Notice of Pre-AIA or AIA Status
1. 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
2. This second Non-Final Office Action is responsive to Applicants’ reply received 11/14/25. Claims 1-20 remain pending, of which claims 1, 8, and 15 are independent.
Claim Rejections - 35 USC § 103
3. 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.
4. 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.
5. 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.
6. Claims 1, 3-8, and 10-14 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent Application No. 2019/0383965 (“Salman”) in view of U.S. Patent Application No. 2020/0183047 (“Denali”, previously cited in Applicants’ IDS submission dated 2/18/22).
Regarding claim 1, SALMAN teaches A method of identifying a drilling target ([0002]: “Geophysical data are acquired using various types of sensors and processes. Geophysical data can be log data as acquired via equipment disposed in one or more locations where one of the locations includes a bore location (e.g., consider wireline, logging while drilling, etc.). Geophysical data can be seismic data, for example, as acquired via reflection seismology equipment. Reflection seismology finds use in geophysics, for example, to estimate properties of subsurface formations ... Seismic data may be processed and interpreted, for example, to understand better composition, fluid content, extent and geometry of subsurface rocks. Various techniques described herein pertain to acquisition, processing and/or control of data such as, for example, one or more of log data and seismic data.”, cited as providing a context for FIG. 1’s system having a management component to “... allow for direct or indirect management of sensing, drilling, injecting, extracting, etc., with respect to the geologic environment ...” (from [0039] and [0105]), e.g., using a control signal based on an interpretation result as discussed per [0236]: “... As an example, a system can include an interface that outputs at least one control signal based at least in part on interpretation results. For example, where interpretation results indicates that hydrocarbons (e.g., pay) exists in a geologic environment, a control signal may be issued to one or more pieces of drilling equipment and/or one or more other pieces of equipment where such a control signal can cause a field or other operation to reach, produce, etc., at least a portion of the hydrocarbons.” [based on the reference as a whole but particularly these cited portions, the Examiner understands the taught framework to encompass the acquisition and interpretation of seismic data to intelligently control drilling to reach subsurface hydrocarbons]), comprising:
obtaining a training set of base subsurface models ([0106] discussing the training and implementing of deep learning networks to interpret seismic data, via the use of algorithms that generate training data that includes synthetic data based on a geologic environment to essentially model the environment, where [0107]-[0108] elaborates that a particular model may be subject to modification to create variations of the geologic environment having different subsurface structural features, where at least the aforementioned particular model being perturbed/modified is a “base subsurface model” as recited that is indicated for use in training);
generating, using an algorithm, a plurality of subsurface model realizations based on training set of the base subsurface models and simulating, for each subsurface model realization among the plurality of subsurface model realizations, a synthetic seismic dataset and training a second artificial intelligence neural network, using the plurality of subsurface model realizations and the synthetic seismic dataset for each subsurface model realization, to predict an inferred subsurface model from a seismic dataset ([0106]-[0108] as discussed above, mentioning the use of an algorithm to modify a particular model to create various modifications of that model, where these modifications are applied to generate the synthetic seismic data for training a deep learning network that interprets seismic data to interpret subsurface features/structures, see e.g., [0108]: “... a model modification may pertain to one or more structural features such as an interface, a fault, a fracture, a geobody, etc. For example, where the shape of an interpreted geobody is to be enhanced, a model may be modified or a plurality of models generated with geobodies of different shapes where such different shapes can be labeled with one or more labels. In such an example, seismic data may be simulated for each of the different shapes where the seismic data include indicia thereof. Such seismic data may be utilized to train a deep learning network where the trained deep learning network may be utilized to interpret real seismic data (e.g., non-synthetic seismic data) of a geologic environment to output interpretation results that more accurately characterize the shape of a geobody in the geologic environment. ...”, where the Examiner is equating the taught “deep learning network” with Applicants’ recitation of “a second artificial intelligence neural network”);
obtaining an observed seismic dataset for a subterranean region of interest and predicting, using the trained second artificial intelligence neural network, a predicted inferred subsurface model from the observed seismic dataset (the deep learning network, as discussed above per [0106]-[0108], is shown to be applied with respect to “acquired geophysical data” to interpret it (FIG. 3’s steps 345, 350, and 360), which the Examiner understands to involve the development of an interpretation of the acquired data based on leveraging of the trained deep learning network which itself encompasses many modifications/variations of a model for the geologic environment, such that the interpretation would be made based on a similarity between the acquired data and a particular set of synthetic data (which the Examiner equates with Applicants’ recitation of “an inferred subsurface model”)); and
identifying the drilling target based on the predicted inferred subsurface model (as already discussed in relation to the preamble, but see specifically [0100] (“As mentioned, a method can include performing one or more actions based at least in part on interpretation results as may be output per the output block 360. For example, a signal may be issued that instructions one or more pieces of equipment to perform one or more actions, which may be one or more field actions (e.g., as to exploration, surveying, data acquisition, drilling, stimulation, production, etc.).”) and [0236] (“... As an example, a system can include an interface that outputs at least one control signal based at least in part on interpretation results. For example, where interpretation results indicates that hydrocarbons (e.g., pay) exists in a geologic environment, a control signal may be issued to one or more pieces of drilling equipment and/or one or more other pieces of equipment where such a control signal can cause a field or other operation to reach, produce, etc., at least a portion of the hydrocarbons.”)).
The Examiner notes that Applicants’ claim requires use of a first artificial intelligence neural network to perform its step of generating ... a plurality of subsurface model realizations based on the training set of base subsurface models. As discussed above, Salman teaches the use of an “algorithm” to vary what is a base model, e.g., to create versions of it with different subsurface structure/feature expressions included therein that constitute its synthetic training data. For some clarification, see [0066]-[0067], [0078]-[0081], [0084]-[0085] with [0085] indicating an objective of the training data to be realistic, and [0106]-[0108]. While Salman provides features that are functionally equivalent to this further recitation with respect to its larger framework and objective, Salmon does not teach that its algorithm is a neural network per Applicants’ further recitation. However, the Examiner notes that it is known in the state of the art to perform the functionality described per Salman as noted here with a neural network specifically, and to that end, the Examiner relies upon DENALI to teach what Salman otherwise lacks, see e.g., Denali’s comparable framework for seismic data collection, analysis and interpretation ([0002]) where a generative adversarial network (i.e., a type of neural network, comporting with Applicants’ recitation) is used to that general effect ([0063], [0066]). The widely understood premise for using a GAN is that its generator is trained in accordance with the use of a discriminator until the generated information from the generator is sufficiently realistic; hence, it provides a training mechanism such that the generative/synthetic data is useful for standing in as real data and helps facilitate effective deep learning.
The cited art both relate to seismic data collection, analysis, and interpretation frameworks, generally, and specifically involve features that generate synthetic data in promotion of their accuracy and performance. Hence, in the Examiner’s view, they are similarly directed and therefore analogous. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Denali’s GAN to improve upon the existing synthetic data generation feature found in Salman, with a reasonable expectation of success, for purposes of promoting realism in Salman’s synthetic data via a generator-discriminator feature as taught by Denali.
Regarding claim 3, Salman in view of Denali teach the method of claim 1, as discussed above. The aforementioned references teach the additional limitations wherein each base subsurface model among the training set of base surface models comprises: a base background model; and a plurality of base canonical geological structures (Salman’s [0107]-[0108] discussing the modeling of a geologic environment with structure features essentially included into it to arrive at variations of that model). The motivation for combining the references is as discussed above in relation to claim 1.
Regarding claim 4, Salman in view of Denali teach the method of claim 3, as discussed above. The aforementioned references teach the additional limitations wherein a canonical geological structure within one of the plurality of base canonical geological structures comprises at least one of an archaic sand dune, a wadi1, or a karst (Salman’s [0200]-[0209] discussing a type of geoscience domain (per [0080]) that is subject to an application of the taught invention, and specifically one that is described and captured in terms of buried basins and channels (which the Examiner likens to Applicants’ recitation of a wadi)). The motivation for combining the references is as discussed above in relation to claim 1.
Regarding claim 5, Salman in view of Denali teach the method of claim 1, as discussed above. The aforementioned references teach the additional limitations wherein the first artificial intelligence neural network comprises a Generative Adversarial Neural Network (Denali, as discussed in relation to claim 1: see e.g., Denali’s comparable framework for seismic data collection, analysis and interpretation where a generative adversarial network (i.e., a type of neural network) is used to that general effect. The widely understood premise for using a GAN is that its generator is trained in accordance with the use of a discriminator until the generated information from the generator is sufficiently realistic; hence, it provides a training mechanism such that the generative/synthetic data is useful for standing in as real data). The motivation for combining the references is as discussed above in relation to claim 1.
Regarding claim 6, Salman in view of Denali teach the method of claim 1, as discussed above. The aforementioned references teach the additional limitations wherein the second artificial intelligence neural network comprises a Deep Neural Network (Salman, as discussed in relation to claim 1: [0106]-[0108] discussing the use of an algorithm to modify a particular model to create various modifications of that model, where these modifications are applied to generate the synthetic seismic data for training a deep learning network that interprets seismic data to interpret subsurface features/structures, where the Examiner is equating the taught “deep learning network” with Applicants’ recitation of “a second artificial intelligence neural network” ). The motivation for combining the references is as discussed above in relation to claim 1.
Regarding claim 7, Salman in view of Denali teach the method of claim 1, as discussed above. The aforementioned references teach the additional limitations wherein simulating the synthetic seismic dataset comprises using a finite-difference solution to an elastic wave equation (Salman’s [0197] discussing its computational framework for wavefield modelling and synthetic data generation as including “finite difference modelling (FDMOD)”, where the waves involved as understood to be “waves of elastic energy” as discussed per Salman’s [0002] and [0113] for example, which as subject to modelling, capture, or characterization would be understood to be defined in terms of a function or equation (see Salman’s [0084]: “... generate synthetic data as modeled (e.g., via wave equation) ...”), as an example of an applied step or algorithm related to its synthetic seismic data generation aspect). The motivation for combining the references is as discussed above in relation to claim 1.
Regarding claim 8, the claim includes the same or similar limitations as claim 1 discussed above, and is there rejected under the same rationale. The present claim additionally recites a non-transitory computer readable medium storing instructions executable by a computer processor to essentially perform the same steps already addressed above in relation to claim 1, and the additional features of the CRM and processor are likewise taught by Salman at [0239] for example.
Regarding claim 10, the claim includes some of the same features as already discussed above in relation to claim 3, and is therefore rejected under the same rationale given there.
Regarding claim 11, the claim includes the same features as already discussed above in relation to claim 4, and is therefore rejected under the same rationale given there.
Regarding claim 12, the claim includes the same features as already discussed above in relation to claim 5, and is therefore rejected under the same rationale given there.
Regarding claim 13, the claim includes the same features as already discussed above in relation to claim 6, and is therefore rejected under the same rationale given there.
Regarding claim 14, the claim includes the same features as already discussed above in relation to claim 7, and is therefore rejected under the same rationale given there.
7. Claims 2, 9, and 15-20 are rejected under 35 U.S.C. 103 as being unpatentable over Salman in view of Denali and further in view of Non-Patent Literature “An Automatic Well Planner for Complex Well Trajectories” (“Kristoffersen”).
Regarding claim 2, Salman in view of Denali teach the method of claim 1, as discussed above. As discussed per claim 1, Salman teaches the use of the deep learning interpretation of seismic data to generally perform actions conducive to exploration, production, drilling, etc. See Salman’s [0100] (“As mentioned, a method can include performing one or more actions based at least in part on interpretation results as may be output per the output block 360. For example, a signal may be issued that instructions one or more pieces of equipment to perform one or more actions, which may be one or more field actions (e.g., as to exploration, surveying, data acquisition, drilling, stimulation, production, etc.).”) and also Salman’s [0236] (“... As an example, a system can include an interface that outputs at least one control signal based at least in part on interpretation results. For example, where interpretation results indicates that hydrocarbons (e.g., pay) exists in a geologic environment, a control signal may be issued to one or more pieces of drilling equipment and/or one or more other pieces of equipment where such a control signal can cause a field or other operation to reach, produce, etc., at least a portion of the hydrocarbons.”)). That said, the teachings fall just short of clearly defining a path determination to better define/guide the drilling as is taught, see e.g., Applicants’ further limitations for determining a wellbore path to intersect the drilling target and drilling a wellbore guided by the wellbore path. Rather, the Examiner relies upon Kristoffersen to teach what Salman etc. otherwise lack, see e.g., Kristoffersen’s section 2.1 which appears to take the results of a simulated reservoir model (such as one Salman can provide with its modelling) to decide per section 2.2 how to drill it for production purposes. Section 2.2 and its subsections specifically address trajectory and steering of the determined drilling operation, which the Examiner likens to Applicants’ recitation of a path.
Regarding claim 9, the claim teaches the same/similar features as found in claim 2 discussed above, and is therefore similarly rejected on the grounds.
Regarding claim 15, the claim teaches the same/similar features as found in claim 2 discussed above, and is therefore similarly rejected on the grounds.
Regarding claim 16, the claim teaches the same/similar features as found in claim 2 discussed above, and is therefore similarly rejected on the grounds.
Regarding claim 17, the claim teaches the same/similar features as found in claim 3 discussed above, and is therefore rejected based on the same mappings provided above in relation to claim 3 based on the art discussed above per claims 2 and 15.
Regarding claim 18, the claim teaches the same/similar features as found in claim 4 discussed above, and is therefore rejected based on the same mappings provided above in relation to claim 4 based on the art discussed above per claims 2 and 15.
Regarding claim 19, the claim teaches the same/similar features as found in claims 5-6 discussed above, and is therefore rejected based on the same mappings provided above in relation to claims 5-6 based on the art discussed above per claims 2 and 15.
Regarding claim 20, the claim teaches the same/similar features as found in claim 7 discussed above, and is therefore rejected based on the same mappings provided above in relation to claim 7 based on the art discussed above per claims 2 and 15.
Conclusion
8. The prior art made of record and not relied upon is considered pertinent to Applicants’ disclosure:
Non-Patent Literature “Data Augmentation with Improved Generative Adversarial Networks” (Shi)
9. Any inquiry concerning this communication or earlier communications from the examiner should be directed to SHOURJO DASGUPTA whose telephone number is (571)272-7207. The examiner can normally be reached M-F 8am-5pm CST.
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, Tamara Kyle can be reached at 571 272 4241. 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.
/SHOURJO DASGUPTA/Primary Examiner, Art Unit 2144
1 The Examiner is interpreting this as indicating a subsurface valley, ravine, or channel, based on the specification and a definition found online via the Oxford dictionary.