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 .
Priority
Current application, US Application No. 18/188,954, is filed on 03/23/2023.
DETAILED ACTION
This office action is responsive to the amendment filed on 02/28/2025. Claims 1-2, 6-10, 12-14, 16-19 and 21-23 are currently pending. Claims 3-5, 11, 15 and 20 are canceled and claims 21-23 are added new per applicant’s request.
Response to Amendment
Applicant's amendment is entered into further examination and appreciated by the examiner.
Response to Arguments/Remarks
Regarding remarks on the rejections under 35 USC 112(a) and 112(b), amendment is accepted and the previous rejections are withdrawn.
Regrading remarks on the rejections under 35 USC 102 and 103, applicant’s arguments have been considered but are moot in view of new ground of rejection necessitated by the amendment because the arguments do not apply to any of the references being used in the current rejection.
Claim Objections
Claims 1-2 and 6-10 are objected to because of the following informalities: As per claim 1, the limitation “a training subterranean region of interest” should be replaced with “a
As per claims 2 and 6-10, claims are also objected because base claim 1 is objected. Appropriate correction is required.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-2, 6-10, 12-13, 16-19 and 21-22 are rejected under 35 U.S.C. 101 because the claimed invention is directed to nonstatutory subject matter. The claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Specifically, representative claim 1 recites:
“A method comprising: (1.A)
obtaining a training seismic dataset pertaining to a training subterranean region of interest; (1,B)
determining a training seismic interpretation using the training seismic dataset, wherein the training seismic interpretation comprises at least two types of interpretations selected from: a geological boundary, a geological structure, a geological fault, a fracture, a pore fluid boundary, or a facies; (1.C)
training a machine learning network, using the training seismic dataset and the training seismic interpretation, to output a predicted seismic interpretation in response to an input seismic dataset, wherein the predicted seismic interpretation comprises the at least two types of interpretations. (1.D)”.
The claim limitations in the abstract idea have been highlighted in bold above; the remaining limitations are “additional elements”.
Under the Step 1 of the eligibility analysis, we determine whether the claims are to a statutory category by considering whether the claimed subject matter falls within the four statutory categories of patentable subject matter identified by 35 U.S.C. 101: Process, machine, manufacture, or composition of matter. The above claim is considered to be in a statutory category (Process or Method).
Under the Step 2A, Prong One, we consider whether the claim recites a judicial exception (abstract idea). In the above claim, the highlighted portion constitutes an abstract idea because, under a broadest reasonable interpretation, it recites limitations that fall into/recite an abstract idea exceptions. Specifically, under the 2019 Revised Patent Subject matter Eligibility Guidance, it falls into the grouping of subject matter when recited as such in a claim limitation, that covers mathematical concepts (mathematical relationships, mathematical formulas or equations, mathematical calculations) and mental processes (concepts performed in the human mind including an observation, evaluation, judgement, and/or opinion).
For example, highlighted limitation/step labeled as (1.C) is treated by the Examiner as belonging to Mathematical Concept or a combination of Mathematical Concept and Mental Process because the limitation show mathematical relationship between seismic dataset and seismic interpretation through a model with an optional mental judgment/observation.
Next, under the Step 2A, Prong Two, we consider whether the claim that recites a judicial exception is integrated into a practical application.
In this step, we evaluate whether the claim recites additional elements that integrate the exception into a practical application of that exception.
The above claims comprise the following additional elements: (Side Note: duplicated elements are not repeated)
In Claim 1: “A method”, “obtaining a training seismic dataset pertaining to a training subterranean region of interest” and “training a machine learning network, using the training seismic dataset and the training seismic interpretation, to output a predicted seismic interpretation in response to an input seismic dataset”;
In Claim 12: “A system”, “a seismic acquisition system”;
In Claims 14 and 23: “a drilling system configured to drilling a wellbore guided by the planned wellbore trajectory” or “drilling, using a drilling system, a wellbore guided by the planned wellbore trajectory”;
As per claim 1, the additional element in the preamble “A method” is not a meaningful limitation because it even fails to link the use of the judicial exception to a general technology or field of use. The limitation/step “obtaining a training seismic dataset pertaining to a training subterranean region of interest” represents a standard data collection step in the art and only adds insignificant extra solution activity to the judicial exception. The limitation/step “training a machine learning network, using the training seismic dataset and the training seismic interpretation, to output a predicted seismic interpretation in response to an input seismic dataset” could be interpreted as part of abstract idea because the machine learning network is an abstract representation of a process or object as a model and the training involves mathematical calculation of model parameters based on the mathematical relationships among the input, the expected output and the model. Even if the limitation is treated as an additional element, the training step only describes input and out and therefore is not particular in the art. The limitation/step only adds insignificant extra solution to the judicial exception at best.
As per claim 12, the additional element in the preamble “A system” is not a meaningful limitation because it even fails to link the use of the judicial exception to a general technology or field of use. The limitation/element “a seismic acquisition system” is not particular in the art.
As per claims 14 and 23, the limitations/steps “a drilling system configured to drilling a wellbore guided by the planned wellbore trajectory” or “drilling, using a drilling system, a wellbore guided by the planned wellbore trajectory” indicate an integration of a practical application to the judicial exception at step 2A prong 2. Claims are determined as patent eligible by the examiner.
In conclusion, the above additional elements except those indicated as patent eligible, considered individually and in combination with the other claim elements as a whole do not reflect an improvement to the computer technology or other technology or technical field, and, therefore, do not integrate the judicial exception into a practical application. No particular machine or real world transformation are claimed. Therefore, the claims are directed to a judicial exception and require further analysis under the Step 2B.
However, under Step 2B analysis, the above claims fails to include additional elements that are sufficient to amount to significantly more than the judicial exception as shown in the prior art of record.
The limitations/steps/elements listed as additional elements above are well understood, routine and conventional steps/elements in the art according to the prior art of record. (See Tierney, Kuroda and others under the list of prior art of record)
Claims 1-2, 6-10, 12-13, 16-19 and 21-22, therefore, are not patent eligible and claims 14 and 23 are patent eligible..
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.
Claims 1-2, 12-14, and 21-23 are rejected under 35 U.S.C. 103 as being unpatentable over Pickles (US 20240086430 A1), hereinafter ‘Pickles” in view of Salman (US 20200278465 A1), hereinafter ‘Salman’.
As per claim 1, Pickles discloses
A method (a method [abs, 0005, claim 1] ) comprising:
obtaining a training seismic dataset pertaining to a training subterranean region of interest; (receipt of input characterizing a geologic environment [abs, 005, claim 1], method, data acquisition [0052, Fig.2 220, 224], training & trained ML model [0153-0154 Fig. 11], machine leaning [0198], various types of data may be acquired …, which may provide for training one or more ML models, for retraining one or more ML models, for further training of one or more ML models, and/or for offline analysis [0201]
determining a training seismic interpretation using the training seismic dataset, wherein the training seismic interpretation comprises at least two types of interpretations selected from: a geological boundary, a geological structure, a geological fault, a fracture, a pore fluid boundary, or a facies; (interpretation process [0003-0004], seismic data may be processed and interpreted … to understand … composition, fluid content, extent and geometry of subsurface rocks [0042], sedimentological interpretations … dips, sand body orientations [0065], interpretation, various types of features … sedimentary bedding, faults and fractures [0066-0067], showing at least two types of interpretation; training & trained ML model [0153-0154 Fig. 11], machine leaning [0198], various types of data may be acquired …, which may provide for training one or more ML models, for retraining one or more ML models, for further training of one or more ML models, and/or for offline analysis [0201])
Pickles discloses training a machine learning network, using the training seismic dataset (training & trained ML model [0153-0154 Fig. 11], machine leaning [0198], various types of data may be acquired …, which may provide for training one or more ML models, for retraining one or more ML models, for further training of one or more ML models, and/or for offline analysis [0201]), but is not explicit on the predicted seismic interpretation as an output.
Salman discloses training a machine learning network, using the training seismic dataset and the training seismic interpretation, to output a predicted seismic interpretation in response to an input seismic dataset, wherein the predicted seismic interpretation comprises the at least two types of interpretations. (receiving seismic image data of a geologic region and interpretation information, train a neural network on seismic … data to generate output as to a geological feature [0155-0156, Fig. 15 1500, 1510, 1530, 1540], interpretation, various types of features may be described …. sedimentary bedding, faults and fractures, cuestas, igneous dikes and sills, metamorphic foliation [0067-0068]).
Therefore, it would have been obvious to one of ordinary skill in the art at the time when invention is filed before the effective filing date of the current application to modify the teachings of Pickles in view of Salman to train a machine learning network, using the training seismic dataset and the training seismic interpretation, to output a predicted seismic interpretation in response to an input seismic dataset, wherein the predicted seismic interpretation comprises the at least two types of interpretations to perform an efficient petroleum exploration and production according to an accurate seismic data interpretations (see Pickles - In the field of resource extraction, enhancements to interpretation can allow for construction of a more accurate model of a subsurface region, which, in tum, may improve characterization of the subsurface region for purposes of resource extraction [0004])
As per claim 2, Pickles and Salman disclose claim 1 set forth above.
Salman further discloses obtaining a first input seismic dataset pertaining to a first subterranean region of interest; inputting the first input seismic dataset into the trained machine learning network; and outputting a first predicted seismic interpretation from the trained machine learning network in response to the first input seismic dataset, wherein the first predicted seismic interpretation comprises the at least two types of interpretations. (automatic seismic interpretation machine learning models to produce interpretations [0128], utilizing the trained neural network on seismic image data to generate output as to a geologic feature of the geologic feature class [0156, Fig. 15 1540 CRM 1541], interpretation, various types of features may be described …. sedimentary bedding, faults and fractures, cuestas, igneous dikes and sills, metamorphic foliation [0067-0068]).
As per claim 12, Pickles discloses
A system (system [0005, 0008, Fig. 1 100]) comprising:
a seismic acquisition system configured to obtain an input seismic dataset pertaining to a subterranean region of interest; (data acquisition [0027, 0036, Fig. 1], system, acquisition, data [0153-0154, Fig. 11 1100 1110, 1116])
and a trained machine learning network configured to: (a trained ML model [abs, 0153—0154, Fig. 11 1130])
Pickles in view of Salman disclose the remaining limitations as shown claims 1 and 2 above.
As per claim 13, Pickles and Salman disclose claim 12 set forth above.
Pickles further discloses planning a wellbore trajectory based, at least in part, on the predicted seismic interpretation. (enabling improved quality drilling programs, drilling plan [0029], control … field equipment, drilling equipment [0041], operational decision, designing a well trajectory … to meet expected production and injection targets in specified reservoir formations [0086], AI workflow, AI component, drilling [0094-0095], well planning and design, drilling [0104], interpretation process [0003-0004], seismic data may be processed and interpreted … to understand … composition, fluid content, extent and geometry of subsurface rocks [0042])
As per claim 14, Pickles and Salman disclose claim 12 set forth above.
Pickles discloses drilling a wellbore guided by the planned wellbore trajectory. (make a drilling operation more accurate as to a borehole's trajectory where the borehole is to have a trajectory that penetrates a reservoir [0004], control … field equipment, drilling equipment [0041])
As per claim 21, Pickles in view of Salman discloses the claim as shown in claims 1 and 2 above.
As per claim 22, Pickles and Salman disclose claim 21 set forth above.
Pickles further discloses identifying a drilling target in the subterranean region of interest based on the predicted seismic interpretation; and planning, using a well planning system, a wellbore trajectory to intersect the drilling target. (enabling improved quality drilling programs, drilling plan [0029], control … field equipment, drilling equipment [0041], operational decision, designing a well trajectory … to meet expected production and injection targets in specified reservoir formations [0086], AI workflow, AI component, drilling [0094-0095], well planning and design, drilling [0104])
As per claim 23, Pickles and Salman disclose claim 21 set forth above.
Pickles discloses drilling, using a drilling system, a wellbore guided by the planned wellbore trajectory. (make a drilling operation more accurate as to a borehole's trajectory where the borehole is to have a trajectory that penetrates a reservoir [0004], control … field equipment, drilling equipment [0041])
Claims 6-7 and 16-17 are rejected under 35 U.S.C. 103 as being unpatentable over Pickles and Salman in view of Kaur (US 20210262329 A1), hereinafter ‘Kaur’.
As per claims 6 and 16, Pickles and Salman disclose claims 1 and 12 set forth above.
The set forth combined prior art is silent regarding the training seismic dataset comprising a training migrated seismic image or determining an input seismic image from the input seismic dataset.
Kaur discloses seismic image comprising migrated image can be used for training a model (seismic image, migrated image, training a deep NN [abs, 0012]).
Therefore, it would have been obvious to one of ordinary skill in the art at the time when invention is filed before the effective filing date of the current application to modify the teachings of the combined prior art in view of Kaur to disclose the training seismic dataset comprising a training migrated seismic image or determining an input seismic image from the input seismic dataset to perform an efficient petroleum exploration and production according to an accurate seismic data interpretations.
As per claims 7 and 17, Pickles, Salman and Kaur disclose claims 6 and 16 set forth above.
Kaur further discloses the training migrated seismic image comprises a training seismic attribute or the input seismic image comprises an input seismic attribute (seismic image, including extracting a reflectivity distribution, migrated image, training [abs, claim 1], generating a high-resolution seismic image includes creating a synthetic geological model; one or more features of the synthetic geological model [0011], migrated image, training [0012], seismic image … distribution of high-frequency signal [0051, Fig. 3]).
Claims 8 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Pickles, Salman and Kaur in view of Duan (US 20230184973 A1).
As per claims 8 and 18, Pickles, Salman and Kaur disclose claims 6 and 16 set forth above.
The set forth combined prior art is silent regarding dividing the training seismic dataset into a plurality of cross-sections through the training migrated seismic image.
Duan discloses generating a training data set combining with separate training data sets per various dataset parameters and cross section images can be used as the training input (make a comprehensive training set that captures a large range of expected responses, parameters may be varied for synthetic data generation [0044], Separate training datasets were generated based on the reservoir/ geo-mechanical models of each specific field [0055], image of time-shift, cross-correlation [0020-0028, Figs. 2A-4C], cross section image [0032-0033, Fig. 6A & B], generate synthetic training data for ML model, a cross-section of ML depth-shifts [0064, Figs 6B, 6D, 6F]).
Therefore, it would have been obvious to one of ordinary skill in the art at the time when invention is filed before the effective filing date of the current application to modify the teachings of the combined prior art in view of Duan to divide the training seismic dataset into a plurality of cross-sections through the training migrated seismic image to perform an efficient petroleum exploration and production according to an accurate seismic data interpretations.
Claims 9 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Pickles and Salman in view of Harsuko (Harsuko, Randy, and Tariq A. Alkhalifah. "StorSeismic: A new paradigm in deep learning for seismic processing." IEEE Transactions on Geoscience and Remote Sensing 60 (2022): 1-15), hereinafter ‘Harsuko’.
As per claims 9 and 19, Pickles and Salman disclose claims 1 and 12 set forth above.
Pickles is silent regarding a modified bidirectional encoder representation from transformers network as the trained machine learning network.
Harsuko discloses use of a modified bidirectional encoder representation from transformers network for the image interpretation task framework as a trained machined learned network (Machine learned tasks, Used often in … in vision tasks, bidirectional encoder representations from transformer (BERT), a form of a transformer model, provides an optimal platform for this framework [abs]).
Therefore, it would have been obvious to one of ordinary skill in the art at the time when invention is filed before the effective filing date of the current application to modify the teachings of the combined prior art in view of Harsuko to use a modified bidirectional encoder representation from transformers network for the image interpretation task framework as a trained machined learned network to perform an accurate seismic data interpretation for an efficient petroleum exploration and production.
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Pickles and Salman in view of Di (US 20220206175 A1), hereinafter ‘Di’
As per claim 10, Di discloses claim 1 set forth above.
Pickles is silent regarding training the machine learning network comprises forming a loss function.
Di further discloses training the machine learning network comprises forming a loss function. (training, loss function [0075-0077])
Therefore, it would have been obvious to one of ordinary skill in the art at the time when invention is filed before the effective filing date of the current application to modify the teachings of the combined prior art in view of Di to form a loss function for training the machine learning network to perform an accurate seismic data interpretation for an efficient petroleum exploration and production.
Notes with regard to Prior Art
The prior arts made of record and not relied upon are considered pertinent to applicant's disclosure.
Li (US 20220229199 A1) also discloses a method for interpreting seismic data using machine learning techniques (see [abs]).
Hlebnikov (Hlebnikov, Volodya. "Deep learning as a tool for seismic data interpolation." (2022)) discloses interpreting 2D cross-sections of the seismic data as an application of DNN [pg. 1 par. 1 from the bottom]).
Liu (US 20200183032 A1) discloses claim 1 as follows.
A method (a method [abs, 0002, 0010, claim 1] ) comprising:
obtaining a training seismic dataset pertaining to a training subterranean region of interest; (subsurface geological features from seismic dataset [0010] with seismic datasets [0030])
determining a training seismic interpretation using the training seismic dataset, wherein the training seismic interpretation comprises at least two types of interpretations selected from: a geological boundary, a geological structure, a geological fault, a fracture, a pore fluid boundary, or a facies; (interpretation process [0003-0004], seismic data may be processed and interpreted … to understand … composition, fluid content, extent and geometry of subsurface rocks [0042], sedimentological interpretations … dips, sand body orientations [0065], interpretation, various types of features … sedimentary bedding, faults and fractures [0066-0067], training & trained ML model [0153-0154 Fig. 11], machine leaning [0198], various types of data may be acquired and optionally stored, which may provide for training one or more ML models, for retraining one or more ML models, for further training of one or more ML models, and/or for offline analysis [0201])
training a machine learning network, using the training seismic dataset and the training seismic interpretation, to output a predicted seismic interpretation in response to an input seismic dataset, wherein the predicted seismic interpretation comprises the at least two types of interpretations. (training & trained ML model [0153-0154 Fig. 11], machine leaning [0198], various types of data may be acquired and optionally stored, which may provide for training one or more ML models, for retraining one or more ML models, for further training of one or more ML models, and/or for offline analysis [0201])
Conclusion
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.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DOUGLAS KAY whose telephone number is (408) 918-7569. The examiner can normally be reached on M, Th & F 8-5, T 2-7, and W 8-1.
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 on 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 an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see https://ppair-my.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/DOUGLAS KAY/Primary Examiner, Art Unit 2857