation, the method comprising:” which is a process.
Step 2:
Step 2A Prong 1, inquiry "does the claim recite a law of nature, a natural phenomenon or an abstract idea?": YES.
performing simulation runs of the reservoir simulation model using stochastically sampled full parameter sets of the reservoir simulation model to identify a highest-ranked full parameter set of the reservoir simulation model; and
A simulation run of the reservoir model for a regression model can be as simple as plugging in values into an equation to produce a result, which is a mathematic calculation and is a mental process as shown by Bobbit_2020. Stochastically sampled parameter sets are parameter sets which are achieved through a statistical methods which is also a mathematical process. Identifying a highest ranked parameter set is done by plugging in the different parameter sets into the regression model to determine which set results in the greatest reduction in a misfit. As stated previously, this calculation is a recitation of math.
updating the knowledge graph logic with knowledge graph logic for success, based on the simulation runs.
As stated previously in claim 7 and 17, updating a knowledge graph logic for success is the mental process of either changing weights or logical steps in a knowledge graph, which is a mental process.
Step 2A Prong 2, Does the claim recite additional elements that integrate the judicial exception into a practical application? NO. This limitation does not recite additional elements beyond the abstract idea.
Step 2B, does the claim recites additional elements that amount to significantly more than the judicial exception. NO. This limitation does not recite additional elements beyond the abstract idea.
Based off of the above facts the office concludes that claim 8 is not eligible under 35 USC 101.
Claim 9:
Step 1: Is the claimed invention one of the four statutory categories? YES. This claim depends on Claim 1 which recites “A method for reservoir simulation, the method comprising:” which is a process.
Step 2:
Step 2A Prong 1, inquiry "does the claim recite a law of nature, a natural phenomenon or an abstract idea?": YES.
wherein updating the knowledge graph logic based on the simulation runs comprises: aggregating model parameters identified with the highest impact on model dynamic response;
As stated in claim 8, performing simulation runs of the reservoir simulation model using stochastically sampled full parameter sets of the reservoir simulation model to identify a highest-ranked full parameter set of the reservoir simulation model was found to be a mental process. Similarly, aggregating parameters identified with the highest impact on model dynamic response is using the sensitivity analysis to isolate parameters and test how modifying them influences the model’s response. Since the model encompasses a regression model, which can be calculated by hand, this is a mathematic response to a change in the variable. As stated in claim 6, this is changing variable x and observing change in output y, and then selecting from different variables which produced the greatest delta y. This is a mathematic recitation.
and performing a refinement simulation run of the reservoir simulation model for the model parameters with the highest impact.
A refinement simulation run of the model for the parameters with the highest impact is simply executing the model with the newly aggregated parameters. This is likely done to fine tune the parameters further to produce a more idealized model that reduces the misfit by isolating the most influential parameters. As stated in claims 6 and 7, executing the model, whether it be to reduce a misfit or to do a sensitivity analysis, encompasses a mathematical recitation.
Step 2A Prong 2, Does the claim recite additional elements that integrate the judicial exception into a practical application? NO. This limitation does not recite additional elements beyond the abstract idea.
Step 2B, does the claim recites additional elements that amount to significantly more than the judicial exception. NO. This limitation does not recite additional elements beyond the abstract idea.
Based off of the above facts the office concludes that claim 9 is not eligible under 35 USC 101.
Claim 10:
Step 1: Is the claimed invention one of the four statutory categories? YES. This claim depends on Claim 1 which recites “A method for reservoir simulation, the method comprising:” which is a process.
Step 2:
Step 2A Prong 1, inquiry "does the claim recite a law of nature, a natural phenomenon or an abstract idea?": YES.
wherein updating the knowledge graph logic based on the simulation runs further comprises:
confirming that the misfit is reduced.
A confirmation that the misfit is reduced is a comparison between two different delta y’s, where the delta y is calculated by some mathematical method between the observed y and calculated y. (i.e.: difference of squares, or absolute value of difference). This is a mathematic recitation and observation which is an abstract idea.
Step 2A Prong 2, Does the claim recite additional elements that integrate the judicial exception into a practical application? NO. This limitation does not recite additional elements beyond the abstract idea.
Step 2B, does the claim recites additional elements that amount to significantly more than the judicial exception. NO. This limitation does not recite additional elements beyond the abstract idea.
Based off of the above facts the office concludes that claim 10 is not eligible under 35 USC 101.
Claim 11
Step 1: Is the claimed invention one of the four statutory categories? YES. This claim depends on Claim 1 which recites “A method for reservoir simulation, the method comprising:” which is a process.
Step 1: Is the claimed invention one of the four statutory categories? YES. This claim depends on claim 13 which recites “A non-transitory machine-readable medium”: which is a manufacture.
Step 2:
Step 2A Prong 1, inquiry "does the claim recite a law of nature, a natural phenomenon or an abstract idea?": YES.
The method of claim 1, wherein the reservoir simulation model is for one selected from a group consisting of a history matching task and a field development planning task.
A history matching task is attempting to match the simulation model to field production data. This is done by modifying the simulation parameters to reduce a misfit. As described in claim 1 as well as the claims above, executing the simulation model in general, or to reduce a misfit, is encompassed by a regression calculation which can be done by hand with a piece of paper.
Step 2A Prong 2, Does the claim recite additional elements that integrate the judicial exception into a practical application? NO. This limitation does not recite additional elements beyond the abstract idea.
Step 2B, does the claim recites additional elements that amount to significantly more than the judicial exception. NO. This limitation does not recite additional elements beyond the abstract idea.
Based off of the above facts the office concludes that claim 11 is not eligible under 35 USC 101.
Claim 12
Step 1: Is the claimed invention one of the four statutory categories? YES. This claim depends on Claim 1 which recites “A method for reservoir simulation, the method comprising:” which is a process.
Step 1: Is the claimed invention one of the four statutory categories? YES. This claim depends on claim 13 which recites “A non-transitory machine-readable medium”: which is a manufacture.
Step 2:
Step 2A Prong 1, inquiry "does the claim recite a law of nature, a natural phenomenon or an abstract idea?": YES.
Claim 12 depends on claim which recites an abstract idea.
Step 2A Prong 2, Does the claim recite additional elements that integrate the judicial exception into a practical application? NO.
The method of claim 1, further comprising updating one selected from a group consisting of drilling parameters and production parameters based on a result of executing the reservoir simulation model.
Updating the simulation model to change parameters is the execution of the simulation model, for example to reduce a misfit. As discussed under “sensitivity analysis” in claim 6, the modification of parameters to cause a change in the model is the mathematical process of changing parameter x to decrease a delta y, where delta y represents the difference between a target y value and a calculated y value. This is the mathematical process of modifying parameters. The examiner believes that the recitation of updating drilling parameters or production parameters is a mere instruction to apply an exception. The MPEP 2106.05(f)(1) states “ Whether the claim recites only the idea of a solution or outcome i.e., the claim fails to recite details of how a solution to a problem is accomplished. The recitation of claim limitations that attempt to cover any solution to an identified problem with no restriction on how the result is accomplished and no description of the mechanism for accomplishing the result, does not integrate a judicial exception into a practical application or provide significantly more because this type of recitation is equivalent to the words ‘apply it’.” Because the claim states “updating” without restriction of how the updating is accomplished, the claim limitation is merely “apply it” instructions to use the judicial exception of mathematics for modifying parameters to these parameters.
Step 2B, does the claim recites additional elements that amount to significantly more than the judicial exception. NO.
As stated, the use of “apply it” instructions does not provide significantly more.
Based off of the above facts the office concludes that claim 12 is not eligible under 35 USC 101.
Claim 13:
Step 1: Is the claimed invention one of the four statutory categories? YES. Claim 13 recites “A non-transitory machine-readable medium comprising a plurality of machine-readable instructions executed by one or more processors, the plurality of machine-readable instructions causing the one or more processors to perform operations comprising: which is a manufacture.
Step 2:
Step 2A Prong 1, inquiry "does the claim recite a law of nature, a natural phenomenon or an abstract idea?": YES.
Claim 13 recites: "examining a knowledge graph logic associated with a reservoir simulation model for completeness”
As stated in the claim interpretation. An examination for completeness involves determining
whether or not a knowledge graph logic (which is a series of steps) has any missing steps that may lead to an inaccurate prediction by the knowledge graph logic. A knowledge graph may be presented in pen and paper alongside decision making such as in figures 22A – 22E of this application. For example par 166: “FIG. 22D shows an example of reasoning/decision making using sub-KGs. In the example(2230), geo&fracture model and a stratigraphic model provide multiple outputs. However, the outputs of the geo&fracture model are incomplete. The missing 3D permeability and 3D porosity are substituted using the corresponding outputs of the stratigraphic model.” This evaluation for completeness for a knowledge graph logic associated with a reservoir simulation model was done mentally with a pen and paper. Therefore this is an examination which can reasonably be performed in the mind by one ordinarily skilled in the art. This examination involves observing the KG logic and evaluating it for its completeness. “Accordingly, the "mental processes" abstract idea grouping is defined as concepts performed in the human mind, and examples of mental processes include observations, evaluations, judgments, and opinions. “ MPEP 2106.04(a)(2)(III). Because the limitation pertains to an evaluation, it recites the abstract idea of a mental process.
making a determination, (an evaluation) based on the examination, that the knowledge graph logic is incomplete; (a mental process) based on the determination, generating an updated knowledge graph logic; obtaining the decision information from the updated knowledge graph;
As stated above, the determination that a knowledge graph logic is incomplete is the mental processes of observation and evaluation. Generating an updated knowledge graph logic is the process of modifying the steps of an existing knowledge graph logic. For example, “decrease variable x in step 1” may become “increase variable x in step 1.” This involves making a determination based on examination (an evaluation), making a decision (a judgement) on what the updated knowledge graph logic (sequence of steps) should be. “Accordingly, the "mental processes" abstract idea grouping is defined as concepts performed in the human mind, and examples of mental processes include observations, evaluations, judgments, and opinions.” Lastly, obtaining the decision information from the updated knowledge graph is the process of following a sequence of steps and utilizing logic to get an answer. This is the mental process of deduction, which is when someone evaluates a series of logical steps to reach a conclusion. This is a mental process pertaining to an evaluation.
Step 2A Prong 2, Does the claim recite additional elements that integrate the judicial exception into a practical application? NO.
Claim 13 additionally recites wherein the knowledge graph logic comprises decision information that governs an execution of the reservoir simulation model;
As stated previously, the examination of a knowledge graph logic associated with a reservoir simulation model for completeness was found to be a mental process. The MPEP 2106.05(h) states that “ 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, and cannot integrate a judicial exception into a practical application.” One example given in the MPEP 2016.05(h) as merely indicating a field of use is “ Limiting the abstract idea of collecting information, analyzing it, and displaying certain results of the collection and analysis to data related to the electric power grid, because limiting application of the abstract idea to power-grid monitoring is simply an attempt to limit the use of the abstract idea to a particular technological environment.”
In this claim, limiting the abstract idea of examining a knowledge graph logic for completeness, by stating that wherein the knowledge graph logic comprises information that governs the execution of a reservoir simulation model, is merely indicating a field of use to apply a judicial exception, because it is simply an attempt to limit the use of the abstract idea to the particular technological environment of reservoir modeling, and therefore does not apply the judicial exception into a practical application nor does it amount to significantly more than the exception itself.
Claim 13 additionally recites executing the reservoir simulation model as instructed by the decision information.
As stated previously, the decision information is information gleaned via the mental process of deduction. The MPEP 2106.05(g) states that “The term "extra-solution activity" can be understood as activities incidental to the primary process or product that are merely a nominal or tangential addition to the claim.“ With one example of insignificant extra-solution activity being “Cutting hair after first determining the hair style.” MPEP 2106.05(g).
Cutting hair after first determining hair style can be understood as executing the process of hair cutting as instructed by the hair style decision information. Executing the reservoir simulation model as instructed by the decision information is therefore insignificant extra-solution activity and does not meaningfully limit the claim as it is a process that is tangentially related to the rest of the claim which pertains to generating knowledge graph logic and does not purpose a significant limitation to that process. This limitation does not integrate a judicial exception into a practical application.
Claim 13 additional recites A non-transitory machine-readable medium comprising a plurality of machine-readable instructions executed by one or more processors, the plurality of machine-readable instructions causing the one or more processors to perform operations comprising:
This preamble states that the judicial exception is being performed by non-transitory machine-readable mediums executed by computer processors. “simply adding a general-purpose computer or computer components after the fact to an abstract idea (e.g., a fundamental economic practice or mathematical equation) does not integrate a judicial exception into a practical application or provide significantly more. “ MPEP 2106.05f(2). Therefore this limitation does not integrate a judicial exception into a practical application
Step 2B, does the claim recites additional elements that amount to significantly more than the judicial exception. NO.
According to the MPEP 2106.05(g) “ the addition of insignificant extra-solution activity does not amount to an inventive concept, particularly when the activity is well-understood or conventional.” As stated, the insignificant extra-solution activity of “executing the reservoir simulation model as instructed by the decision information “ is by definition conventional, as the decision information is defined as “decision information that governs an execution of the reservoir simulation model.” Whereas it is obvious and well understood that decision information that governs an execution of a reservoir simulation model would be used to govern the execution of a simulation model.
Secondly, The MPEP 2106.05(h) states that “ 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, and cannot integrate a judicial exception into a practical application.”
Lastly, simply adding a general-purpose computer or computer components after the fact to an abstract idea (e.g., a fundamental economic practice or mathematical equation) does not integrate a judicial exception into a practical application or provide significantly more.
Therefore the additional elements in the claim do not amount to significantly more than the judicial exception.
Based off of the above facts the office concludes that claim 13 is not eligible under 35 USC 101.
Claim 14:
, wherein the examination of the knowledge graph logic for completeness is performed based on one selected from a group consisting of an ability to render statically accurate success failure decisions and an ability to render statistically accurate predictions, by the reservoir simulation model.
Step 1: Is the claimed invention one of the four statutory categories? YES. This claim depends on claim 13 which recites “A non-transitory machine-readable medium”: which is a manufacture.
Step 2:
Step 2A Prong 1, inquiry "does the claim recite a law of nature, a natural phenomenon or an abstract idea?": YES.
As stated under 13, the examination for completeness is a mental process. en.et al in “Knowledge Graph Completion: A Review” (Chen_2020) discusses information relating to knowledge graph completion. Chen_2020 states in page 16 col 2 par 2 “Commonly used knowledge graph completion task evaluation indicators include Hits@k, Mean Rank (MR), and Mean Reciprocal Rank (MRR) .” Chen_2020 then outlines these methodologies as equations (12, 13, and 14) for example page 16 col 2 par 4: “Mean Reciprocal Rank scores the predicted triples based on whether they are true or not. If the first predicted triple is true, its score is 1, and the second true score is 1/2, and so on. When
the n-th triplet is established, it is scored 1/n, and the final MRR value is the sum of all the scores. The calculation formula is shown in Equation (14). “(examiner note: this is the ability to render statistically accurate predictions)
PNG
media_image1.png
89
533
media_image1.png
Greyscale
As outlined, this method for completeness performed based on one selected from a group consisting of an ability to render statically accurate success failure decisions and an ability to render statistically accurate prediction is adding a mathematic calculation to be performed as outlined to an existing mental process. Therefore this limitation further recites an abstract idea.
Step 2A Prong 2, Does the claim recite additional elements that integrate the judicial exception into a practical application? NO. This limitation does not recite additional elements beyond the abstract idea.
Step 2B, does the claim recites additional elements that amount to significantly more than the judicial exception. NO. This limitation does not recite additional elements beyond the abstract idea.
Based off of the above facts the office concludes that claim 14 is not eligible under 35 USC 101.
Claim 15:
Step 1: Is the claimed invention one of the four statutory categories? YES. This claim depends on claim 13 which recites “A non-transitory machine-readable medium”: which is a manufacture.
Step 2:
Step 2A Prong 1, inquiry "does the claim recite a law of nature, a natural phenomenon or an abstract idea?": YES.
executing, using a parameterization, the reservoir simulation model to reduce a misfit;
The reservoir simulation model under its broadest reasonable interpretation can include a regression model. Executing a regression model to reduce a misfit (delta between calculated and expected value) by using parameterization (modifying parameters and weights) is simply a recitation of math which can be performed with pen and paper. Therefore this claim pertains to an abstract idea.
and when the execution of the reservoir simulation model fails to result in a reduction of the misfit, updating the knowledge graph logic with knowledge graph logic for failure, based on the parameterization.
Updated a knowledge graph logic based on parameterization can include changing the weights of the regression model, which can be done with pen and paper. For instance, we can take the regression model done by hand as taught by Bobbitt_2020 page 3: “y=32.783 + 0.2001x” and change the weight to “y=32 + 0.3x” which effectively changes the logic. Updating the knowledge graph for failure means simply updating the graph with steps which led to the failure. Therefore this limitation pertains to a mental process.
Step 2A Prong 2, Does the claim recite additional elements that integrate the judicial exception into a practical application? NO. This limitation does not recite additional elements beyond the abstract idea.
Step 2B, does the claim recites additional elements that amount to significantly more than the judicial exception. NO. This limitation does not recite additional elements beyond the abstract idea.
Based off of the above facts the office concludes that claim 15 is not eligible under 35 USC 101.
Claim 16:
Step 1: Is the claimed invention one of the four statutory categories? YES. This claim depends on claim 13 which recites “A non-transitory machine-readable medium”: which is a manufacture.
Step 2:
Step 2A Prong 1, inquiry "does the claim recite a law of nature, a natural phenomenon or an abstract idea?": YES.
wherein the parameterization is determined using a sensitivity analysis.
A sensitivity analysis involves a statistical method that observes how a change in one variable impacts the outcome of the model. For a model built on regression for example, this sensitivity analysis is a mathematical procedure (i.e.: changing variable x and observing change in output y). This is similar to what was discussed in claim 15. This claim limitation recites math which is an abstract idea and does not limit the scope of the claim beyond that abstract idea.
Step 2A Prong 2, Does the claim recite additional elements that integrate the judicial exception into a practical application? NO. This limitation does not recite additional elements beyond the abstract idea.
Step 2B, does the claim recites additional elements that amount to significantly more than the judicial exception. NO. This limitation does not recite additional elements beyond the abstract idea.
Based off of the above facts the office concludes that claim 16 is not eligible under 35 USC 101.
Claim 17:
Step 1: Is the claimed invention one of the four statutory categories? YES. This claim depends on claim 13 which recites “A non-transitory machine-readable medium”: which is a manufacture.
Step 2:
Step 2A Prong 1, inquiry "does the claim recite a law of nature, a natural phenomenon or an abstract idea?": YES.
executing, using a parameterization, the reservoir simulation model to reduce a misfit;
If the reservoir simulation model includes a regression or classification model, then the usage of that model to reduce a misfit using a parametrization is simply a mathematical calculation. For instance, modifying parameter x results in predicted value y. The misfit can be interpreted as the delta between y and real-world historic data. Modifying parameter x to reduce the delta is the execution of the reservoir simulation model to reduce a misfit. For the example of Bobbitt_2020, this would be plugging in a test value into the equation in page 3: y = 32.784 + 0.2001x (which describes a relationship between height and weight) and drawing a comparison to a real individual’s height and weight, with the purpose of minimizing that difference. This process as described is the mathematical recitation of equation finding to reduce a delta y, which is an abstract math recitation and does not limit the scope of the claim beyond an abstract idea.
and when the execution of the reservoir simulation model results in a reduction of the misfit, updating the knowledge graph logic with knowledge graph logic for success, based on the parameterization.
As stated earlier in claim 15, updating a knowledge graph logic can be simply changing the weights of the regression model, which can be done with pen and paper. Updating a knowledge graph logic for success is changing the steps the reservoir model takes to produce a successful result. Both these processes as described are mental processes as stated earlier, and therefore do not limit the scope of the claim beyond a mental process
Step 2A Prong 2, Does the claim recite additional elements that integrate the judicial exception into a practical application? NO. This limitation does not recite additional elements beyond the abstract idea.
Step 2B, does the claim recites additional elements that amount to significantly more than the judicial exception. NO. This limitation does not recite additional elements beyond the abstract idea.
Based off of the above facts the office concludes that claim 17 is not eligible under 35 USC 101.
Claim 18:
Step 1: Is the claimed invention one of the four statutory categories? YES. This claim depends on claim 13 which recites “A non-transitory machine-readable medium”: which is a manufacture.
Step 2:
Step 2A Prong 1, inquiry "does the claim recite a law of nature, a natural phenomenon or an abstract idea?": YES.
performing simulation runs of the reservoir simulation model using stochastically sampled full parameter sets of the reservoir simulation model to identify a highest-ranked full parameter set of the reservoir simulation model; and
A simulation run of the reservoir model for a regression model can be as simple as plugging in values into an equation to produce a result, which is a mathematic calculation and is a mental process as shown by Bobbit_2020. Stochastically sampled parameter sets are parameter sets which are achieved through a statistical methods which is also a mathematical process. Identifying a highest ranked parameter set is done by plugging in the different parameter sets into the regression model to determine which set results in the greatest reduction in a misfit. As stated previously, this calculation is a recitation of math.
updating the knowledge graph logic with knowledge graph logic for success, based on the simulation runs.
As stated previously in claim 7 and 17, updating a knowledge graph logic for success is the mental process of either changing weights or logical steps in a knowledge graph, which is a mental process.
Step 2A Prong 2, Does the claim recite additional elements that integrate the judicial exception into a practical application? NO. This limitation does not recite additional elements beyond the abstract idea.
Step 2B, does the claim recites additional elements that amount to significantly more than the judicial exception. NO. This limitation does not recite additional elements beyond the abstract idea.
Based off of the above facts the office concludes that claim 18 is not eligible under 35 USC 101.
Claim 19:
Step 1: Is the claimed invention one of the four statutory categories? YES. This claim depends on claim 13 which recites “A non-transitory machine-readable medium”: which is a manufacture.
Step 2:
Step 2A Prong 1, inquiry "does the claim recite a law of nature, a natural phenomenon or an abstract idea?": YES.
wherein updating the knowledge graph logic based on the simulation runs comprises: aggregating model parameters identified with the highest impact on model dynamic response;
As stated in claim 18, performing simulation runs of the reservoir simulation model using stochastically sampled full parameter sets of the reservoir simulation model to identify a highest-ranked full parameter set of the reservoir simulation model was found to be a mental process. Similarly, aggregating parameters identified with the highest impact on model dynamic response is using the sensitivity analysis to isolate parameters and test how modifying them influences the model’s response. Since the model encompasses a regression model, which can be calculated by hand, this is a mathematic response to a change in the variable. As stated in claim 16, this is changing variable x and observing change in output y, and then selecting from different variables which produced the greatest delta y. This is a mathematic recitation.
and performing a refinement simulation run of the reservoir simulation model for the model parameters with the highest impact.
A refinement simulation run of the model for the parameters with the highest impact is simply executing the model with the newly aggregated parameters. This is likely done to fine tune the parameters further to produce a more idealized model that reduces the misfit by isolating the most influential parameters. As stated in claime 17 executing the model, whether it be to reduce a misfit or to do a sensitivity analysis, encompasses a mathematical recitation.
Step 2A Prong 2, Does the claim recite additional elements that integrate the judicial exception into a practical application? NO. This limitation does not recite additional elements beyond the abstract idea.
Step 2B, does the claim recites additional elements that amount to significantly more than the judicial exception. NO. This limitation does not recite additional elements beyond the abstract idea.
Based off of the above facts the office concludes that claim 19 is not eligible under 35 USC 101.
Claim 20:
Step 1: Is the claimed invention one of the four statutory categories? YES. This claim depends on claim 13 which recites “A non-transitory machine-readable medium”: which is a manufacture.
Step 2:
Step 2A Prong 1, inquiry "does the claim recite a law of nature, a natural phenomenon or an abstract idea?": YES.
wherein updating the knowledge graph logic based on the simulation runs further comprises:
confirming that the misfit is reduced.
A confirmation that the misfit is reduced is a comparison between two different delta y’s, where the delta y is calculated by some mathematical method between the observed y and calculated y. (i.e.: difference of squares, or absolute value of difference). This is a mathematic recitation and observation which is an abstract idea.
Step 2A Prong 2, Does the claim recite additional elements that integrate the judicial exception into a practical application? NO. This limitation does not recite additional elements beyond the abstract idea.
Step 2B, does the claim recites additional elements that amount to significantly more than the judicial exception. NO. This limitation does not recite additional elements beyond the abstract idea.
Based off of the above facts the office concludes that claim 20 is not eligible under 35 USC 101.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1,2,4,7, 11,12, 13, 14 and 17 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by US 20210042634 A1. Maucec_2021.
Claim 1:
Maucec_2021 teaches A method for reservoir simulation, the method comprising: par 4: (“The previously described implementation is implementable using a computer-implemented method;”… Par 5: “This conventional approach may not provide accurate representation of geological and physical attributes of pressure propagation and fluid transport in reservoir simulation models of PE systems.”)
examining a knowledge graph logic associated with a reservoir simulation model for completeness, wherein the knowledge graph logic comprises decision information that governs an execution of the reservoir simulation model; (par29: “In some implementations, techniques of the present disclosure can provide a representation learning to massive petroleum engineering system (ReLMaPS), organized as knowledge graphs or networks. For example, a knowledge discovery engine can be built around an ontological framework with an evolving PE vocabulary that enables automated unified semantic querying. The techniques can include techniques that combine, for example, techniques used in deep representation learning (DRL), online purchasing and network based discovery, disease pathways discovery, and drug engineering for therapeutic applications. The techniques can also provide, for example, 1) implementation of knowledge graphs and networks of large-scale (or big data) PE systems data as a unified knowledge engine for DRL; 2) an integration of DRL tools, such as graph convolutional neural networks (GCNNs) in PE knowledge graphs, as enablers for implementations of large-scale recommendation (or advisory) systems; and 3) an integration of case- and objective-specific smart agents focusing on providing recommendation/advice on decision actions related to production optimization, (Examiner note: these are examples of knowledge graph logic) rapid data-driven model calibration, field development planning and management, risk mitigation, reservoir monitoring, and surveillance. For example, optimization can refer to setting or achieving production values that indicate or result in a production above a predefined threshold or to setting or achieving production values that minimize the difference or misfit between the numerically simulated model and observed or measured data. (Examiner note: this is a measure of completeness, where calculating the misfit between the simulated model and observed data is an examination for completeness).
making a determination, based on the examination, that the knowledge graph logic is incomplete; based on the determination, generating an updated knowledge graph logic; obtaining the decision information from the updated knowledge graph; and executing the reservoir simulation model as instructed by the decision information.
(par 77: “ At 1202, the geological and fracture models (for example, three-dimensional (3D) structural grids with associated subsurface properties) are imported. At 1204, the observed well pressure and production data are imported. At 1206, the reservoir simulation model data tables are updated with imported data (Examiner note: this is considered updating a KG logic). At 1208, the agent builds a joint data misfit objective function (OF), which can combine prior model terms (corresponding to the misfit reservoir subsurface properties of geological and fracture models) and likelihood terms (corresponding to the misfit between the observed and calculated dynamic pressure and production data). At 1210, the misfit OF is validated using a non-linear estimator, namely the reservoir simulator, for dynamic response in terms of well pressure and production data. (Examiner note: obtaining some decision information from the updated knowledge graph) At 1212, the process of optimization is performed with the objective to minimize the misfit OF and obtain an acceptable history match between the observed and simulated data (Examiner note: the term “acceptable” and “validated” implies a determination that the knowledge graph logic will either be complete or incomplete based on the misfit). Optimization process can be a deterministic or stochastic and can be performed on a single simulation model realization or under uncertainty, using an ensemble of statistically diverse simulation model realizations. At 1214, the agent visualizes the results of AHM optimization process as time series, aggregated reservoir grid properties, and quality maps.”)
Claim 2:
wherein the examination of the knowledge graph logic for completeness is performed based on one selected from a group consisting of an ability to render statically accurate success failure decisions and an ability to render statistically accurate predictions, by the reservoir simulation model.
(Par 29: “For example, optimization can refer to setting or achieving production values that indicate or result in a production above a predefined threshold or to setting or achieving production values that minimize the difference or misfit between the numerically simulated model and observed or measured data (Examiner note: this is an examination for completeness that is based on making accurate predictions).” ... par:77 “At 1212, the process of optimization is performed with the objective to minimize the misfit OF and obtain an acceptable history match between the observed and simulated data. Optimization process can be a deterministic or stochastic and can be performed on a single simulation model realization or under uncertainty, using an ensemble of statistically diverse simulation model realizations. At 1214, the agent visualizes the results of AHM optimization process as time series, aggregated reservoir grid properties, and quality maps.”)”
Claim 4:
wherein the reservoir simulation model is one selected from a group consisting of a classifier model and a regression model. (par 83: “ Alternatively, if an objective is to identify wells with problematic performance in terms of production rates, then the problem can be categorized as a continuous or regression problem. At 1506, the agent builds a corresponding predictive model or identifies the model from a library of predefined machine learning (ML) models.”)
Claim 7:wherein generating the updated knowledge graph logic comprises:
executing, using a parameterization, the reservoir simulation model to reduce a misfit; (par 81: “The agent automatically tunes the model to minimize the error between measured and calculated flow rate (Examiner note: this is reducing a misfit) and flowing bottom-hole pressure (FBHP) by adjusting unknown parameters, such as skin and ESP wear factor.” … par 83: “At 1510, the agent recommends actions for well management and maintenance to optimize production.” )
and when the execution of the reservoir simulation model results in a reduction of the misfit, updating the knowledge graph logic with knowledge graph logic for success, based on the parameterization.
(Par 83: “At 1508, the agent performs training, validation, and prediction with the selected ML model. At 1510, the agent recommends actions for well management and maintenance to optimize production. For example, when regression decision trees used as a predictive ML model, individual scenarios leading to the lowest well production can be isolated by automatically tracing a sequence of steps propagating through the nodes and edges of the decision tree. Similarly, the sequence of actions leading to a scenario yielding the highest production can be automatically identified as well.” Examiner note: knowledge graph logic for success).
Claim 11:The method of claim 1, wherein the reservoir simulation model is for one selected from a group consisting of a history matching task (par 20: FIG. 12 is a flow diagram of an example of a smart agent process for computer-assisted history matching (AHM), according to some implementations of the present disclosure.”) and a field development planning task. (par 29: “an integration of case- and objective-specific smart agents focusing on providing recommendation/advice on decision actions related to production optimization, rapid data-driven model calibration, field development planning “)
Claim 12
The method of claim 1, further comprising updating one selected from a group consisting of drilling parameters (par 33: “ Data sources can be interconnected and stored in databases and repositories, combining geological data, production data, real-time data, drilling and completion data,” and production parameters based on a result of executing the reservoir simulation model. (par 79: “ the acquired data is used to update the production and injection tables of the operational reservoir simulation model. At 1306, the reservoir simulation model is executed with updated injection and production data”)
Claim 13:
Maucec_2021 teaches A non-transitory machine-readable medium comprising a plurality of machine-readable instructions executed by one or more processors, the plurality of machine-readable instructions causing the one or more processors to perform operations comprising: of claim 13 (par 4: “The previously described implementation is implementable using a computer-implemented method; a non-transitory, computer-readable medium storing computer-readable instructions to perform the computer-implemented method; and a computer-implemented system including a computer memory interoperably coupled with a hardware processor configured to perform the computer-implemented method/the instructions stored on the non-transitory, computer-readable medium.” … Par 5: “This conventional approach may not provide accurate representation of geological and physical attributes of pressure propagation and fluid transport in reservoir simulation models of PE systems.”)
examining a knowledge graph logic associated with a reservoir simulation model for completeness, wherein the knowledge graph logic comprises decision information that governs an execution of the reservoir simulation model; (par29: “In some implementations, techniques of the present disclosure can provide a representation learning to massive petroleum engineering system (ReLMaPS), organized as knowledge graphs or networks. For example, a knowledge discovery engine can be built around an ontological framework with an evolving PE vocabulary that enables automated unified semantic querying. The techniques can include techniques that combine, for example, techniques used in deep representation learning (DRL), online purchasing and network based discovery, disease pathways discovery, and drug engineering for therapeutic applications. The techniques can also provide, for example, 1) implementation of knowledge graphs and networks of large-scale (or big data) PE systems data as a unified knowledge engine for DRL; 2) an integration of DRL tools, such as graph convolutional neural networks (GCNNs) in PE knowledge graphs, as enablers for implementations of large-scale recommendation (or advisory) systems; and 3) an integration of case- and objective-specific smart agents focusing on providing recommendation/advice on decision actions related to production optimization, (Examiner note: these are examples of knowledge graph logic) rapid data-driven model calibration, field development planning and management, risk mitigation, reservoir monitoring, and surveillance. For example, optimization can refer to setting or achieving production values that indicate or result in a production above a predefined threshold or to setting or achieving production values that minimize the difference or misfit between the numerically simulated model and observed or measured data. (Examiner note: this is a measure of completeness, where calculating the misfit between the simulated model and observed data is an examination for completeness).
making a determination, based on the examination, that the knowledge graph logic is incomplete; based on the determination, generating an updated knowledge graph logic; obtaining the decision information from the updated knowledge graph; and executing the reservoir simulation model as instructed by the decision information.
(par 77: “ At 1202, the geological and fracture models (for example, three-dimensional (3D) structural grids with associated subsurface properties) are imported. At 1204, the observed well pressure and production data are imported. At 1206, the reservoir simulation model data tables are updated with imported data (Examiner note: this is considered updating a KG logic). At 1208, the agent builds a joint data misfit objective function (OF), which can combine prior model terms (corresponding to the misfit reservoir subsurface properties of geological and fracture models) and likelihood terms (corresponding to the misfit between the observed and calculated dynamic pressure and production data). At 1210, the misfit OF is validated using a non-linear estimator, namely the reservoir simulator, for dynamic response in terms of well pressure and production data. (Examiner note: obtaining some decision information from the updated knowledge graph) At 1212, the process of optimization is performed with the objective to minimize the misfit OF and obtain an acceptable history match between the observed and simulated data (Examiner note: the term “acceptable” and “validated” implies a determination that the knowledge graph logic will either be complete or incomplete based on the misfit). Optimization process can be a deterministic or stochastic and can be performed on a single simulation model realization or under uncertainty, using an ensemble of statistically diverse simulation model realizations. At 1214, the agent visualizes the results of AHM optimization process as time series, aggregated reservoir grid properties, and quality maps.”)
Claim 14:
wherein the examination of the knowledge graph logic for completeness is performed based on one selected from a group consisting of an ability to render statically accurate success failure decisions and an ability to render statistically accurate predictions, by the reservoir simulation model.
(Par 29: “For example, optimization can refer to setting or achieving production values that indicate or result in a production above a predefined threshold or to setting or achieving production values that minimize the difference or misfit between the numerically simulated model and observed or measured data (Examiner note: this is an examination for completeness that is based on making accurate predictions).” ... par:77 “At 1212, the process of optimization is performed with the objective to minimize the misfit OF and obtain an acceptable history match between the observed and simulated data. Optimization process can be a deterministic or stochastic and can be performed on a single simulation model realization or under uncertainty, using an ensemble of statistically diverse simulation model realizations. At 1214, the agent visualizes the results of AHM optimization process as time series, aggregated reservoir grid properties, and quality maps.”)”
Claim 17:wherein generating the updated knowledge graph logic comprises:
executing, using a parameterization, the reservoir simulation model to reduce a misfit; (par 81: “The agent automatically tunes the model to minimize the error between measured and calculated flow rate (Examiner note: this is reducing a misfit) and flowing bottom-hole pressure (FBHP) by adjusting unknown parameters, such as skin and ESP wear factor.” … par 83: “At 1510, the agent recommends actions for well management and maintenance to optimize production.” )
and when the execution of the reservoir simulation model results in a reduction of the misfit, updating the knowledge graph logic with knowledge graph logic for success, based on the parameterization.
(Par 83: “At 1508, the agent performs training, validation, and prediction with the selected ML model. At 1510, the agent recommends actions for well management and maintenance to optimize production. For example, when regression decision trees used as a predictive ML model, individual scenarios leading to the lowest well production can be isolated by automatically tracing a sequence of steps propagating through the nodes and edges of the decision tree. Similarly, the sequence of actions leading to a scenario yielding the highest production can be automatically identified as well.” Examiner note: knowledge graph logic for success).
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.
Claim(s) 3,5,6,15, and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Maucec_2021 in view of “A Methodology for Knowledge Acquisition and Reasoning in Failure Analysis of Systems by N. HARi NARAYANAN, and N. VISW AN ADHAM” (Narayanan_1987)
Claim 3:
Maucec_2021 teaches the limitations of claim 1, and makes obvious the limitations of claim 3 wherein the knowledge graph logic comprises knowledge graph logic for success par 29: “ techniques of the present disclosure can provide a representation learning to massive petroleum engineering system (ReLMaPS), organized as knowledge graphs or networks. For example, a knowledge discovery engine can be built around an ontological framework with an evolving PE vocabulary that enables automated unified semantic querying. The techniques can include techniques that combine, for example, techniques used in deep representation learning (DRL), online purchasing and network based discovery, disease pathways discovery, and drug engineering for therapeutic applications. The techniques can also provide, for example, 1) implementation of knowledge graphs and networks of large-scale (or big data) PE systems data as a unified knowledge engine for DRL; 2) an integration of DRL tools, such as graph convolutional neural networks (GCNNs) in PE knowledge graphs, as enablers for implementations of large-scale recommendation (or advisory) systems; and 3) an integration of case- and objective-specific smart agents focusing on providing recommendation/advice on decision actions related to production optimization, rapid data-driven model calibration, field development planning and management, risk mitigation, reservoir monitoring, and surveillance. (Examiner notes: these are examples of knowledge graphs logic) For example, optimization can refer to setting or achieving production values that indicate or result in a production above a predefined threshold or to setting or achieving production values that minimize the difference or misfit between the numerically simulated model and observed or measured data. (Examiner note: this is the definition of a knowledge graph logic for success”).
While Maucec_2021 implies knowledge graph logic for failure (par 5: “Therefore, representation learning from large-scale petroleum network systems and graph structures can represent significant advantages (for example, smart agents) and wider applicability over traditional, fit-for-purpose applications in petroleum/reservoir engineering. The advantages apply to well event modeling, well argumentation, and well failure diagnostics, “(Examiner note: where failure diagnostics implies a logical system which determines the steps that led to a failure) Maucec_2021 does not explicitly teach a knowledge graph logic for failure.)
Narayanan_1987 makes obvious knowledge graph logic for failure (page 274 col 2 par 3-4: “The models used are fault propagation digraphs that represent the propagative aspects of faults and cause-consequence knowledge bases based on augmented fault trees that represent the causal aspects of failures. Failure analysis processes that operate on these models utilize backtracking with constraint enforcement, implicit problem reduction, and bidirectional chaining of production rules. Initially, a framework for knowledge-based failure analysis is developed.”)
Narayanan_1987 and Maucec_2021 are both analogous arts as they both deal with generating logic with knowledge graphs, where Narayanan_1987 discusses well understood theory in 1987 and Maucec_2021 applies that theory for the use in reservoir systems. Maucec_2021 in par 10: discusses the use of “topological ordering of directed acyclic graphs (DAGs), according to some implementations of the present disclosure.” Narayanan_1987 states in Page 278 col 2 par 4 that : “There are many advantages in structuring the knowledge about failure propagation as directed graphs. More often than not, faults propagate along actual interconnections, and so the digraphs reflect the physical structure of the system. Parameters required to characterize fault propagation such as interunit propagation times and probabilities can be easily incorporated in graph models. Besides a number of efficient graph algorithms are known, many of which may be advantageously used for failure analysis.” Similarly, as already stated, Macuec_2021 states that par 5: “The advantages apply to well event modeling, well argumentation, and well failure diagnostics.”
Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date, to combine Maucec_2021 knowledge graph system of directed acyclic graphs for their advantages ability in failure analysis, and combine it with the known theory of Narayanan_1987 of using directed graphs to generate knowledge graph logic for failure for the many benefits of such an approach, such as to notice how the faults propagate along the interconnections.
Claim 5:
Maucec_2021 makes obvious wherein generating the updated knowledge graph logic comprises: executing, using a parameterization, the reservoir simulation model to reduce a misfit; (par 81: “The agent automatically tunes the model to minimize the error between measured and calculated flow rate (Examiner note: this is reducing a misfit) and flowing bottom-hole pressure (FBHP) by adjusting unknown parameters, such as skin and ESP wear factor.”)
Maucec_2021 also makes obvious and when the execution of the reservoir simulation model fails to result in a reduction of the misfit, (par 77: “the process of optimization is performed with the objective to minimize the misfit OF and obtain an acceptable history match between the observed and simulated data. Optimization process can be a deterministic or stochastic and can be performed on a single simulation model realization or under uncertainty, using an ensemble of statistically diverse simulation model realizations.” (Examiner note: where running an optimization with the objective to minimize a misfit implies the possibility that the optimization might not inherently always succeed in reducing the misfit) … par 81: “the agent automatically tunes the model to minimize the error between measured and calculated flow rate and flowing bottom-hole pressure (FBHP) by adjusting unknown parameters, such as skin and ESP wear factor. “ Par 83: “At 1508, the agent performs training, validation, and prediction with the selected ML model. At 1510, the agent recommends actions for well management and maintenance to optimize production. For example, when regression decision trees used as a predictive ML model, individual scenarios leading to the lowest well production can be isolated by automatically tracing a sequence of steps propagating through the nodes and edges of the decision tree. (Examiner note: further implies that the ML model may not always produce optimal results) Similarly, the sequence of actions leading to a scenario yielding the highest production can be automatically identified as well.”)
Maucec_2021 does not teach updating the knowledge graph logic with knowledge graph logic for failure,
Narayanan_1987 makes obvious updating the knowledge graph logic with knowledge graph logic for failure, page 279 col 1 par 4-5: “In this section we outline a systematic procedure to develop the hierarchical failure model, consisting of fault propagation digraphs and cause-consequence knowledge bases, of a given system. This procedure uses the augmented fault tree as an intermediate representation from which the production rules for a knowledge base are derived.” … page 280 col 1 par 1: “Fig. 4 shows a reactor system and an augmented fault tree of it for the failure event "hazardous reaction rate in reactor." To convert an augmented fault tree into a set of production rules, decompose the AFT into "mini" fault trees, each containing only one logical connective. The leaves of a mini fault tree then form the antecedent of the corresponding rule, and its root forms the consequent. The time interval associated with each leaf is incorporated as the value of int for the corresponding failure event in the rule antecedent. The C factors of leaves become the C factors of the corresponding failure events in the rule antecedent. A rule is said to be true if the conditional statement in its antecedent holds true. In such a case it may be deduced that the failure event in its consequent has occurred. Therefore, the rule priority, which is a measure of the criticality of the rule, is the same as the criticality of the failure event in the rule consequent. As this failure event is the root of the mini fault tree from which the rule was derived, the importance of the root event reflects this criticality. So the importance of the root event of a mini fault tree is incorporated as the rule priority of the corresponding production rule. This conversion is illustrated in Fig. 5. A procedure to develop the hierarchical failure model can now be given. S denotes the system under analysis.” (Examiner note: where the process as outlined is an updating and creation of a knowledge graph logic for failure based on a failure event))
Therefore, it would have been obvious to one ordinarily skilled in the art before the effective filing date to combine Maucec_2021 parameterization to determine if the execution of the reservoir simulation model fails to result in a reduction of the misfit, and modify it by using Narayanan_1987 failure analysis by analyzing the failure in reducing the misfit to update a knowledge graph logic for failure. As previously mentioned, a person ordinarily skilled in the art before the effective filing date would have been motivated to do so to take advantage of the benefits of generating a knowledge graph logic for failures discussed by Narayanan_1987, such as to notice how the faults propagate along the interconnections.
Claim 6:
Maucec_2021 teaches wherein the parameterization is determined using a sensitivity analysis (par 43: “A recommendation/advisory system (for example, including smart agents) can execute sensitivity analysis, evaluate well productivity performance, recommend choke and/or artificial lift settings (for example, vertical lift performance (VLP)) to maintain optimal operating point (for example, inflow performance relationship (IPR)), and update well models.” …. Wherein par 44: “.A sensitivity analysis information area 254 can be used to display minimum and maximum range values for reservoir pressure, skin, and permeability. (examiner note: the parameterization determined by a sensitivity analysis”)
Claim 15:
Maucec_2021 makes obvious wherein generating the updated knowledge graph logic comprises: executing, using a parameterization, the reservoir simulation model to reduce a misfit; (par 81: “The agent automatically tunes the model to minimize the error between measured and calculated flow rate (Examiner note: this is reducing a misfit) and flowing bottom-hole pressure (FBHP) by adjusting unknown parameters, such as skin and ESP wear factor.”)
Maucec_2021 also makes obvious and when the execution of the reservoir simulation model fails to result in a reduction of the misfit, (par 77: “the process of optimization is performed with the objective to minimize the misfit OF and obtain an acceptable history match between the observed and simulated data. Optimization process can be a deterministic or stochastic and can be performed on a single simulation model realization or under uncertainty, using an ensemble of statistically diverse simulation model realizations.” (Examiner note: where running an optimization with the objective to minimize a misfit implies the possibility that the optimization might not inherently always succeed in reducing the misfit) … par 81: “the agent automatically tunes the model to minimize the error between measured and calculated flow rate and flowing bottom-hole pressure (FBHP) by adjusting unknown parameters, such as skin and ESP wear factor. “ Par 83: “At 1508, the agent performs training, validation, and prediction with the selected ML model. At 1510, the agent recommends actions for well management and maintenance to optimize production. For example, when regression decision trees used as a predictive ML model, individual scenarios leading to the lowest well production can be isolated by automatically tracing a sequence of steps propagating through the nodes and edges of the decision tree. (Examiner note: further implies that the ML model may not always produce optimal results) Similarly, the sequence of actions leading to a scenario yielding the highest production can be automatically identified as well.”)
Maucec_2021 does not teach updating the knowledge graph logic with knowledge graph logic for failure,
Narayanan_1987 makes obvious updating the knowledge graph logic with knowledge graph logic for failure, page 279 col 1 par 4-5: “In this section we outline a systematic procedure to develop the hierarchical failure model, consisting of fault propagation digraphs and cause-consequence knowledge bases, of a given system. This procedure uses the augmented fault tree as an intermediate representation from which the production rules for a knowledge base are derived.” … page 280 col 1 par 1: “Fig. 4 shows a reactor system and an augmented fault tree of it for the failure event "hazardous reaction rate in reactor." To convert an augmented fault tree into a set of production rules, decompose the AFT into "mini" fault trees, each containing only one logical connective. The leaves of a mini fault tree then form the antecedent of the corresponding rule, and its root forms the consequent. The time interval associated with each leaf is incorporated as the value of int for the corresponding failure event in the rule antecedent. The C factors of leaves become the C factors of the corresponding failure events in the rule antecedent. A rule is said to be true if the conditional statement in its antecedent holds true. In such a case it may be deduced that the failure event in its consequent has occurred. Therefore, the rule priority, which is a measure of the criticality of the rule, is the same as the criticality of the failure event in the rule consequent. As this failure event is the root of the mini fault tree from which the rule was derived, the importance of the root event reflects this criticality. So the importance of the root event of a mini fault tree is incorporated as the rule priority of the corresponding production rule. This conversion is illustrated in Fig. 5. A procedure to develop the hierarchical failure model can now be given. S denotes the system under analysis.” (Examiner note: where the process as outlined is an updating and creation of a knowledge graph logic for failure based on a failure event))
Therefore, it would have been obvious to one ordinarily skilled in the art before the effective filing date to combine Maucec_2021 parameterization to determine if the execution of the reservoir simulation model fails to result in a reduction of the misfit, and modify it by using Narayanan_1987 failure analysis by analyzing the failure in reducing the misfit to update a knowledge graph logic for failure. As previously mentioned, a person ordinarily skilled in the art before the effective filing date would have been motivated to do so to take advantage of the benefits of generating a knowledge graph logic for failures discussed by Narayanan_1987, such as to notice how the faults propagate along the interconnections.
Claim 16:
Maucec_2021 teaches wherein the parameterization is determined using a sensitivity analysis (par 43: “A recommendation/advisory system (for example, including smart agents) can execute sensitivity analysis, evaluate well productivity performance, recommend choke and/or artificial lift settings (for example, vertical lift performance (VLP)) to maintain optimal operating point (for example, inflow performance relationship (IPR)), and update well models.” …. Wherein par 44: “.A sensitivity analysis information area 254 can be used to display minimum and maximum range values for reservoir pressure, skin, and permeability. (examiner note: the parameterization determined by a sensitivity analysis”)
Claim(s) 8, 9, 10, 18, 19, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Maucec_2021 in view of US 7657494 B2 (Wilkinson_2010).
Claim 8:Maucec_2021 teaches the limitations of claim 7, as well as updating the knowledge graph logic with knowledge graph logic for success, based on the simulation runs. (Par 83: “At 1508, the agent performs training, validation, and prediction with the selected ML model. At 1510, the agent recommends actions for well management and maintenance to optimize production. For example, when regression decision trees used as a predictive ML model, individual scenarios leading to the lowest well production can be isolated by automatically tracing a sequence of steps propagating through the nodes and edges of the decision tree. Similarly, the sequence of actions leading to a scenario yielding the highest production can be automatically identified as well.” Examiner note: knowledge graph logic for success).
Maucec_2021 does not explicitly teach performing simulation runs of the reservoir simulation model using stochastically sampled full parameter sets of the reservoir simulation model to identify a highest-ranked full parameter set of the reservoir simulation model;
Wilkinson_2010 teaches performing simulation runs of the reservoir simulation model using stochastically sampled full parameter sets of the reservoir simulation model ( col 8 lines 1-10: “One embodiment of the present invention utilizes uniform sampling to further reduce the uncertainty with the computer analysis of production for oil reservoirs. FIG. 3 provides an illustration of the uniform sampling method. The uniform sampling generates a sampling distribution 62 that covers the entire parameter space 64 for a predetermined number of runs. It ensures that no large regions of the parameter space 64 are left under sampled. Such coverage is used to obtain simulation data for the construction of a robust proxy that is able to interpolate all intermediate points in the parameter space 64.”) to identify a highest-ranked full parameter set of the reservoir simulation model; and (Wilkinson col 4 lines 55-58: “One object of the present invention is to identify the most significant parameters of the reservoir and systematically integrate those parameters into the analysis.”)
Wilkinson_2010 and Maucec_2021 are analogous arts as they both apply machine learning methodologies for improvements of reservoir simulations. Maucec_2021 teaches adjusting parameters to better reduce the misfit par 81:” The agent automatically tunes the model to minimize the error between measured and calculated flow rate and flowing bottom-hole pressure (FBHP) by adjusting unknown parameters, such as skin and ESP wear factor.“ Wilkinson_2010 teaches that col 2 lines 5-12: “Since inverse problems have no unique solutions, i.e., more than one combination of reservoir parameter values give the same flow outputs, a large number of well-matched or "good" reservoir models needs to be obtained in order to achieve a high degree of confidence in the history-matching results.” Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date to take Maucec_2021 adjusting parameter values to reduce a metric, with Wilkinson_2010 generating multiple full parameter sets (with the idea of having a best parameter set as determined by the misfit) in order to ensure that there is a high degree of confidence in the model for history matching. The examiner also notes Maucec_2021 adjusting parameter values to reduce a metric also implies that there is a calculated best parameter set.
Claim 9:
Wilkinson_2010 teaches wherein updating the knowledge graph logic based on the simulation runs comprises:
aggregating model parameters identified with the highest impact on model dynamic response; and
col 4 lines 55-58: “One object of the present invention is to identify the most significant parameters of the reservoir and systematically integrate those parameters into the analysis.”)
performing a refinement simulation run of the reservoir simulation model for the model parameters with the highest impact.
col 8 lines 30-44: “Forecasting future production of the field also requires computer simulation. Since the number of good models identified by the genetic programming proxy is normally quite large, it is not practical to make all of the simulation runs with the good models. Similar to the way the simulator proxy is constructed for history matching, a second genetic programming proxy is generated for production forecast. As shown on the right side of FIG. 4, the simulation results again based on uniform sampling 86 will be used to construct a genetic programming forecasting proxy 88. This proxy is then applied to all the good models (Examiner note: a refinement simulation). identified in the history matching phase 90. Based on the forecasting results, uncertainty statistics such as the P10, P50 and P90 are then estimated 92.” (Examiner note: where history matching is defined as “col 1 line 50-55: History matching is the process of updating reservoir descriptor parameters in a given computer model to reflect such changes, “ See FIG. 4. )
Claim 10:
Maucec_2021 teaches wherein updating the knowledge graph logic based on the simulation runs further comprises: confirming that the misfit is reduced. (par 77: “At 1212, the process of optimization is performed with the objective to minimize the misfit OF and obtain an acceptable history match between the observed and simulated data. “ See fig 12. Whereas simulation is ran (1210) and then afterwards an optimization is performed to minimize the objective function (1212). )
Claim 18:Maucec_2021 teaches the limitations of claim 17, as well as updating the knowledge graph logic with knowledge graph logic for success, based on the simulation runs. (Par 83: “At 1508, the agent performs training, validation, and prediction with the selected ML model. At 1510, the agent recommends actions for well management and maintenance to optimize production. For example, when regression decision trees used as a predictive ML model, individual scenarios leading to the lowest well production can be isolated by automatically tracing a sequence of steps propagating through the nodes and edges of the decision tree. Similarly, the sequence of actions leading to a scenario yielding the highest production can be automatically identified as well.” Examiner note: knowledge graph logic for success).
Maucec_2021 does not explicitly teach performing simulation runs of the reservoir simulation model using stochastically sampled full parameter sets of the reservoir simulation model to identify a highest-ranked full parameter set of the reservoir simulation model;
Wilkinson_2010 teaches performing simulation runs of the reservoir simulation model using stochastically sampled full parameter sets of the reservoir simulation model ( col 8 lines 1-10: “One embodiment of the present invention utilizes uniform sampling to further reduce the uncertainty with the computer analysis of production for oil reservoirs. FIG. 3 provides an illustration of the uniform sampling method. The uniform sampling generates a sampling distribution 62 that covers the entire parameter space 64 for a predetermined number of runs. It ensures that no large regions of the parameter space 64 are left under sampled. Such coverage is used to obtain simulation data for the construction of a robust proxy that is able to interpolate all intermediate points in the parameter space 64.”) to identify a highest-ranked full parameter set of the reservoir simulation model; and (Wilkinson col 4 lines 55-58: “One object of the present invention is to identify the most significant parameters of the reservoir and systematically integrate those parameters into the analysis.”)
Wilkinson_2010 and Maucec_2021 are analogous arts as they both apply machine learning methodologies for improvements of reservoir simulations. Maucec_2021 teaches adjusting parameters to better reduce the misfit par 81:” The agent automatically tunes the model to minimize the error between measured and calculated flow rate and flowing bottom-hole pressure (FBHP) by adjusting unknown parameters, such as skin and ESP wear factor.“ Wilkinson_2010 teaches that col 2 lines 5-12: “Since inverse problems have no unique solutions, i.e., more than one combination of reservoir parameter values give the same flow outputs, a large number of well-matched or "good" reservoir models needs to be obtained in order to achieve a high degree of confidence in the history-matching results.” Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date to take Maucec_2021 adjusting parameter values to reduce a metric, with Wilkinson_2010 generating multiple full parameter sets (with the idea of having a best parameter set as determined by the misfit) in order to ensure that there is a high degree of confidence in the model for history matching. The examiner also notes Maucec_2021 adjusting parameter values to reduce a metric also implies that there is a calculated best parameter set.
Claim 19:
Wilkinson_2010 teaches wherein updating the knowledge graph logic based on the simulation runs comprises:
aggregating model parameters identified with the highest impact on model dynamic response; and
col 4 lines 55-58: “One object of the present invention is to identify the most significant parameters of the reservoir and systematically integrate those parameters into the analysis.”)
performing a refinement simulation run of the reservoir simulation model for the model parameters with the highest impact.
col 8 lines 30-44: “Forecasting future production of the field also requires computer simulation. Since the number of good models identified by the genetic programming proxy is normally quite large, it is not practical to make all of the simulation runs with the good models. Similar to the way the simulator proxy is constructed for history matching, a second genetic programming proxy is generated for production forecast. As shown on the right side of FIG. 4, the simulation results again based on uniform sampling 86 will be used to construct a genetic programming forecasting proxy 88. This proxy is then applied to all the good models (Examiner note: a refinement simulation). identified in the history matching phase 90. Based on the forecasting results, uncertainty statistics such as the P10, P50 and P90 are then estimated 92.” (Examiner note: where history matching is defined as “col 1 line 50-55: History matching is the process of updating reservoir descriptor parameters in a given computer model to reflect such changes, “ See FIG. 4. )
Claim 20:
Maucec_2021 teaches wherein updating the knowledge graph logic based on the simulation runs further comprises: confirming that the misfit is reduced. (par 77: “At 1212, the process of optimization is performed with the objective to minimize the misfit OF and obtain an acceptable history match between the observed and simulated data. “ See fig 12. Whereas simulation is ran (1210) and then afterwards an optimization is performed to minimize the objective function (1212). )
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AHMAD HUSSAM SHALABY whose telephone number is (571)272-7414. The examiner can normally be reached Mon-Fri 8:30am - 5pm.
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, Emerson Puente can be reached at 5712723652. 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.
/A.H.S./Examiner, Art Unit 2187
/BRIAN S COOK/Primary Examiner, Art Unit 2187
Prosecution Insights