DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of Claims
Applicant’s reply dated 03/10/2025 amended claims 1, 2, 4, 5, 6, 8, 9, 11, 12, 13, 15, 16, 18, and 19. Claims 1-20 are pending and rejected as set forth below.
Response to Amendment
The 35 U.S.C. 101 rejection of claims 1-20 is maintained with a revised rejection below addressing the amendments to the claims.
The 35 U.S.C. 103 rejection(s) of claims 1-20 in the previous office action are withdrawn However, the claims are newly rejected under 103 as necessitated by amendment. Applicant’s arguments are moot and/or unpersuasive in view of the new grounds of rejection.
Response to Arguments
Applicant argues that claim 1 is analogous to the claim found eligible in Example 48 claim 2 because the determining of the velocity model integrates the abstract idea into a practical application (Remarks P. 12-16). Examiner respectfully disagrees. The determining of the velocity model is itself part of the abstract idea, i.e. is merely determining a numerical/mathematical representation (e.g. Applicant’s spec. [0039] EQ2, “m is a vector indicating the direction velocities at the spatial coordinate x”) through mathematical calculations (e.g. see spec. [0057] describing the mathematical calculations performed by the LSTM to predict the output vector) and thus is not an additional element when analyzed under Step 2A Prong 2 and cannot itself integrate the abstract idea into a practical application. The use of the “machine-learned model” is an additional element, however, the claims are found to recite the use of the ML model at a high-level of generality to make predictions that are otherwise abstract and is thus merely the use of general purpose computer technology as a tool. Therefore, the determination of a velocity model in the instant case is more akin to the determining of embedding vectors using a DNN found ineligible in Example 48 Claim 1 or to the detection of anomalies by an ANN in Example 47 Claim 2.
Applicant argues that the training of a ML model using seismic data sets having been transformed to the wavenumber-time domain provides an improvement to velocity model determination and thus integrates the abstract idea into a practical application (Remarks P. 17). This argument is unpersuasive. The improvements are to the abstract idea itself (velocity model determination) and not an improvement to the functioning of the computer or computer technology. Applicant asserts that the improvement arises due to the “transforming” however this is part of the abstract idea itself. For example, the transforming when read in light of the specification is merely a manipulation of the data through sorting the data and mathematical transformation (Fourier transform) (see Spec. [0063]). See MPEP 2106.05(a): “It is important to note, the judicial exception alone cannot provide the improvement.” And MPEP 2106.04(a)(2): “Examples of mathematical relationships recited in a claim include: iv. organizing information and manipulating information through mathematical correlations, Digitech Image Techs., LLC v. Electronics for Imaging, Inc., 758 F.3d 1344, 1350, 111 USPQ2d 1717, 1721 (Fed. Cir. 2014). The patentee in Digitech claimed methods of generating first and second data by taking existing information, manipulating the data using mathematical functions, and organizing this information into a new form. The court explained that such claims were directed to an abstract idea because they described a process of organizing information through mathematical correlations, like Flook's method of calculating using a mathematical formula. 758 F.3d at 1350, 111 USPQ2d at 1721.”
Applicant argues that the “machine-learned model of independent claim 1 is properly described with meaningful limitations on its operation such that it is more than a mere tool to perform an alleged mental process” (Remarks P. 18). Examiner respectfully disagrees. The claims do not specify any details of the machine-learned model itself. The claims merely describe the inputs and outputs to the model and the data used to train the model which is mere data characterization. There are no details on how the machine-learned model itself functions, it is simply claimed as a black box. The use of a ML model at this high-level of generality is the use of a general purpose computer as a tool and/or merely an attempt to limit the abstract idea to a particular technological environment. The ML model is used in its ordinary capacity to make predictions/determinations that are otherwise abstract and thus fails to integrate the abstract idea into a practical application. See MPEP 2106.05(f): “Use of a computer or other machinery in its ordinary capacity for economic or other tasks (e.g., to receive, store, or transmit data) or simply adding a general purpose computer or computer components after the fact to an abstract idea (e.g., a fundamental economic practice or mathematical equation) does not integrate a judicial exception into a practical application or provide significantly more.”
Applicant argues that the claims provide an unconventional use of a machine-learned model with a particular domain transfer of the seismic data and thus amounts to significantly more (Remarks P. 20). This argument is unpersuasive. As discussed above, the use of a ML model in this case is the use of general purpose computer technology as a tool to apply the abstract idea. The “a particular domain transfer” appears to refer to the “transforming” step in the claims which is a data manipulation using mathematical functions and thus is part of the abstract idea itself and not an additional element under Step 2B. Therefore, for similar reasons as discussed above with respect to Step 2A Prong 2, using a generic machine-learned model on input data that has been “transformed” is not enough to necessitate a conclusion that the claims amount to significantly more. Noting that whether or not something is well-understood, routine, or conventional is a consideration with respect to the additional elements and new or novel abstract ideas are still abstract (MPEP 2106.04(I)).
For at least these reasons, Applicant’s arguments with respect to 35 U.S.C. 101 are unpersuasive and the rejection is maintained.
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 filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual 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/apply/applying-online/eterminal-disclaimer.
Claims 1, 3, 7, 8, 10, 14, 15, 17, and 20 are provisionally rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1, 3, 7, 8, 10, 11, 13, 15, 16, 17, 19, 20 of copending Application No. 18362720 (reference application). Although the claims at issue are not identical, they are not patentably distinct from each other because the claims in the ‘720 application anticipate and/or render obvious the claims of the instant application.
This is a provisional nonstatutory double patenting rejection because the patentably indistinct claims have not in fact been patented.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception without significantly more. A subject matter eligibility analysis is set forth below. See MPEP 2106.
Specifically, representative Claim 1 recites:
A method, comprising:
receiving an input seismic data set and a data type for the input seismic data set, wherein the input seismic data set corresponds to a subsurface region of interest;
obtaining an initial velocity model, wherein the initial velocity model corresponds to the data type;
perturbing the initial velocity model to form a plurality of velocity models;
determining, using a forward model, a plurality of seismic data sets from the plurality of velocity models;
transforming the plurality of seismic data sets to a wavenumber-time domain to form a plurality of transformed seismic data sets;
training a machine-learned model using the plurality of velocity models and the first plurality of transformed seismic data sets, wherein the machine-learned model is configured to accept, as input, a transformed seismic data set associated with the data type and return, as output, a velocity model;
transforming the input seismic data set to the wavenumber-time domain to form an input transformed seismic data set;
determining a velocity model for the subsurface region of interest by processing the input transformed seismic data set with the trained machine-learned model;
determining a presence or location of a hydrocarbon reservoir in the subsurface region of interest based on the velocity model for the subsurface region of interest.
The claim limitations in the abstract idea have been highlighted in bold above; the remaining limitations are “additional elements.”
Similar limitations comprise the abstract idea of non-transitory computer-readable medium claim 8 and system claim 15.
Under Step 1 of the analysis, claims 1, 8, and 15 belong to a statutory category, namely a “method”, “non-transitory computer-readable medium”, and “system”, respectively.
Under Step 2A, prong 1: This part of the eligibility analysis evaluates whether the claim recites a judicial exception. As explained in MPEP 2106.04, subsection II, a claim “recites” a judicial exception when the judicial exception is “set forth” or “described” in the claim.
In the instant case, claim 1 is found to recite at least one judicial exception (i.e. abstract idea), that being a Mental Process and/or a Mathematical Concept. This can be seen in the claim limitations of “determining” hydrocarbon reservoir presence/location based on the determined velocity model which is the judicial exception of a mental process because these limitations are merely data observations, evaluations, and/or judgements capable of being performed mentally and/or with the aid of pen and paper. Additionally, the limitations highlighted in claim 1 above recite Mathematical Concepts including mathematical calculations for perturbing velocity models, performing forward modeling, transforming data through Fourier transform, and training a ML model to predict velocity models based on the input seismic data, e.g. see Spec. [0039]-[0053] describing the various mathematical calculations, equations, and relationships used.
Similar limitations comprise the abstract ideas of Claims 8 and 15.
Step 2A, prong 2 of the eligibility analysis evaluates whether the claim as a whole integrates the recited judicial exception(s) into a practical application of the exception. This evaluation is performed by (a) identifying whether there are any additional elements recited in the claim beyond the judicial exception, and (b) evaluating those additional elements individually and in combination to determine whether the claim as a whole integrates the exception into a practical application.
In addition to the abstract ideas recited in claim 1, the claimed method recites additional elements including “receiving an input seismic data set and a data type for the input seismic data set, wherein the input seismic data set corresponds to a subsurface region of interest” however these elements are found to be data gathering steps, which are recited at a high level of generality, and thus merely amount to “insignificant extra-solution” activity(ies), e.g. the claims do not specify how the data is received such that it could simply be retrieved from general purpose computer memory. See MPEP 2106.05(g) “Insignificant Extra-Solution Activity,”. Furthermore, the claim recites that velocity model is determined “with the trained machine-learned model” which implies processing by a general purpose computer. However, the use of a computer to performed the claimed modeling is found to be equivalent to adding the words “apply it” and mere instructions to apply a judicial exception on a general purpose computer does not integrate the abstract idea into a practical application. See MPEP 2106.05(f). Therefore, the use of “machine-learned model” to perform steps that are otherwise abstract does not integrate the abstract idea into a practical application. See the 2024 Guidance Update on Patent Subject Matter Eligibility, Including on Artificial Intelligence1; and Example 47, ineligible claim 22.
Claims 8 and 15 recite the same additional elements as claim 1 and also recites “A non-transitory computer readable medium storing instructions executable by a compute processor, the instructions comprising functionality for:” (claim 8) and “A system, comprising: a seismic data acquisition system comprising at least one seismic source and seismic receiver; a computer comprising one or more computer processors and configured to:” (claim 15) which merely amount to general purpose computer hardware and/or software components used as a tool to “apply” the abstract idea in a technological environment. Further, claim 15 recites that the computer system obtains data “from the seismic data acquisition system,” and “from a database” however the receiving of data over a network or from memory is found to be insignificant extra-solution activity, i.e. data gathering. See MPEP 2106.05(h): “For instance, a data gathering step that is limited to a particular data source (such as the Internet) or a particular type of data (such as power grid data or XML tags) could be considered to be both insignificant extra-solution activity and a field of use limitation.”
The generic data gathering, processing, and output steps, are recited at such a high level of generality that it represents no more than mere instructions to apply the judicial exceptions on a computer. It can also be viewed as nothing more than an attempt to generally link the use of the judicial exceptions to the technological environment of a computer. Noting MPEP 2106.04(d)(I): “It is notable that mere physicality or tangibility of an additional element or elements is not a relevant consideration in Step 2A Prong Two. As the Supreme Court explained in Alice Corp., mere physical or tangible implementation of an exception does not guarantee eligibility. Alice Corp. Pty. Ltd. v. CLS Bank Int’l, 573 U.S. 208, 224, 110 USPQ2d 1976, 1983-84 (2014) ("The fact that a computer ‘necessarily exist[s] in the physical, rather than purely conceptual, realm,’ is beside the point")”.
Thus, under Step 2A, prong 2 of the analysis, even when viewed in combination, these additional elements do not integrate the recited judicial exception into a practical application and the claim is directed to the judicial exception. No specific practical application is associated with the claimed system. For instance, nothing is done with the result of determining the velocity model beyond making further determinations as to the presence or location of hydrocarbon reservoirs that are themselves abstract, as discussed above.
Under Step 2B, the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements, as described above with respect to Step 2A Prong 2, merely amount to a general purpose computer system that attempts to apply the abstract idea in a technological environment, limiting the abstract idea to a particular field of use, and/or merely performs insignificant extra-solution activit(ies) (claims 1, 8, and 15). Such insignificant extra-solution activity, e.g. data gathering and output, when re-evaluated under Step 2B is further found to be well-understood, routine, and conventional as evidenced by MPEP 2106.05(d)(II) (describing conventional activities that include transmitting and receiving data over a network, electronic recordkeeping, storing and retrieving information from memory, and electronically scanning or extracting data from a physical document).
Therefore, similarly the combination and arrangement of the above identified additional elements when analyzed under Step 2B also fails to necessitate a conclusion that claim 1, as well as claims 8 and 15, amount to significantly more than the abstract idea.
With regards to the dependent claims, claims 2-7, 9-14, and 16-20, merely further expand upon the algorithm/abstract idea and do not set forth further additional elements that integrate the recited abstract idea into a practical application or amount to significantly more. The dependent claims either do not recite any additional elements or only set forth generic elements that are insufficient to render the claims eligible for similar reasons as those discussed above. Therefore, these claims are found ineligible for the reasons described for parent claims 1, 8, and 15.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1, 2, 4-6, 8, 9, 11-13, 15, 16, 18, and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over: Wang et al. US 20220018981 A1 (hereinafter “Wang”) in view of Ikelle US 20070274155 A1 (hereinafter “Ikelle”).
Regarding claims 1, 8, and 15,
Wang teaches: A method, comprising:
receiving an input seismic data set and a data type for the input seismic data set, wherein the input seismic data set corresponds to a subsurface region of interest; ([0009]: “may include receiving a 5D seismic dataset representative of a subsurface volume of interest and a 3D velocity model;”, [0033]: “These choices can be further optimized based on the survey type, geological environment and the desired resolution of the output velocity model”)
obtaining an initial velocity model, wherein the initial velocity model corresponds to the data type; perturbing the initial velocity model to form a plurality of velocity models; ([0028]: “An ideal training dataset can be selected from multiple field datasets with tens of thousands of shot groups and accurately defined velocity models. Alternatively, synthetic data simulated from perturbed or randomly generated velocity models can also be used as training data,”)
determining, using a forward model, a plurality of seismic data sets from the plurality of velocity models; ([0028]: “Alternatively, synthetic data simulated from perturbed or randomly generated velocity models can also be used as training data, with the caveat that the discrepancy between synthetic seismic forward modeling”, [0039]: “Incorporating physical constraints in training is another option with part of the loss function characterizing the fidelity of physical correctness by simulating shots with forward modeling.”)
training a machine-learned model using the plurality of velocity models and the first plurality of transformed seismic data sets, wherein the machine-learned model is configured to accept, as input, a transformed seismic data set associated with the data type and return, as output, a velocity model; (Abstract, [0009]: “preparing a subset of the 5D seismic dataset and a subset of the 3D velocity model to generate a training dataset; training a model using the training dataset to generate a trained model…estimating a predicted velocity model using the trained model and a subset of the 5D seismic dataset”, [0026]: “An embodiment takes multiple shot records, each with 3 dimensions of cable, channel and time as training features and a block of velocity within the shot-receiver coverage of the shot group as the training label. The DNN learns the mapping from shot records to a block of underlying velocity model.”, [0052]: “build a neural network based on training data”, [0036]: “After the training dataset has been prepared, it is used to train a model (operation 18).”
determining a velocity model for the subsurface region of interest by processing the input transformed seismic data set with the trained machine-learned model; ([0009]: “estimating a predicted velocity model using the trained model and a subset of the 5D seismic dataset;”, [0042]: “Once the model is trained, it can be used with any appropriate 5D seismic dataset to predict a velocity model.”, [0045]: “FIGS. 7, 8, 9, and 10 illustrate examples of the trained model from method 100 being used for predicting velocity models for a synthetic seismic dataset (the synthetic seismic dataset is associated a “ground truth” velocity model).”)
determining a presence or location of a hydrocarbon reservoir in the subsurface region of interest based on the velocity model for the subsurface region of interest. ([0045]: “The velocity model can be used as an FWI initial model for further updates, or for seismic imaging (e.g., migration) in order to generate a seismic image that can be interpreted to identify subsurface geologic features including hydrocarbon reservoirs.”)
Although Wang describes preparing and processing the seismic data, e.g [0027], Wang fails to clearly describe transforming the seismic data sets to a wavenumber-time domain.
Ikelle however, in analogous art of seismic data processing, teaches:
transforming the plurality of seismic data sets to a wavenumber-time domain to form a plurality of transformed seismic data sets; ([0251] “(2) Sort the data into receiver or CMP gathers.”; [0252] “(3) Transform the receiver gathers to the F-K or K-T (wavenumber-time) domain.”)
transforming the input seismic data set to the wavenumber-time domain to form an input transformed seismic data set; ([0251] “(2) Sort the data into receiver or CMP gathers.”; [0252] “(3) Transform the receiver gathers to the F-K or K-T (wavenumber-time) domain.”)
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to have modified Wang’s training of a ML model based on seismic data sets to predict velocity models, as described above, to clearly include transforming the seismic data sets for use in training the ML model and as input to the ML model for velocity model prediction in view of Ikelle, with the motivation to more easily and cost effectively generate seismic data sets for velocity modeling, e.g. Ikelle [0042]-[0043] (see MPEP 2143 G).
Claims 8 and 15 recite the same or substantially similar claim limitations as independent claim 1 merely further reciting “A non-transitory computer readable medium storing instructions executable by a compute processor, the instructions comprising functionality for:” (claim 8) and “A system, comprising: a seismic data acquisition system comprising at least one seismic source and seismic receiver; and a computer comprising one or more computer processors and configured to:” (Claim 15) which is also taught by Wang describing implementing the described method(s) using a computer system (Fig. 11, [0053]) and seismic data acquisition comprising a seismic source and receiver ([0003]-[0004], [0026]-[0027]: “the method receives 5D seismic data at operation 10”) and thus claims 8 and 15 are similarly rejected under 35 U.S.C. 103 as being unpatentable over Wang in view of Ikelle for the same reasons as representative claim 1.
Regarding claims 2, 9, and 16,
Wang in view of Ikelle teach the elements of parent claims 1, 8, and 15 as described above.
Wang fails to describe, however Ikelle further teaches: wherein transforming the plurality of seismic data sets and transforming the input seismic data set further comprises: sorting the data to a common middle point; and applying a Fourier transform to the sorted data. ([0251] “(2) Sort the data into receiver or CMP gathers.”; [0252] “(3) Transform the receiver gathers to the F-K or K-T (wavenumber-time) domain.”)
One of ordinary skill in the art would have been motivated to combine these references’ teachings to render the claimed invention obvious for the same or similar reasons as described above in regard to parent claims 1, 8, and 15.
Regarding claims 4, 11, and 18,
Wang in view of Ikelle teach the elements of parent claims 1, 8, and 15 as described above.
Wang further teaches: constructing a subsurface model for the subsurface region of interest based, at least in part, on the velocity model for the subsurface region of interest, wherein the subsurface model informs oil and gas field planning and lifecycle management decisions. ([0009]: “and concatenating the set of estimated velocity models to generate a whole 3D velocity model.”; [0045]: “The velocity model can be used as an FWI initial model for further updates, or for seismic imaging (e.g., migration) in order to generate a seismic image that can be interpreted to identify subsurface geologic features including hydrocarbon reservoirs.”; [0007]: “Decisions include, but are not limited to, budgetary planning, obtaining mineral and lease rights, signing well commitments, permitting rig locations, designing well paths and drilling strategy, preventing subsurface integrity issues by planning proper casing and cementation strategies, and selecting and purchasing appropriate completion and production equipment.”)
Regarding claims 5, 12, and 19,
Wang in view of Ikelle teach the elements of parent claims 1, 8, and 15 as described above.
Wang further teaches:
obtaining a seismic data database comprising at least one of a seismic data set having a streamer data type, a seismic data set having an ocean bottom node data type, and a seismic data set having a land data type; ([0026]: “In exploration and appraisal surveys, 5-dimensional data (shot X, Y coordinates, receiver cable, channel and time) are acquired for 3D velocity modeling and imaging…An embodiment takes multiple shot records, each with 3 dimensions of cable, channel and time as training features and a block of velocity within the shot-receiver coverage of the shot group as the training label.”, [0027]: “As explained above, the method receives 5D seismic data at operation 10.”, [0029]: “marine and land surveys… One example for differentiating data collection and organization based on survey type”; [0004]: “the sensors generate corresponding electrical signals, known as traces, and record them in storage media as seismic data.”)
selecting an initial seismic data set from the seismic data database according to the data type of the input seismic data set; ([0009]: “preparing a subset of the 5D seismic dataset and a subset of the 3D velocity model to generate a training dataset”; [0031]: “When training data contains multiple field surveys, it is necessary to pre-process seismic traces prior to feeding to a Deep Neural Network.”; [0033]: “ These choices can be further optimized based on the survey type” ) and
processing the initial seismic data set with a benchmark model to determine the initial velocity model. ([0031]: “The training label-velocity model can be the full salt model out of a conventional Tomography workflow, or a Full Waveform Inversion (FWI) model.”, [0005]: “Subsurface velocity can be estimated from seismic surveys acquired from the surface. The main algorithms are seismic tomography and Full Waveform Inversion (FWI), which start from an initial model, simulate ray or wave propagation and derive gradients from data misfit to update the model.”)
Regarding claims 6 and 13,
Wang in view of Ikelle teach the elements of parent claims 1, 8, and 15 as described above.
Wang further teaches: wherein the forward model is configured according to a first survey configuration and the input seismic data set is acquired according to a second survey configuration, and the first and second survey configurations are not the same. ( [0028]: “Alternatively, synthetic data simulated from perturbed or randomly generated velocity models can also be used as training data, with the caveat that the discrepancy between synthetic seismic forward modeling”, [0031]: “When training data contains multiple field surveys, it is necessary to pre-process seismic traces prior to feeding to a Deep Neural Network.”, [0033]: These choices can be further optimized based on the survey type, geological environment and the desired resolution of the output velocity model.”, [0025]: “starting from seismic shot records, a Deep Neural Network can be trained to predict all input attributes to seismic forward simulation”, [0042] “Once the model is trained, it can be used with any appropriate 5D seismic dataset to predict a velocity model. As described previously, the seismic dataset can be arranged in shot gathers which can then be presented to the model which will predict a 3D velocity model within the shot gather aperture. This can be repeated for multiple shot gathers to generate multiple 3D velocity blocks.”)
Claim(s) 3, 10, and 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over: Wang et al. US 20220018981 A1 (hereinafter “Wang”) in view of Ikelle US 20070274155 A1 (hereinafter “Ikelle”), in further view of Nicholson “A Beginner’s Guide to LSTMs and Recurrent Neural Networks”, A.I. Wiki, Pathmind, available online April 13, 2022, https://wiki.pathmind.com/lstm (retrieved from Wayback Machine) (hereinafter “Nicholson”).
Regarding claims 3, 10, and 17,
Wang in view of Ikelle teach the elements of parent claims 1, 8, and 15 as described above.
Although Wang discloses a deep learning neural network including a 3D Encoder-Decoder architecture or alternatively the use of a Generative Adversarial Network, Wang notes that “any machine-learning algorithm may be used” and “any supervised learning approach may be used”, e.g. [0026], [0036], [0038], [0041]. Wang fails to disclose specifically using a LSTM network.
Nicholson however teaches that LSTMs are well-known and powerful neural network models, e.g. see Page 1.
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art to substitute the use of the neural network model, such as a 3D encoder-decoder or GAN, as taught by Wang with specifically a Long-Short-Term Memory (LSTM) network as taught by Nicholson, and one of ordinary skill in the art would have recognized that, given the existing technical ability to substitute the elements as evidenced by Wang describing the use of deep learning neural networks including teaching the use of different model types such as a 3D encoder-decoder or GAN, noting that “any machine-learning algorithm may be used” and “any supervised learning approach may be used”, and Nicholson describing that LSTMs (which are a type of recurrent neural network) are powerful models that take into account temporal dimension and are even suitable for images, e.g. see Page 1, the results of the substitution were predictable (MPEP 2143 B).
Claim(s) 7, 14, and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over: Wang et al. US 20220018981 A1 (hereinafter “Wang”) in view of Ikelle US 20070274155 A1 (hereinafter “Ikelle”), in further view of Valensi et al. US 20210223424 A1 (hereinafter “Valensi”).
Regarding claims 7, 14, and 20,
Wang in view of Ikelle teach the elements of parent claims 1, 8, and 15 as described above.
Wang fails to clearly describe, however Valensi in analogous art of seismic data processing and velocity model generation, teaches: wherein the initial velocity model is perturbed according to a prior knowledge and a plurality of perturbation parameters, wherein the prior knowledge comprises: petrophysical information about the subsurface region of interest. (Abstract: “initial model”, “each iteration”; [0077]: “said cost function being a measure of discrepancies between the recorded seismic wavefields data and the modeled seismic wavefields data…the low frequency perturbation term δm.sub.b(x) as a parameter in the optimization of the cost function, the high frequency perturbation term δm.sub.r(x) being related to the velocity parameter model w(x) to keep the provided zero-offset seismic wavefield data invariant with respect to the low frequency perturbation term δm.sub.b(x).”; [0078]: “The cost function may include a classical regularization term for taking into account a priori information on the velocity parameter model.”)
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to have modified Wang’s generation of a training data set by perturbing velocity models as described above, to clearly include perturbing the initial velocity model according to a priori knowledge and perturbation parameters in view of Valensi with the motivation to provide for fast and efficient generation of velocity models and accurate images of the subsurface (e.g. Valensi: [0010]).
Pertinent Prior Art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
CN111239802A describing training a neural network for velocity model prediction based on seismic data sets, e.g. see Abstract: “The invention comprises the following steps: the method comprises the steps of generating a training set seismic velocity model, generating and processing training set data, building a deep neural network architecture, training the deep neural network model, preparing input data and predicting the seismic velocity model.”, Page 2: “Step 2: Training set data generation and processing: For all training set seismic velocity models obtained in step 1, multi-shot seismic data is generated in parallel through pseudo-spectral acoustic forward simulation, and then seismic records are used to generate different common center points The velocity spectrum of the location, and then normalize the seismic data of the training set and the velocity spectrum generated separately, and combine them into a three-dimensional matrix;”
Ma et al. US 20240141773 A1, e.g. [0114]: “In such an approach, an initial velocity model may be subsequently calibrated using one or more of various types of seismic-scale inversion algorithms. As an example, a collection of 3D velocity models incorporating the structural component of a zone of interest may be prepared using one or more 1D velocity models.”; also [0167]: “The DLT provides convolutional neural networks (ConvNets, CNNs) and long short-term memory (LSTM) networks to perform classification and regression on image, time-series, and text data.”
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.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SHELBY A TURNER whose telephone number is (571)272-6334. (via email: Shelby.Turner1@uspto.gov “without a written authorization by applicant in place, the USPTO will not respond via internet e-mail to an Internet correspondence” MPEP 502.02 II). The examiner can normally be reached on M-F 10-6 ET.
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, Technology Center Director Allana Bidder can be reached at (571) 272-5560. 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 http://pair-direct.uspto.gov. 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.
/SHELBY A TURNER/Supervisory Patent Examiner, Art Unit 2857
1 https://www.federalregister.gov/documents/2024/07/17/2024-15377/2024-guidance-update-on-patent-subject-matter-eligibility-including-on-artificial-intelligence
2 https://www.uspto.gov/sites/default/files/documents/2024-AI-SMEUpdateExamples47-49.pdf