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 .
Response to Arguments
Applicant’s arguments with respect to claim(s) 15-20, 22-25, and 28-34 have been considered but are moot in view of the new grounds of rejection necessitated by the applicant’s amendments to the claims.
Drawings
As previously discussed, the drawings filed on 02/17/23 are accepted.
Examiner’s Note - 35 USC § 101
In view of the applicant’s 11/14/25 claim amendments, claims 15-20, 22-25, and 28-34 qualify as eligible subject matter under 35 U.S.C. 101.
Independent claim 15 have been amended to include the following limitations:
which is used to exploit a fluid in the underground formation by determining the electrofacies interpretation of the measurements from at least a portion of the at least one well
F) from at least the electrofacies interpretation of the measurements, constructing a grid representation of the underground formation, determining at least one exploitation scheme for fluid present in the underground formation based on at least the grid representation of the underground formation, and exploiting the fluid of the underground formation according to the exploitation scheme
Here, the applicant has more positively recited exploiting the fluid of the underground formation according to the exploitation scheme.
Paragraph 0103 of the Applicant’s Second Substitute Specification states, “Then, once the exploitation scheme is determined, the hydrocarbons trapped in the oil reservoir are exploited according to this exploitation scheme, notably at least by drilling the injection and production wells of the exploitation scheme thus determined, to produce the hydrocarbons, and by setting up the production infrastructures required for developing this reservoir.”
While the exploitation scheme itself appears to simply be a data simulation, the affirmative act of exploiting, according to the exploitation scheme, appears to effect a real-world transformation or reduction of a particular article to a different state or thing (see MPEP 2106.05(c)). The amended limitations are therefore indicative of integration into a practical application under step 2A, prong two.
As such, claim 15 is not directed to a judicial exception. It qualifies as eligible subject matter under 35 U.S.C. 101.
All other claims depend on independent claim 15 and are also eligible, as a result of their dependency.
Claim Objections
Claim 33 is objected to because of the following informalities:
Claim 33 is substantially similar to claims 31-32 and 34. Claims 31-32 and 34 were amended to cancel the language of “of at least one of the first and second supervised classification methods.” The examiner is not sure if this language was meant to also be cancelled from claim 33, since claim 33 appeared to be intended to be substantially identical to claims 31-32 and 34, other than its dependency. For the purposes of examination, the examiner will construe the cancelled language to also be cancelled from claim 33.
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 15-20, 22-25, and 28-34 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 15 has been amended to state:
C) among the first electrofacies classifications of the measurements relative to at least the portion of the at least one well, selecting a first reference electrofacies classification according to a criterion for selecting the classification of the first electrofacies classifications exhibiting at least a smallest number of class changes along at least the portion of the at least one well drilled through the underground formation, and selecting a portion of the reference first electrofacies classification
D) applying second classification methods to the measurements relative to at least the portion of the at least one well and determining second electrofacies classifications of the measurements relative to at least the portion of the at least one well with the second classification methods being supervised classification methods trained on the portion of the reference first electrofacies classifications
These amended limitations are considered indefinite for a number of reasons.
First, the applicant notes that C) states, “portion of the reference first electrofacies classification,” where classification is singular, while D) states, “portion of the reference first electrofacies classifications,” where classifications is plural. It is not clear how the classification of the reference first electrofacies classification can be singular and plural at the same time.
This highlights the bigger issue, which is that by inserting the word “first” before “reference electrofacies classification” in limitation C), it is no longer clear whether “the reference first electrofacies classification(s)” is referring to “among the first electrofacies classifications” or to “selecting a first reference electrofacies classification”. Is “reference first electrofacies classification(s)” the same or different than “first reference electrofacies classification”? Is “reference first electrofacies classification(s)” the same or different than “first electrofacies classifications”?
For the purposes of examination, the examiner will construe “portion of the reference first electrofacies classification(s)” to be “portion of the first electrofacies classifications …” Furthermore, the examiner will construe the “portion of the first electrofacies classifications” to be satisfied by any teaching of a “first reference electrofacies classification.” The examiner is essentially interpreting the “first electrofacies classifications” as the “big group,” and the “first reference electrofacies classification” as a subset or “portion” of that big group.
Furthermore, claim 15 has also been amended to include the following limitation:
E) determining the electrofacies interpretation of the measurements, relative to at least the portion of the at least one well from the second electrofacies classifications of the measurements relative to at least the portion of the at least one well with the determination of the electrofacies interpretation of the measurements being performed using an ensemble learning method
This limitation is indefinite because there are four individual clauses here:
determining the electrofacies interpretation of the measurements
relative to at least the portion of the at least one well from the second electrofacies classifications of the measurements
relative to at least the portion of the at least one well
with the determination of the electrofacies interpretation of the measurements being performed using an ensemble learning method
It is not clear which clauses are meant to modify which other clauses. There is now only one comma in the entire limitation, which is the comma between the first clause and the remaining three clauses. It is not clear whether the remaining three clauses are all meant to modify the first clause, or whether they are meant to modify the clause that immediately precedes them, or whether they are meant to be viewed as conditional options for the first clause, such as: 1) determining the electrofacies interpretation of the measurements relative to at least the portion of the at least one well from the second electrofacies classifications of the measurements or 2) determining the electrofacies interpretation of the measurements relative to at least the portion of the at least one well or 3) determining the electrofacies interpretation of the measurements, with the determination of the electrofacies interpretation of the measurements being performed using an ensemble learning method (emphasis mine).
For the purposes of examination, the examiner will interpret that the three clauses, after the “determining the electrofacies interpretation of the measurements” clause, are conditional, such that the disclosure of any of the three options discussed above would satisfy the limitation, as a whole.
All other claims depend on independent claim 15 and are also rejected as a result of their dependency.
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) 15-20, 22-25, and 28-34 is/are rejected under 35 U.S.C. 103 as being unpatentable over Emelyanova et al NPL (Emelyanova, I., Pervukhima, M., Clennell, M., & Dyt, C. (2017, June). “Unsupervised identification of electrofacies employing machine learning”. In 79th EAGE Conference and Exhibition 2017 – Workshops (pp. cp-519). European Association of Geoscientists & Engineers.) in view of Mirowski (US PgPub 20060074825) and Carullo et al (US PgPub 20200272947). Please note that Mirowski was cited in the 02/17/23 IDS.
With respect to claim 15, Emelyanova et al NPL discloses:
A method of determining an electrofacies interpretation of measurements relative to at least a portion of at least one well drilled through an underground formation (page 1, paragraph 3 states, “One approach to automated identification of electrofacies … to reliably classify electrofacies at a petroleum exploration well Lauda-1 drilled in the Northern Carnarvon Basin (Western Australia).”), which is used to exploit a fluid in the underground formation by determining the electrofacies interpretation of the measurements from at least a portion of the at least one well (The claims do not define what “exploiting a fluid” entails. Page 1, paragraphs 2-3 state, “ANN techniques were used for seismic event classifications, first arrival picking, earthquake prediction, velocity structure recovery … One approach to automated identification of electrofacies is based on applying various clustering techniques to log data … in order to reliably classify electrofacies at a petroleum exploration well Lauda-1 drilled in the Northern Carnarvon Basin …” The examiner broadly interprets actual applications of electrofacies classification, like the ones stated, to anticipate the claimed limitation.)
A) carrying out measurements, relative to at least the portion of the at least one well drilled through the underground formation with the measurements being from at least one of a well log and an image of at least one core sample taken from the at least one well (page 1, paragraph 4 states, “Electrofacies analysis is based on distinguishing various sediments or lithological types from well logs.”)
B) applying classification methods to the measurements from at least the portion of the at least one well and determining first electrofacies classifications of the measurements from at least the portion of the at least one well, the classification methods being unsupervised classification methods, or, if learning information is available for at least one subset of the measurements relative to at least the portion of the at least one well by using supervised classification methods trained on the learning information (page 1, paragraph 4 states, “various clustering algorithms have been applied for automated electrofacies analysis to provide efficient and objective quantification of lithological variations from log data. Clustering is an unsupervised classification technique applied for organizing data into homogenous groups based on a certain dissimilarity measure between the groups. When added for electrofacies analysis this technique allows appropriate recognition of sedimentary sequences by grouping similar well data.”)
With respect to claim 15, Emelyanova et al NPL differs from the claimed invention in that it does not explicitly disclose:
C) among the first electrofacies classifications of the measurements relative to at least the portion of the at least one well, selecting a first reference electrofacies classification according to a criterion for selecting the classification of the first electrofacies classifications exhibiting at least a smallest number of class changes along at least the portion of the at least one well drilled through the underground formation, and selecting a portion of the first electrofacies classifications
D) applying second classification methods to the measurements relative to at least the portion of the at least one well and determining second electrofacies classifications of the measurements relative to at least the portion of the at least one well with the second classification methods being supervised classification methods trained on the portion of the first electrofacies classifications
E) determining the electrofacies interpretation of the measurements, relative to at least the portion of the at least one well from the second electrofacies classifications of the measurements relative to at least the portion of the at least one well with the determination of the electrofacies interpretation of the measurements being performed using an ensemble learning method
F) from at least the electrofacies interpretation of the measurements, constructing a grid representation of the underground formation, determining at least one exploitation scheme for fluid present in the underground formation based on at least the grid representation of the underground formation, and exploiting the fluid of the underground formation according to the exploitation scheme
With respect to claim 15, Mirowski discloses:
C) among the first electrofacies classifications of the measurements relative to at least the portion of the at least one well, selecting a first reference electrofacies classification according to a criterion for selecting the classification of the first electrofacies classifications exhibiting at least a smallest number of class changes along at least the portion of the at least one well drilled through the underground formation, and selecting a portion of the first electrofacies classifications (The abstract of Mirowski states, “optimising the class probabilities according to the sequencing knowledge.” Paragraph 0006 of Mirowski states, “A current limitation in analyzing geological measured data such as downhole logs, is that their relationship to classes such as rock facies is not obvious. In each borehole, there are unknown local factors that may affect the data in unexpected ways. It can thus be risky to classify on a simplified theoretical analysis or by data clustering.” Paragraph 0009 of Mirowski states, “The main advantage of those neural nets is their learning capability. During the learning phase, given a training set of data, the interconnection weights are gradually adjusted so as to stabilize the network’s output, and, in the case of the supervised learning, to minimize the mean square error between the effective output and the desired one.” Paragraph 0038 states, “The geological classification is inferred using supervised neural networks that are applied to the input data and that predict the associated classes. The vertical class transition constraints are learned within a Markov class transition table …” Paragraph 0123 of Mirowski states, “The lithofacies learning set for the Hybrid ANN/HMM system was provided by the results of electrofacies predictions … The stability of the predictions of the latter systems has then been compared … The Hybrid ANN/HMM system is more reliable.” At a high level, the examiner views claimed step B) as being directed to defining electrofacies using unsupervised learning techniques, such as clustering, which is taught in Emelyanova et al NPL. The examiner views claimed step D) as being directed to using supervised learning techniques to help predict labeled facies. Mirowski references this step. However, Carullo et al, as discussed below, is more clear about the distinction of a unsupervised training phase and a supervised training phase and so will continue to be applied to teach step D). What Mirowski is being applied here for is step C), which addresses the issues pertaining to the relationship of classes to rock facies not being obvious based on pure clustering (as discussed in paragraph 0006 of Mirowski). Mirowski bridges the gap between unsupervised clustering techniques and supervised prediction techniques.)
With respect to claim 15, it would have been obvious to one having ordinary skill in the art before the effective filing date of the invention to incorporate the teachings of Mirowski into the invention of Emelyanova et al NPL. The motivation for the skilled artisan in doing so is to gain the benefit of electrofacies interpretations that more accurately reflect the relationship of classes to rock facies.
With respect to claim 15, Carullo et al discloses:
D) applying second classification methods to the measurements relative to at least the portion of the at least one well and determining second electrofacies classifications of the measurements relative to at least the portion of the at least one well with the second classification methods being supervised classification methods trained on the portion of the first electrofacies classifications (abstract states, “The machine learning pipeline may include an unsupervised training phase, a validation phase and a supervised training and scoring phase …”; paragraphs 0017 - 0019 states, “During an unsupervised learning stage, the system may train a topic model … During a second stage, the system can perform supervised learning on the validated model. The supervised learning may be referred to as ensemble learning.” The claimed limitation is obvious in view of Emelyanova et al NPL in view of Carullo et al. Emelyanova et al NPL already teaches the context of electrofacies classification using an unsupervised model. Carullo et al is specifically being applied to teach the artificial intelligence principle of feeding the output of an unsupervised model into a supervised model as a form of ensemble learning. Although the technological context of Carullo et al is not the same as in Emelyanova et al NPL, one of ordinary skill in the art understands that artificial intelligence principles are applied to a wide variety of technological contexts. The claimed limitation would be obvious to one of ordinary skill in the art, as the contextual electrofacies classification data of Emelyanova et al NPL would continue through to the output of the first unsupervised model being refined by an additional second supervised model.)
E) determining the electrofacies interpretation of the measurements, relative to at least the portion of the at least one well from the second electrofacies classifications of the measurements relative to at least the portion of the at least one well with the determination of the electrofacies interpretation of the measurements being performed using an ensemble learning method (This limitation is obvious in view of combination; The abstract of Carullo et al states, “The machine learning pipeline may include an unsupervised training phase, a validation phase and a supervised training and scoring phase …”; paragraphs 0017 - 0019 states, “During an unsupervised learning stage, the system may train a topic model … During a second stage, the system can perform supervised learning on the validated model. The supervised learning may be referred to as ensemble learning.” Emelyanova et al NPL already teaches the context of determining electrofacies interpretation based on relevant data. Carullo et al is specifically being applied to teach the artificial intelligence principle of feeding the output of an unsupervised model into a supervised model as a form of ensemble learning. Although the technological context of Carullo et al is not the same as in Emelyanova et al NPL, one of ordinary skill in the art understands that artificial intelligence principles are applied to a wide variety of technological contexts. The claimed limitation would be obvious to one of ordinary skill in the art, as the contextual electrofacies classification data of Emelyanova et al NPL would continue through to the output of the first unsupervised model being refined by an additional second supervised model. As stated in paragraph 0019 of Carullo et al, “The supervised learning may be referred to as ensemble learning.”)
F) from at least the electrofacies interpretation of the measurements, constructing a grid representation of the underground formation, determining at least one exploitation scheme for fluid present in the underground formation based on at least the grid representation of the underground formation, and exploiting the fluid of the underground formation according to the exploitation scheme (obvious in view of combination; Emelyanova et al NPL figure 2 shows diagrams that are broadly construed to serve as “grid interpretations.” As discussed above, the claims do not explicitly define what “exploitation” entails, but the applications discussed in Emelyanova et al NPL are broadly construed to anticipate the term.)
With respect to claim 15, it would have been obvious to one having ordinary skill in the art before the effective filing date of the invention to incorporate the teachings of Carullo et al into the invention of Emelyanova et al NPL. The motivation for the skilled artisan in doing so is to gain the benefit of orchestrating a machine learning pipeline for more accurate and refined results.
With respect to claim 16, Emelyanova et al NPL, as modified, discloses:
wherein the at least one well log is selected from among gamma ray logs, sonic logs, density logs, electric logs or well image logs (Emelyanova et al NPL page 2, paragraph 3 states, “The Lauda-1 well logs used in this study, namely, transit time (DT), gamma ray (GR) … bulk density …”)
With respect to claim 17, Emelyanova et al NPL, as modified, discloses:
wherein the unsupervised classification methods comprise at least five types of unsupervised classification methods (The main embodiment of Emelyanova et al NPL discloses using three different clustering algorithms (page 1, paragraph 3). However, it is well-known to one of ordinary skill in the artificial intelligence art that there are many more unsupervised classification methods that can be used. Official notice is taken. The claimed limitation would be obvious in view of what is well-known and well-understood in the art. Please also note the references incorporated by reference into Emelyanova et al NPL, as well as the various methods discussed in Carullo et al (paragraph 0043).)
With respect to claim 18, Emelyanova et al NPL, as modified, discloses:
wherein at least one unsupervised classification method of the unsupervised classification methods is selected by a model-based data clustering method, a fuzzy clustering method, a hierarchical k-means clustering method, and a density- based clustering method (Emelyanova et al NPL page 1, paragraph 3 states, “Here we apply three different clustering algorithms, namely, Spectral Clustering … Self-Organizing Map … and k-means in order to reliably classify electrofacies …”
With respect to claim 19, Emelyanova et al NPL, as modified, discloses:
wherein the second supervised classification methods comprise at least five types of supervised classification methods (obvious in view of combination; Carullo et al paragraph 0043 states, “The training function may use an ensemble of different algorithms, for example, SVM, supervised LDA, boosting, random forests, Glmnet, decision trees, neural networks, maximum entropy, and the like …”)
With respect to claim 20, Emelyanova et al NPL, as modified, discloses:
wherein at least one supervised classification method of at least one of the first and second supervised classification methods is selected from a decision tree-based classification and regression, a random forest type classification, support vector machines, a bagged decision tree model, a linear discriminant analysis, a mixture discriminant analysis, and a k-nearest neighbour method (obvious in view of combination; see paragraph 0043 of Carullo et al)
With respect to claim 22, Emelyanova et al NPL, as modified, discloses:
wherein, in step A, measurements are carried out for at least one of an additional well and at least an additional portion of the well, and steps B and C are used only with the portion of the well, and steps D and E are applied to the portion of the well, and to at least one of the additional well and the additional portion of the well (obvious in view of total teachings of Emelyanova et al; page 4, paragraph 1 states, “there are nearby wells with appreciable oil and gas columns in the same lithological units, and therefore a multi-well study could help to distinguish lithological from fluid factors in the rock properties.” It would be obvious to apply the artificial intelligence principles of modified Emelyanova et al NPL to either single wells, portions of single wells, multiple wells, or portions of multiple wells, depending on use case, user preference, and scope of study. One of ordinary skill in the art understands that it would be obvious to apply the broad principles of modified Emelyanova et al to a wide variety of applications in a wide variety of technological contexts, as well as a wide scope within those various technological contexts. The applicant’s disclosure has not established criticality for the claimed limitation; it appears to be a permissible implementation, not a restrictive one.)
With respect to claim 23, Emelyanova et al NPL, as modified, discloses:
wherein the portion of the reference electrofacies classification comprises between 20% and 30% of the samples of the reference electrofacies classification (obvious in view of the total teachings of Emelyanova et al NPL; Emelyanova page 2, paragraphs 3-4 states, “the log dataset consisted of 9054 samples … The optimal number of clusters was determined as seven … Figure 3 shows the clustering outputs …” Emelyanova does not detail whether any of the clusters comprises between 20% and 30% of the samples, though a deeper analysis of the results in figure 3 may be able to confirm this. Nonetheless, the applicant’s disclosure does not establish criticality for this range of 20-30%. It would appear to be a permissible implementation and not a restrictive one. One or ordinary skill in the art would also recognize that this limitation may be data-dependent, and dependent on the situation and use case, this limitation would be satisfied.)
With respect to claim 24, Emelyanova et al NPL, as modified, discloses:
wherein the samples of the portion of the reference electrofacies classification are randomly selected (obvious in view of combination; Emelyanova et al NPL page 1, paragraph 5 states, “K-means is a traditional clustering algorithm based on minimization of a cost function by migrating the cluster centres, initially randomly generated …” Paragraph 0043 of Carullo et al discloses random forests (paragraph 0043). One of ordinary skill in the art would recognize that the claimed limitation may be satisfied depending on what model(s) are used, and selecting different models for different purposes would be obvious to one of ordinary skill in the art.)
With respect to claim 25, Emelyanova et al NPL, as modified, discloses:
wherein the ensemble learning method is a majority voting method (obvious in view of combination; Emelyanova et al NPL page 2, paragraph 2 states, “Then, that cluster number is selected for the integrated classification which was suggested by the majority of algorithms …” Even paragraph 0012 of the applicant’s own specification admits that Emelyanova et al NPL teaches majority vote.)
With respect to claim 28, Emelyanova et al NPL, as modified, discloses:
wherein the exploitation scheme of the fluid comprises at least one site of at least one of an injection well and at least one production well, and the wells of the site are drilled and equipped with production infrastructures (suggested by technological context disclosed by Emelyanova et al. Emelyanova et al NPL page 1, paragraph 3 discloses a petroleum exploration well.)
With respect to claims 29-30, Emelyanova et al NPL, as modified, discloses:
wherein the at least one unsupervised classification method of the unsupervised classification methods is selected from a model-based data clustering method, a fuzzy clustering method, a hierarchical k-means clustering method, and a density- based clustering method (see rejection of claim 18 above)
With respect to claims 31-34, Emelyanova et al NPL, as modified, discloses:
wherein the at least one supervised classification method is selected from a decision tree-based classification and regression, a random forest type classification, support vector machines, a bagged decision tree model, a linear discriminant analysis, a mixture discriminant analysis, and a k-nearest neighbour method (see rejection of claim 20 above)
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Peyaud et al (US PgPub 20170275982) discloses a simulated core sample estimated from composite borehole measurement.
Zhang et al (US PgPub 20090259446) discloses a method to generate numerical pseudocores using borehole images, digital rock samples, and multi-point statistics.
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to LEONARD S LIANG whose telephone number is (571)272-2148. The examiner can normally be reached M-F 10:00 AM - 7 PM.
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, ARLEEN M VAZQUEZ can be reached at (571)272-2619. 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.
/LEONARD S LIANG/Examiner, Art Unit 2857 03/28/26
/ARLEEN M VAZQUEZ/Supervisory Patent Examiner, Art Unit 2857