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 .
DETAILED ACTION
The Office Action is in response to the application filed on 08/11/2023. Claims 1-20 are pending in
the application. Claims 1 and 11 are independent claims.
Specification
The abstract dated 08/11/2023 has been reviewed. It has 60 words and 6 lines and no legal
phraseology. It is accepted.
The use of the terms Bluetooth and Wi-Fi ([0068]), each of which is a trade names or a marks
used in commerce, has been noted in this application. The term should be accompanied by the generic terminology; furthermore the term should be capitalized wherever it appears or, where appropriate, include a proper symbol indicating use in commerce such as ™, SM , or ® following the term.
Although the use of trade names and marks used in commerce (i.e., trademarks, service marks, certification marks, and collective marks) are permissible in patent applications, the proprietary nature of the marks should be respected and every effort made to prevent their use in any manner which might adversely affect their validity as commercial marks.
The disclosure is objected to because of the following informalities:
In paragraph [0038], line 8 of the specification, the term “and/” should be read as “and/or”.
Appropriate correction is required.
Claim Objections
Claims 10 and 20 are objected to because of the following informalities:
Claim 10 recites “the operation characteristics of the well includes pressure and temperature at the well” should be read as “the operation characteristics of the well include pressure and temperature at the well.”
Claim 20 recites “the operation characteristics of the well includes pressure and temperature at the well” should be read as “the operation characteristics of the well include pressure and temperature at the well.”
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 3, 4, 8, 13, 14 and 18 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second
paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claims 3 and 13 recite the limitation " … the linear unsupervised machine- learning model … " in line 1. There is insufficient antecedent basis for this limitation in the claim. Examiner recommends amending claim 3 depends on claim 2, and claim 13 depends on claim 12. For purposes of examination, the claims will be construed as though they did have this dependency.
Claims 4 and 14 recite the limitation " … the linear unsupervised machine- learning model … " in line 1. There is insufficient antecedent basis for this limitation in the claim. Examiner recommends amending claim 4 depends on claim 2, and claim 14 depends on claim 12. For purposes of examination, the claims will be construed as though they did have this dependency.
Claims 8 and 18 recite “the comparison between the anomaly score and the anomaly score threshold” in line 3. Examiner recommends amending claim 8 depends on claim 5, and claim 18 depends on claim 15. For purposes of examination, the claims will be construed as though they did have this dependency.
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in
public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/process/file/efs/guidance/eTD-info-I.jsp.
Instant Application 18/546,132
Co-pending Application 18/311,884
1. A system for predicting sanding events, the system comprising:
one or more physical processors configured by machine-readable instructions to:
obtain well operation information, the well operation information characterizing operation characteristics of a well for a duration of time;
determine reconstructed operation characteristics of the well for the duration of time using an unsupervised machine-learning model, wherein the unsupervised machine-learning model is trained using historical well operation information, the historical well operation information characterizing the operation characteristics of the well for a period of time preceding the duration of time; and
predict a future occurrence of a sanding event at the well based on the operation characteristics of the well for the duration of time and the reconstructed operation characteristics of the well for the duration of time.
2. The system of claim 1, wherein the unsupervised machine-learning model includes a linear unsupervised machine-learning model and/or a non-linear unsupervised machine-learning model.
3. The system of claim 1, wherein the linear unsupervised machine-learning model includes a principal component analysis.
4. The system of claim 1, wherein the non-linear unsupervised machine- learning model includes a long short-term memory autoencoder.
5. The system of claim 1, wherein prediction of the future occurrence of the sanding event at the well based on the operation characteristics of the well for the duration of time and the reconstructed operation characteristics of the well for the duration of time includes:
determination of an anomaly score based on a difference between the operation characteristics of the well for the duration of time and the reconstructed operation characteristics of the well for the duration of time; and
prediction of the future occurrence of the sanding event at the well based on a comparison between the anomaly score and an anomaly score threshold.
6. The system of claim 5 wherein the anomaly score threshold is determined based on the operation characteristics of the well for the period of time and reconstructed operation characteristics of the well for the period of time.
7. The system of claim 6, wherein the anomaly score threshold is determined based on the operation characteristics of the well for the period of time and reconstructed operation characteristics of the well for the period of time such that a threshold percentage of historical anomaly scores satisfies the anomaly score threshold.
8. The system of claim 1, wherein the one or more physical processors are further configured by the machine-readable instructions to present a visualization of the comparison between the anomaly score and the anomaly score threshold.
9. (Original) The system of claim 1, wherein the unsupervised machine-learning model is retrained using the well operation information.
10. (Original) The system of claim 1, wherein the operation characteristics of the well includes pressure and temperature at the well.
1. A system for predicting asphaltene anomalies, the system comprising:
one or more physical processors configured by machine-readable instructions to:
obtain well operation information, the well operation information characterizing operation characteristics of a well during production of oil and/or gas from the well for a duration of time;
determine reconstructed operation characteristics of the well for the duration of time using an unsupervised machine-learning model, wherein the unsupervised machine-learning model is trained using historical well operation information, the historical well operation information characterizing the operation characteristics of the well for a period of time preceding the duration of time; and
predict, during production of oil and/or gas from the well, a future occurrence of an asphaltene anomaly at the well before the asphaltene anomaly occurs, based on a difference between the operation characteristics of the well for the duration of time and the reconstructed operation characteristics of the well for the duration of time, wherein the asphaltene anomaly is a production of asphaltene in the well and/or an effect of asphaltene production in the well; wherein one or more preventative or mitigative actions are performed in response to the future occurrence of the asphaltene anomaly predicted by the system, the one or more preventative or mitigative actions including: changing a production rate of the well, performing an intervention on the well at a scheduled time, or controlling operations to prevent uncommanded shut-in of the well.
2. The system of claim 1, wherein the unsupervised machine-learning model includes a linear unsupervised machine-learning model and/or a non-linear unsupervised machine- learning model.
3. The system of claim 2, wherein the linear unsupervised machine-learning model includes a principal component analysis algorithm.
4. The system of claim 2, wherein the non-linear unsupervised machine-learning model includes a long short-term memory autoencoder.
5. The system of claim 1, wherein prediction of the future occurrence of the asphaltene anomaly at the well based on the operation characteristics of the well for the duration of time and the reconstructed operation characteristics of the well for the duration of time includes: determination of an anomaly score based on the difference between the operation characteristics of the well for the duration of time and the reconstructed operation characteristics of the well for the duration of time; and
prediction of the future occurrence of the asphaltene anomaly at the well based on a comparison between the anomaly score and an anomaly score threshold.
6. The system of claim 5, wherein the anomaly score threshold is determined based on the operation characteristics of the well for the period of time and reconstructed operation characteristics of the well for the period of time.
7. The system of claim 6, wherein the anomaly score threshold is determined based on the operation characteristics of the well for the period of time and reconstructed operation characteristics of the well for the period of time such that a threshold percentage of historical anomaly scores satisfies the anomaly score threshold.
8. The system of claim 5, wherein the one or more physical processors are further configured by the machine-readable instructions to present a visualization of the comparison between the anomaly score and the anomaly score threshold.
9. (Original) The system of claim 1, wherein the unsupervised machine-learning model is retrained using the well operation information.
10. (Previously Presented) The system of claim 1, wherein the operation characteristics of the well include pressure and temperature at the well.
Examiner note: “Bold and Italic” indicate different limitations between the co-pending application and the instant application.
This is a provisional nonstatutory double patenting rejection.
Claims 1-15 are provisionally rejected on the ground of nonstatutory double patenting as
being unpatentable over claims 1-15 of co-pending Application No. 18311884 in view of Thiruvenkatanathan US20220349298A1.
Claims 1-15 of co-pending Application ‘884 teaches all of the limitations of claims 1-15 of the Instant Application, except “predict a future occurrence of a sanding event.” Co-pending Application ‘884 in view of Thiruvenkatanathan teach predict a future occurrence of a sanding event (See Thiruvenkatanathan, [0137], “Thus, utilizing operating envelopes (and underlying sand prediction model), predictions can be made as to whether sand ingress may occur at the one or more production zones under certain operating conditions (e.g., drawdown pressure, production rate, etc.) … However, the sand prediction model and/or the operating envelope may be used (e.g., at block 412) to predict the timing or even the severity of sand ingress for each of the one or more production zones in the second well, so that early action (e.g., such as prophylactic action) may be taken by a well operator so as to minimize or avoid the complications caused by the predicted sand ingress.”).
It would have been obvious for a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified co-pending Application ‘884 to incorporate the teachings of Thiruvenkatanathan, and apply prediction of future sand ingress under well operating condition in order to provide advance warning of sanding and enable early action to reduce or avoid complications caused by sand ingress.
Claims 11-15 of the Instant Application recite substantially the similar elements as claims 1-5 of the Instant Application, and are provisionally rejected for the same reasons by claims 11-15 of the Co-pending Application ‘884 in view of Thiruvenkatanathan ‘298.
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.
The claims 1-20 are rejected under 35 USC § 101 because the claimed invention is directed to
judicial exception, an abstract idea, it has not been integrated into practical application and the claims further do not recite significantly more than the judicial exception. Examiner has evaluated
the claims under the framework provided in the 2019 Revised Patent Subject Matter Eligibility Guidance
published in the Federal Register 01/07/2019, as well as subsequent USPTO eligibility guidance updates,
and has provided such analysis below.
Step 1: Are the claims to a process, machine, manufacture or composition of matter?"
Yes, Claims 1-10 are directed to system and fall within the statutory category of machine;
Yes, Claims 11-20 are directed to method and fall within the statutory category of process.
In order to evaluate the Step 2A inquiry "Is the claim directed to a law of nature, a natural phenomenon or an abstract idea?" we must determine, at Step 2A Prong 1, whether the claim recites a law of nature, a natural phenomenon or an abstract idea and further whether the claim recites additional elements that integrate the judicial exception into a practical application.
Step 2A Prong 1:
Claim 1: The limitations of “determine reconstructed operation characteristics of the well for the duration of time,” as drafted, is a process that, but for the recitation of generic computing components, under its broadest reasonable interpretation (BRI) in light of the specification, covers performance of the limitation in the human mind. For example, a person is capable of reviewing earlier information regarding operation of the well, recognizing relationships or patterns reflected in that information, and mentally using the recognized relationships or patterns to estimate or recreate the well’s operating characteristics for a later time interval. The steps include observation, evaluation, judgment, and reasoning processes that can be performed mentally or with the aid of pen and paper (The courts consider a mental process (thinking) that "can be performed in the human mind, or by a human using a pen and paper" to be an abstract idea. CyberSource Corp. v. Retail Decisions, Inc., 654 F.3d 1366, 1372, 99 USPQ2d 1690, 1695 (Fed. Cir. 2011)) – MPEP 2106.04(a)(2)(III).
Claim 1: The limitations of “predict a future occurrence of a sanding event at the well based on the operation characteristics of the well for the duration of time and the reconstructed operation characteristics of the well for the duration of time,” as drafted, is a process that, but for the recitation of generic computing components, under its broadest reasonable interpretation (BRI) in light of the specification, covers performance of the limitation in the human mind. For example, a person is capable of reviewing information describing the actual operation of the well during a given time interval, comparing that information with the estimated or recreated representation of the well’s operation during same interval, and mentally evaluating the similarities or difference to judge whether sand is likely to enter the well at a later time. The steps include observation, evaluation, judgment, and reasoning processes that can be performed mentally or with the aid of pen and paper (The courts consider a mental process (thinking) that "can be performed in the human mind, or by a human using a pen and paper" to be an abstract idea. CyberSource Corp. v. Retail Decisions, Inc., 654 F.3d 1366, 1372, 99 USPQ2d 1690, 1695 (Fed. Cir. 2011)) – MPEP 2106.04(a)(2)(III).
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea under step 2A Prong I.
The elements of claim 11 is substantially the same as those of claim 1. Therefore, the elements of claim 11 is rejected due to the same reasons as outlined above for claim 1.
Therefore, claim 1 and 11 recite judicial exceptions. The claims have been identified to recite judicial exceptions, Step 2A Prong 2 will evaluate whether the claim as a whole integrates the exception into a practical application of that exception.
Step 2A Prong 2: Claims 1 and 11: The judicial exception is not integrated into a practical application.
In particular, the claims recite the following additional elements - “A system for predicting sanding events, the system comprising: one or more physical processors configured by machine-readable instructions to:” and “A method for predicting sanding events, the method comprising:,” which are merely recitations of instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to implement the judicial exception, which does not integrate judicial exception into a practical application (see MPEP §2106.05(f)).
Further, the following additional elements - “obtain well operation information, the well operation information characterizing operation characteristics of a well for a duration of time,” which is merely recitations of insignificant extra-solution activity such as data gathering (i.e., receiving data), which does not integrate a judicial exception into practical application (see MPEP § 2106.05(g)).
Further, the following additional elements – “using an unsupervised machine-learning model, wherein the unsupervised machine-learning model is trained using historical well operation information, the historical well operation information characterizing the operation characteristics of the well for a period of time preceding the duration of time,” which is merely adding the words "apply it" (or an equivalent) with the judicial exception, or instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea. See MPEP 2106.05(f).
In particular, the claim does not recite a particular model architecture, reconstruction algorithm, training technique, or a manner in which the model improves computer, machine learning functionality, to any other technology or technical field. Rather, the model is merely used as a tool to estimate or recreate well operation characteristics, while the historical information merely identifies the general data used to train the model.
Therefore, these additional limitations merely use a computer and machine learning model in their ordinary capacity to apply the recited mental concepts. The limitation does not impose a meaningful limitation on the judicial exception and does not integrate the judicial exception into a practical application.
Alternatively, the limitations merely link the use of the judicial exception to a particular technological environment or field of use, such as unsupervised machine-learning model for prediction. See MPEP § 2106.05(h). Accordingly, the additional limitations does not integrate the judicial exception into a practical application.
The Federal Circuit held that “patents that do no more than claim the application of generic machine learning to new data environments without disclosing improvements to the machine learning models to be applied, are patent ineligible under 35 U.S.C. § 101.” See Recentive Analytics, Inc. v, Fox Corp.
Therefore, "Do the claims recite additional elements that integrate the judicial exception into a practical application? No, these additional elements do not integrate the abstract idea into a practical application and they do not impose any meaningful limits on practicing the abstract idea. The claims are directed to an abstract idea.
After having evaluated the inquires set forth in Steps 2A Prong 1 and 2, it has been concluded that claims 1, 8 and 15 not only recite a judicial exception but that the claims are directed to the judicial exception as the judicial exception has not been integrated into practical application.
Step 2B: Claims 1, 8 and 15: The claim does not include additional elements, alone or in combination, that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements amount to no more than generic computing components which do not amount to significantly more than the abstract idea. Limitations that the courts have found not to be enough to qualify as "significantly more" when recited in a claim with a judicial exception include:
i. Adding the words "apply it" (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, e.g., a limitation indicating that a particular function such as creating and maintaining electronic records is performed by a computer, as discussed in Alice Corp., 573 U.S. at 225-26, 110 USPQ2d at 1984 (see MPEP § 2106.05(f));
ii. Simply appending well-understood, routine, conventional activities previously known to the industry, specified at a high level of generality, to the judicial exception, e.g., a claim to an abstract idea requiring no more than a generic computer to perform generic computer functions that are well-understood, routine and conventional activities previously known to the industry, as discussed in Alice Corp., 573 U.S. at 225, 110 USPQ2d at 1984 (see MPEP § 2106.05(d));
iii. Adding insignificant extra-solution activity to the judicial exception, e.g., mere data gathering in conjunction with a law of nature or abstract idea such as a step of obtaining information about credit card transactions so that the information can be analyzed by an abstract mental process, as discussed in CyberSource v. Retail Decisions, Inc., 654 F.3d 1366, 1375, 99 USPQ2d 1690, 1694 (Fed. Cir. 2011) (see MPEP § 2106.05(g)); …
The courts have recognized the following computer functions as well‐understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity. i. Receiving or transmitting data over a network, …; ii. Performing repetitive calculations, … iii. Electronic recordkeeping, … (updating an activity log). iv. Storing and retrieving information in memory, …
In particular, the claim recites the additional elements including generic computing component and a machine learning model. These elements recites merely perform their ordinary functions of receiving and processing information, and apply a trained model to data. Therefore, the additional elements, when considered individually and in combination, merely apply the judicial exception using generic computing components functionality and do not provide significantly more than the judicial exception.
Therefore, "Do the claims recite additional elements that amount to significantly more than the judicial exception? No, these additional elements, alone or in combination, do not amount to significantly more than the judicial exception. Having concluded analysis within the provided framework, claims 1 and 11 do not recite patent eligible subject matter under 35 U.S.C. § 101.
Dependent claims 2-10 and 12-20 are also similar rejected under same rationale as cited above wherein these claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. These claims are merely further elaborate the mental process and/or mathematical concepts, or providing additional definition of process which does not impose any meaningful limits on practicing the abstract idea. Claims 2-10 and 12-20 are also rejected for incorporating the deficiency of their independent claims 1 and 11.
Claim 2 recites “The system of claim 1, wherein the unsupervised machine-learning model includes a linear unsupervised machine-learning model and/or a non-linear unsupervised machine-learning model.”
The limitation merely further defines different type of unsupervised machine-learning model recited in claim 1 as including a linear model, a nonlinear model or both. This limitation does not meaningfully limit the mental processes recited in claim 1, but merely specifies the type of machine learning model associated with the processes. Accordingly, the imitation does not integrate the judicial exception into a practical application or provide significantly more than the judicial exception. See MPEP 2106.05(f) and 2106.05(h). Therefore, the office finds that the claim 2 is ineligible under 35 USC 101.
Claim 3 recites “The system of claim 1, wherein the linear unsupervised machine-learning model includes a principal component analysis.”
The limitation merely specifies that the linear unsupervised machine- learning model includes a principal component analysis. This limitation does not meaningfully limit the mental processes recited in claim 1, but merely identifies an analytical technique associated with the model at a high level of generality. Accordingly, the imitation does not integrate the judicial exception into a practical application or provide significantly more than the judicial exception. See MPEP 2106.05(f) and 2106.05(h). Therefore, the office finds that the claim 3 is ineligible under 35 USC 101.
Claim 4 recites “The system of claim 1, wherein the non-linear unsupervised machine- learning model includes a long short-term memory autoencoder.”
The limitation merely specifies that the non-linear unsupervised machine- learning model includes a long short-term memory autoencoder. This limitation does not meaningfully limit the mental processes recited in claim 1, but merely identifies a model architecture associated with the process at a high level of generality. Accordingly, the imitation does not integrate the judicial exception into a practical application or provide significantly more than the judicial exception. See MPEP 2106.05(f) and 2106.05(h). Therefore, the office finds that the claim 4 is ineligible under 35 USC 101.
Claim 5 recites “The system of claim 1, wherein prediction of the future occurrence of the sanding event at the well based on the operation characteristics of the well for the duration of time and the reconstructed operation characteristics of the well for the duration of time includes:
determination of an anomaly score based on a difference between the operation characteristics of the well for the duration of time and the reconstructed operation characteristics of the well for the duration of time; and
prediction of the future occurrence of the sanding event at the well based on a comparison between the anomaly score and an anomaly score threshold.”
The limitation merely specifies determining an anomaly score based on a difference between the actual and reconstructed well operation characteristics and predicting a future sanding event based on a comparison between the anomaly score and a threshold, which is an extension of the metal processes recited in claim 1. For example, a person is capable of reviewing the actual and recreated well operation information, identifying a difference between the two, assigning a score representing the difference, comparing the score with a selected threshold, and mentally judging whether sanding is likely to occur at a later time. The steps include observation, evaluation, judgment, and reasoning processes that can be performed mentally or with the aid of pen and paper (The courts consider a mental process (thinking) that "can be performed in the human mind, or by a human using a pen and paper" to be an abstract idea. CyberSource Corp. v. Retail Decisions, Inc., 654 F.3d 1366, 1372, 99 USPQ2d 1690, 1695 (Fed. Cir. 2011)) – MPEP 2106.04(a)(2)(III). Therefore, the office finds that the claim 5 is ineligible under 35 USC 101.
Claim 6 recites “The system of claim 5 wherein the anomaly score threshold is determined based on the operation characteristics of the well for the period of time and reconstructed operation characteristics of the well for the period of time.”
The limitation merely specifies determining the anomaly score threshold based on the actual and reconstructed well operation characteristics from an earlier time period, which is an extension of mental processes recited in claim 5. For example, a person is capable of reviewing the actual and recreated well operation information for the earlier time period, evaluating the information, and mentally identifying a threshold for further comparison purpose. The steps include observation, evaluation, judgment, and reasoning processes that can be performed mentally or with the aid of pen and paper (The courts consider a mental process (thinking) that "can be performed in the human mind, or by a human using a pen and paper" to be an abstract idea. CyberSource Corp. v. Retail Decisions, Inc., 654 F.3d 1366, 1372, 99 USPQ2d 1690, 1695 (Fed. Cir. 2011)) – MPEP 2106.04(a)(2)(III). Therefore, the office finds that the claim 6 is ineligible under 35 USC 101.
Claim 7 recites “The system of claim 6, wherein the anomaly score threshold is determined based on the operation characteristics of the well for the period of time and reconstructed operation characteristics of the well for the period of time such that a threshold percentage of historical anomaly scores satisfies the anomaly score threshold.”
The limitation merely further specifies selecting the anomaly score threshold such that a selected percentage of historical anomaly scores satisfies the threshold, which is an extension of the metal processes recited in claim 6. For example a person is capable of reviewing historical anomaly scores, counting or estimating the proportion of scores that meet a selected threshold condition, and mentally adjusting the threshold until the selected percentage is reached. The steps include observation, evaluation, judgment, and reasoning processes that can be performed mentally or with the aid of pen and paper (The courts consider a mental process (thinking) that "can be performed in the human mind, or by a human using a pen and paper" to be an abstract idea. CyberSource Corp. v. Retail Decisions, Inc., 654 F.3d 1366, 1372, 99 USPQ2d 1690, 1695 (Fed. Cir. 2011)) – MPEP 2106.04(a)(2)(III). Therefore, the office finds that the claim 7 is ineligible under 35 USC 101.
Claim 8 recites “The system of claim 1, wherein the one or more physical processors are further configured by the machine-readable instructions to present a visualization of the comparison between the anomaly score and the anomaly score threshold.”
The limitation merely specifies presenting a visualization of the comparison between the anomaly score and the anomaly score threshold. This limitation does not meaningfully limit the mental processes recited in claim 1, but merely displays the result of the comparison at a high level of generality and constitutes insignificant data outputting. Accordingly, the imitation does not integrate the judicial exception into a practical application or provide significantly more than the judicial exception. See MPEP 2106.05(g). Therefore, the office finds that the claim 8 is ineligible under 35 USC 101.
Claim 9 recites “The system of claim 1, wherein the unsupervised machine-learning model is retrained using the well operation information.”
The limitation merely further defines the unsupervised machine learning model by requiring the model to be retrained using the well operation information. This limitation does not meaningfully limit the mental processes recited in claim 1, but merely requires updating the model using additional well operation data at high level of generality, without reciting any specific retraining operation or technological improvement. Accordingly, the imitation does not integrate the judicial exception into a practical application or provide significantly more than the judicial exception. See MPEP 2106.05(f) and 2106.05(h). Therefore, the office finds that the claim 9 is ineligible under 35 USC 101.
Claim 10 recites “The system of claim 1, wherein the operation characteristics of the well includes pressure and temperature at the well.”
The limitation merely specifies that the well operation characteristics include pressure and temperature. This limitation does not meaningfully limit the mental processes recited in claim 1, but merely identifies the types of information received for use in the recited mental processes at a high level of generality and constitutes insignificant data gathering. Accordingly, the imitation does not integrate the judicial exception into a practical application or provide significantly more than the judicial exception. See MPEP 2106.05(g). Therefore, the office finds that the claim 10 is ineligible under 35 USC 101.
Claims 11-20 recite the similar elements as claims 2-10, and are rejected for the same reasons under 35 U.S.C. 101.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and
103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set
forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103
are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1-2, 5-6, 8, 10-12, 15-16, 18 and 20 are rejected under 35 U.S.C. 103 as being
unpatentable over Alamu (“ESP Data Analytics: Use of Deep Autoencoders for Intelligent Surveillance of Electric Submersible Pumps,” published in 2020) in view of Thiruvenkatanathan US20220349298A1.
Claim 1, Alamu teaches A system for predicting
one or more physical processors configured by machine-readable instructions (Page.1, “The reconstruction error is used to distinguish a normal event from an anomalous event because it increases prior to an event and reduces as the system returns to stability … The model was able to detect the gas locks on average 5 hrs in advance and electrical issues several days in advance before the actual events.” Page.7, “After the model was trained and validated on historical data, the model and the supporting python program were deployed in a docker container on a Linux server.” Examiner note: the reference teaches a computer implemented system that executes a machine learning model and supporting Python program in a Linux server advance warning of future operating events) to:
obtain well operation information, the well operation information characterizing operation characteristics of a well for a duration of time (Page.4, para.1, “The data collected was time series data from 90-97 sensors around an ESP. The data collected was from electrical sensors, valve position sensors, well flowrate sensors, sensors that measure fluid properties, and sensors that monitor the operation of the ESP such as vibration sensors, motor winding temperature, intake and discharge sensors for temperature and pressure on the ESP.” Page.7, “Every 10 mins, data is downloaded from the process historian database and passed through the machine learning model.” Examiner note: the reference teaches obtaining time series sensor data characterizing operating conditions of an ESP in a production well, including fluid properties, vibration, temperature, and pressure measurements, over a period of time);
determine reconstructed operation characteristics of the well for the duration of time using an unsupervised machine-learning model, wherein the unsupervised machine-learning model is trained using historical well operation information, the historical well operation information characterizing the operation characteristics of the well for a period of time preceding the duration of time (Page.1, “Methods, Procedures, Process: … We trained the network on stable operating data from a 2-years historical data dump of 97 sensors. This allowed the model to understand the patterns of stability in an ESP.” Page.5, para.2, “An Autoencoder is a type of artificial neural network used to learn efficient data encodings in an unsupervised manner. The aim of an autoencoder is to learn a representation for a set of input data and to reproduce this input data in the output.” Page.5, para.2 from last, “x’ = Model reconstruction of sensor values.” Page.7, para.1, “After the model was trained and validated on historical data, the model and the supporting python program were deployed in a docker container on a Linux server. Every 10 mins, data is downloaded from the process historian database and passed through the machine learning model.” Examiner note: the reference teaches using an unsupervised autoencoder trained with two years of historical stable ESP sensor data. After training, subsequent time series sensor data is passed through the model to generate reconstructed sensor values. The reconstructed sensor values represent reconstructed operating characteristics of the ESP and production well for the monitored duration, while the two year historical dataset represents operating information from a period preceding that duration); and
predict a future occurrence of a (Page.5, paragraph from last, “x = Vector of input sensors (vector of size N, where N is number of sensors / tags in the dataset used to build the model) x’ = Model reconstruction of sensor values. The reconstruction error of the autoencoder is calculated as the difference between the input vector to the model and its predicted output vector … A useful way to summarize this vector to a single number is to find the mean of the squared reconstruction error (MSE), this value is used as an anomaly score for the system. ” Page.6, “Determination of anomaly threshold, After training of the autoencoder, the entire stable data points are passed through the model and the mean squared error for each time stamp is determined.” Page.7, results, “This section outlines the results for the different ESPs used in this study, in each case, the model was able to detect events such as gas locks, riser instabilities and electrical issues. The image above shows how the anomaly score for an ESP rises before an event and then reduces after the system returns to stability.” Page.1, last paragraph, “The model was able to detect the gas locks on average 5 hrs in advance and electrical issues several days in advance before the actual events.” Examiner note: the reference teaches determining an anomaly score based on the different between actual operating sensor values and their corresponding reconstructed sensor values for each monitored timestamp. The anomaly score provides advance warning of future ESP operating events. Therefore, the prediction is based on both the actual operation characteristics and the reconstructed operation characteristics for the same monitored duration).
However, Alamu fails to teach predict a future occurrence of a sanding event.
Thiruvenkatanathan teaches predict a future occurrence of a sanding event ([0137], “Thus, utilizing operating envelopes (and underlying sand prediction model), predictions can be made as to whether sand ingress may occur at the one or more production zones under certain operating conditions (e.g., drawdown pressure, production rate, etc.) … However, the sand prediction model and/or the operating envelope may be used (e.g., at block 412) to predict the timing or even the severity of sand ingress for each of the one or more production zones in the second well, so that early action (e.g., such as prophylactic action) may be taken by a well operator so as to minimize or avoid the complications caused by the predicted sand ingress.”).
It would have been obvious for a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified Alamu to incorporate the teachings of Thiruvenkatanathan, and apply prediction of future sand ingress under well operating condition in order to provide advance warning of sanding and enable early action to reduce or avoid complications caused by sand ingress. In this case, Alamu teaches using actual operating sensor values and corresponding reconstructed sensor values to generate an anomaly score and provide advance warning of future ESP operating events. Thiruvenkatanathan teaches predicting whether sand ingress will occur under well operating conditions, and predicting the timing or severity of the sand ingress so that early action may be taken. The combination of teachings would predictably provide benefit of using deviations between actual and reconstructed well operation characteristics to provide advance warning of a future sanding event, thereby enabling preventative or mitigating action before complications caused by sand ingress occur.
Claim 2, Alamu teaches The system of claim 1, wherein the unsupervised machine-learning model includes a linear unsupervised machine-learning model and/or a non-linear unsupervised machine-learning model (Page.5, para.2, “An Autoencoder is a type of artificial neural network used to learn efficient data encodings in an unsupervised manner.” Page.5, para.3, “The encoder section acts in a manner to PCA for dimensionality reduction, it however, performs this dimensionality reduction in a non-linear manner unlike PCA.”).
Claim 5, Alamu teaches The system of claim 1, wherein prediction of the future occurrence of the
determination of an anomaly score based on a difference between the operation characteristics of the well for the duration of time and the reconstructed operation characteristics of the well for the duration of time; and
prediction of the future occurrence of the (Page.5, last paragraph, “The reconstruction error of the autoencoder is calculated as the difference between the input vector to the model and its predicted output vector.” A useful way to summarize this vector to a single number is to find the mean of the squared reconstruction error (MSE), this value is used as an anomaly score for the system.” Page.6, last paragraph, “ The mean and standard deviation of this distribution can be determined and used as anomaly threshold for the dataset. Data points whose mean squared error value is 3 standard deviations from the mean are flagged as an anomalous data point.” Page.7, Results, “The image above shows how the anomaly score for an ESP rises before an event and then reduces after the system returns to stability.” Examiner note: the reference teaches determining an anomaly score from the different between actual operating sensor values and their corresponding reconstructed values, and further teaches comparing the anomaly score with an anomaly threshold to identify an anomalous condition, wherein the anomaly score rises before a future event).
However, Alamu fails to teach prediction of the future occurrence of the sanding event at the well.
Thiruvenkatanathan teaches prediction of the future occurrence of the sanding event at the well ([0137], “Thus, utilizing operating envelopes (and underlying sand prediction model), predictions can be made as to whether sand ingress may occur at the one or more production zones under certain operating conditions (e.g., drawdown pressure, production rate, etc.) … However, the sand prediction model and/or the operating envelope may be used (e.g., at block 412) to predict the timing or even the severity of sand ingress for each of the one or more production zones in the second well, so that early action (e.g., such as prophylactic action) may be taken by a well operator so as to minimize or avoid the complications caused by the predicted sand ingress.”).
It would have been obvious for a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified Alamu to incorporate the teachings of Thiruvenkatanathan, and apply prediction of future sand ingress under well operating condition in order to provide advance warning of sanding and enable early action to reduce or avoid complications caused by sand ingress. In this case, Alamu teaches determining an anomaly score based on differences between actual operating sensor values and corresponding reconstructed sensor values, comparing the anomaly score with an anomaly threshold, and using the anomaly score to provide advance warning of future ESP operating events. Thiruvenkatanathan teaches predicting whether sand ingress will occur under well operating conditions, and predicting the timing or severity of the sand ingress so that early action may be taken. The combination of teachings would predictably provide benefit of using an anomaly score and anomaly threshold based on actual and reconstructed well operation characteristics to provide advance warning of a future sanding event, thereby enabling preventative or mitigating action before complications caused by sand ingress occur.
Claim 6, Alamu teaches The system of claim 5 wherein the anomaly score threshold is determined based on the operation characteristics of the well for the period of time and reconstructed operation characteristics of the well for the period of time (Page.1, Methods, Procedures, Process:” … We trained the network on stable operating data from a 2-years historical data dump of 97 sensors.” Page.5, last paragraph, “The reconstruction error of the autoencoder is calculated as the difference between the input vector to the model and its predicted output vector.” Page.6, Determination of anomaly threshold, “After training of the autoencoder, the entire stable data points are passed through the model and the mean squared error for each time stamp is determined … The mean and standard deviation of this distribution can be determined and used as anomaly threshold for the dataset.” Examiner note: the reference teaches passing the historical stable operating sensor data through the trained autoencoder, determining the mean squared error from the difference between the historical sensor values and their reconstructed values for each timestamp, and using the resulting error distribution to determine the anomaly threshold).
Claim 8, Alamu teaches The system of claim 1, wherein the one or more physical processors are further configured by the machine-readable instructions to present a visualization of the comparison between the anomaly score and the anomaly score threshold (page.6, last paragraph, “The mean and standard deviation of this distribution can be determined and used as anomaly threshold for the dataset. Data points whose mean squared error value is 3 standard deviations from the mean are flagged as an anomalous data point.” Page.7, para.1, “The model results are written back to the process historian database so that the engineers can visualize the results in any visualization tool of their choice.”Page.7, RESULTS, “The image above shows how the anomaly score for an ESP rises before an event and then reduces after the system returns to stability.” Examiner note: the reference teaches comparing the mean squared error anomaly score with an anomaly threshold to identify anomalous data points and presenting the model results through a visualization tool. The displayed anomaly score distinguishes unstable anomalous points from table points and therefore provides a visualization of the comparison between the anomaly score and the anomaly score threshold).
Claim 10, Alamu teaches The system of claim 1, wherein the operation characteristics of the well includes pressure and temperature at the well (Page.4, para.1, “The data collected was from electrical sensors, valve position sensors, well flowrate sensors, sensors that measure fluid properties, and sensors that monitor the operation of the ESP such as vibration sensors, motor winding temperature, intake and discharge sensors for temperature and pressure on the ESP.”).
The elements of claims 11-12, 15-16, 18 and 20 are substantially the same as those of claims 1-2, 5-6, 8 and 10. Therefore, the elements of claims 11-12, 15-16, 18 and 20 are rejected due to the same reasons as outlined above for claims 1-2, 5-6, 8 and 10.
Claim(s) 3 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over Alamu and
Thiruvenkatanathan as applied to claim 1 and 11 above, and further in view of Yoon US20200320402A1.
Claim 3, Alamu and Thiruvenkatanathan fail to teach, but Yoon teaches The system of claim 1, wherein the linear unsupervised machine-learning model includes a principal component analysis ([0022], “Some unsupervised and semi-supervised learning models can handle such imbalance by focusing on characterization of normality and detecting samples out of the normality: e.g., principal component analysis (PCA) for linearity and autoencoders for non-linearity.”).
It would have been obvious for a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified Alamu and Thiruvenkatanathan to incorporate the teachings of Yoon, and apply a principal component analysis to characterize normal operating data and detect samples outside the characterized normality in order to effectively identify anomalous operating conditions when examples of abnormal operation are limited.
The elements of claim 13 is substantially the same as those of claim 3. Therefore, the elements of claim 13 is rejected due to the same reasons as outlined above for claim 3.
Claim(s) 4 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Alamu and
Thiruvenkatanathan as applied to claim 1 and 11 above, and further in view of Heidari US20210087925A1.
Claim 4, Alamu and Thiruvenkatanathan fail to teach, but Heidari teaches The system of claim 1, wherein the non-linear unsupervised machine-learning model includes a long short-term memory autoencoder ([0058], “An LSTM autoencoder may take the time-series data associated with multiple sources or variables such as flow rate, proppant concentration, fluid concentration, and pressure and may encode the data using the LSTM encoder.” [0068], “Each type of data may be encoded separately using a LSTM encoder. Alternatively, the data may be combined together and encoded using the LSTM encoder. This is shown in 402. The encoding represents the time-series data. The encoded data may be decoded in 404 to retrieve the original time-series data.” [0078], “the machine learning model for the particular hydraulic fracturing well may be generated using a Long Short Term Memory (LSTM) autoencoder for a time t=1 to t=n.”).
It would have been obvious for a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified Alamu and Thiruvenkatanathan to incorporate the teachings of Heidari, and apply an LSTM autoencoder to encode hydraulic fracturing time series data and decode the encoded data to retrieve the original time series data in order to account for temporal relationships among sequential operating measurements and improve identification of abnormal operating conditions.
The elements of claim 14 is substantially the same as those of claim 4. Therefore, the elements of claim 14 is rejected due to the same reasons as outlined above for claim 4.
Claim(s) 7 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Alamu and
Thiruvenkatanathan as applied to claim 6 and 16 above, and further in view of Beggel US20190130279A1.
Claim 7, Alamu teaches The system of claim 6, wherein the anomaly score threshold is determined based on the operation characteristics of the well for the period of time and reconstructed operation characteristics of the well for the period of time (Page.1, Methods, Procedures, Process:” … We trained the network on stable operating data from a 2-years historical data dump of 97 sensors.” Page.5, last paragraph, “The reconstruction error of the autoencoder is calculated as the difference between the input vector to the model and its predicted output vector.” Page.6, Determination of anomaly threshold, “After training of the autoencoder, the entire stable data points are passed through the model and the mean squared error for each time stamp is determined … The mean and standard deviation of this distribution can be determined and used as anomaly threshold for the dataset.” Examiner note: the reference teaches passing the historical stable operating sensor data through the trained autoencoder, determining the mean squared error from the difference between the historical sensor values and their reconstructed values for each timestamp, and using the resulting error distribution to determine the anomaly threshold).
However, Alamu and Thiruvenkatanathan fail to teach a threshold percentage of historical anomaly scores satisfies the anomaly score threshold.
Beggel teaches a threshold percentage of historical anomaly scores satisfies the anomaly score threshold ([0043], “The anomaly decision threshold can be chosen based on reconstruction error and can depend on the distribution of reconstruction errors obtained during training. Several alternatives are possible to determine this threshold, several examples of which include: … a percentile of reconstruction errors, e.g., the 95% percentile, such that only 5% of all training images exceed this reconstruction error; and 3. an adaptive threshold that depends on the expected anomaly rate α, such as the (1−α)% percentile.” The reference teaches determining an anomaly threshold as a percentile of the distribution of historical reconstruction errors obtained during training, such as a 95th percentile threshold for which only five percent of the historical reconstruction error exceed the threshold. Thus, a threshold percentage of the historical anomaly scores satisfy the anomaly score threshold).
It would have been obvious for a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified Alamu and Thiruvenkatanathan to incorporate the teachings of Beggel, and apply determination of the anomaly score threshold using a percentile of historical reconstruction errors in order to control the proportion of historical scores classified as anomalous and provide a threshold corresponding to an expected anomaly rate.
The elements of claim 17 is substantially the same as those of claim 7. Therefore, the elements of claim 17 is rejected due to the same reasons as outlined above for claim 7.
Claim(s) 9 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Alamu and
Thiruvenkatanathan as applied to claim 1 and 11 above, and further in view of Bodishbaugh US20210025383A1.
Claim 9, Alamu and Thiruvenkatanathan fail to teach, but Bodishbaugh teaches The system of claim 1, wherein the unsupervised machine-learning model is retrained using the well operation information ([0095], “Control center 605 may further tune hyperparameters or training parameters to improve predictive performance of generalized model 730. In one embodiment, the candidate algorithms may be supervised, unsupervised … machine learning algorithms depending on the characteristics of incoming data … Once generalized model 730 that performs well is deployed, the model may be used to detect predetermined states (e.g., make predictions, classifications, diagnosis) on test field dataset 735 (i.e., live or real-time incoming data from sensors 205 during hydraulic fracturing operation) to generate predicted responses 740 (i.e., perform a prediction operation, diagnostic operation or classification operation on field data to detect one of a plurality of predetermined states for the incoming data).” [0096], “In order to keep generalized model 730 predicting accurately, control center 605 may continuously monitor incoming data and indicate that the model be updated (retrained) 745 based on new incoming data if control center 605 determines that data distribution of data on which AI model 630 is making predictions has deviated significantly from data distribution of original training dataset 710.” Examiner note: the reference teaches that generalized model 730 may use an unsupervised machine learning algorithm and is retrained based on new incoming data, and the incoming data is live or real-time sensor data obtained during hydraulic fracturing operations as well operation information).
It would have been obvious for a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified Alamu and Thiruvenkatanathan to incorporate the teachings of Bodishbaugh, and apply retraining the unsupervised machine learning model using newly obtained well operation information in order to maintain prediction accuracy and efficiency when the predictions has deviated significantly from data distribution of original training dataset [0096], thereby reduce prediction errors.
The elements of claim 19 is substantially the same as those of claim 9. Therefore, the elements of claim 19 is rejected due to the same reasons as outlined above for claim 9.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Mese (US20090055098A1) discloses predicting sand production in a wellbore. A first set of characteristics is determined for a formation in the wellbore, wherein determining uses a plastic model of the formation, and wherein the first set of characteristics comprises a yield surface, a failure surface, a stress total strain, an elastic strain, and a plastic-strain relationship …
Ige (US20130175030A1) discloses an unsupervised learning algorithm that models a set of inputs, like clustering (e.g., data mining and knowledge discovery); a semi-supervised learning algorithm that combines both labeled and unlabeled examples to generate an appropriate function or classifier.
Madasu (US20210148213A1) discloses retrain the model. For example, the model may be retrained using additional input variables, e.g., reservoir properties or other information relating to the characteristics of the subsurface formation, which may affect ROP during a drilling operation.
Any inquiry concerning this communication or earlier communications from the examiner should be
directed to YI HAO whose telephone number is (571)270-1303. The examiner can normally be reached Monday - Friday.
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 on (571)272-3652. 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.
/YI . HAO/
Examiner, Art Unit 2187
/EMERSON C PUENTE/Supervisory Patent Examiner, Art Unit 2187
Prosecution Insights