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 .
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 (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Specifically, representative Claim 1 recites:
A method, comprising:
obtaining a synthetic seismogram representing a seismic well tie, a shifted synthetic seismogram representing the seismic well tie, and a shift input including domain shift data for converting well log data from a depth domain to a time domain;
generating a shift label based on the synthetic seismogram and the shifted synthetic seismogram using a machine learning model, wherein the shift label includes domain shift data for converting well log data from a depth domain to a time domain;
determining that an accuracy of the shift label is less than a threshold based on a comparison of the shift input and the shift label;
adjusting the machine learning model in response to determining that the accuracy of the shift label is less than the threshold;
predicting a second shift for a second seismic well tie from a second seismogram using the machine learning model; and
generating a seismic image based on the second seismic well tie, the second seismogram, and the second shift.
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).
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 mental processes – concepts performed in the human mind including an observation, evaluation, judgement, and/or opinion.
For example, steps of “generating a shift label based on the synthetic seismogram and the shifted synthetic seismogram using a machine learning model, wherein the shift label includes domain shift data for converting well log data from a depth domain to a time domain (inputting values into a regression);
determining that an accuracy of the shift label is less than a threshold based on a comparison of the shift input and the shift label (deciding if a comparison result is acceptable);
adjusting the machine learning model in response to determining that the accuracy of the shift label is less than the threshold (modifying the regression equation);
predicting a second shift for a second seismic well tie from a second seismogram using the machine learning model (inputting new values into the regression); and
generating a seismic image based on the second seismic well tie, the second seismogram, and the second shift (plotting data and results)” are treated by the Examiner as belonging to mental process grouping.
Similar limitations comprise the abstract ideas of Claims 9 and 17.
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:
Claim 1: obtaining a synthetic seismogram representing a seismic well tie, a shifted synthetic seismogram representing the seismic well tie, and a shift input including domain shift data for converting well log data from a depth domain to a time domain;
Claim 9: one or more processors; and a memory including one or more non-transitory computer-readable media storing instructions that, when executed by at least one of the one or more processors, cause the computing system to perform operations, the operations comprising: obtaining a synthetic seismogram representing a seismic well tie, a shifted synthetic seismogram representing the seismic well tie, and a shift input including domain shift data for converting well log data from a depth domain to a time domain;
Claim 17: A non-transitory computer-readable medium storing instructions that, when executed by at least one processor of a computing system, cause the computing system to perform operations, the operations comprising: obtaining a synthetic seismogram representing a seismic well tie, a shifted synthetic seismogram representing the seismic well tie, and a shift input including domain shift data for converting well log data from a depth domain to a time domain.
The additional element of “obtaining a synthetic seismogram representing a seismic well tie, a shifted synthetic seismogram representing the seismic well tie, and a shift input including domain shift data for converting well log data from a depth domain to a time domain” represents a mere data gathering step and only adds an insignificant extra-solution activity to the judicial exception. A non-transitory computer-readable medium or memory (generic memory) and one or more processors or a computing system (generic processor) are generally recited and are not qualified as particular machines.
In conclusion, the above additional elements, considered individually and in combination with the other claim elements do not reflect an improvement to other technology or technical field, and, therefore, do not integrate the judicial exception into a practical application. Therefore, the claims are directed to a judicial exception and require further analysis under the Step 2B.
However, the above claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception (Step 2B analysis).
The claims, therefore, are not patent eligible.
With regards to the dependent claims, claims 2-8, 10-16, and 18-20 provide additional features/steps which are part of an expanded algorithm, so these limitations should be considered part of an expanded abstract idea of the independent claims.
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1-5, 9-13, and 17-20 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Nivlet et al (US 20220137245 A1).
Regarding Claim 1, Nivlet teaches a method, comprising:
obtaining a synthetic seismogram representing a seismic well tie, a shifted synthetic seismogram representing the seismic well tie, and a shift input including domain shift data for converting well log data from a depth domain to a time domain (Nivlet [0048] Process 200 may be initiated by receiving input data at block 205. Input data received at block 205 can include data 206 in the depth domain and data 207 in time domain (e.g., TWT data). Data 206 may relate to available time-depth curves. Data 207 may relate to depth—TWT curves. Data received at block 205 may also include at least one seismic wave trace in a depth domain and at least one time-depth curve. First data);
generating a shift label based on the synthetic seismogram and the shifted synthetic seismogram using a machine learning model, wherein the shift label includes domain shift data for converting well log data from a depth domain to a time domain (Nivlet [0041] The method also includes operations for data preparation, predicting an output TWT length for each sequence, and converting an input sequence to the output sequence with a defined length. The method also includes realigning different sequences in the TWT domain by estimating an optimal time-lag from one sequence to the next. The method can include output for any given TWT value. Also see [0050] At block 215, one or more operations are performed to train a model to predict the length of an output sequence. By way of example, training is performed by a neural network that learns the length of the output TWT sequences when it is fed with an input sequence in depth. First training iteration);
determining that an accuracy of the shift label is less than a threshold based on a comparison of the shift input and the shift label (Nivlet [0052] The neural network can provide a corresponding vector of output TWT sequence lengths, and compare it to the expected vector of sequence lengths. The measure of discrepancy (also called loss) can be the mean absolute difference, or mean squared difference, even though other measures are possible. Determining model accuracy);
adjusting the machine learning model in response to determining that the accuracy of the shift label is less than the threshold (Nivlet [0052] The neural network can provide a corresponding vector of output TWT sequence lengths, and compare it to the expected vector of sequence lengths. The measure of discrepancy (also called loss) can be the mean absolute difference, or mean squared difference, even though other measures are possible. The neural network can then automatically modify internal weights using a back-propagation algorithm in order to decrease the measured discrepancy. Adjust model based on determined errors);
predicting a second shift for a second seismic well tie from a second seismogram using the machine learning model (Nivlet [0055] Process 200 may include modelling/predicting output sequence length using the model at block 216 and modeling transformation of data at block 225. A modeling transformation operation is performed at block 225 for transformation of data based on training in block 215 and 220 and for domain conversion. Also see [0080] Process 1000 may be initiated by receiving input data at block 1005. Input data received at block 1005 can include data for a field region, such as data 206 in the depth domain and data 207 in time domain (e.g., TWT data). Data received at block 1005 may also include at least one seismic wave trace (e.g., sonic trace) in a depth domain and at least one time-depth curve. And [0081] Data preprocessing at block 1010 may include preprocessing of the data received at block 1005 to prepare the data for conversion relative to a depth domain and time domain. According to embodiments, preprocessing at block 1010 may include determining a length of output sequence for received input data. Block 1010 may include one or more operations described with reference to FIG. 3, data preprocessing in FIG. 6A, and data preparation in FIG. 7. At block 1015 a model may be applied to input data for transformation of the input data from transforming, using the one or more processors, input data in the depth domain to a time domain using a model. The model at block 1015 may be a neural network configured to determine a length of an output in a time domain for well data received in a depth domain. Apply trained model to new data); and
generating a seismic image based on the second seismic well tie, the second seismogram, and the second shift (Nivlet [0082] At block 1020, transformed data may be output. Output of transformed data at block 1010 may include converting an input sequence of a well to an output sequence with a defined length. Transforming can also include realigning sequences in two-way-time by estimating a time-lag relative to the sequences and resampling the sequences following realignment to a common grid for output as a set of values in two-way-time. Output of trained model).
Regarding Claim 2, Nivlet further teaches wherein adjusting the machine learning model includes using backpropagation to determine an adjustment to at least one weight of the machine learning model to increase the accuracy of the predicted shifts by the machine learning model (Nivlet [0052] The neural network can then automatically modify internal weights using a back-propagation algorithm in order to decrease the measured discrepancy).
Regarding Claim 3, Nivlet further teaches predicting a third shift using the machine learning model based at least in part on a third synthetic seismogram and a third seismogram (Nivlet [0055] Process 200 may include modelling/predicting output sequence length using the model at block 216 and modeling transformation of data at block 225. A modeling transformation operation is performed at block 225 for transformation of data based on training in block 215 and 220 and for domain conversion.);
comparing the third shift with validating shift data to determine an accuracy of the predicted third shifts (Nivlet [0052] The neural network can provide a corresponding vector of output TWT sequence lengths, and compare it to the expected vector of sequence lengths. The measure of discrepancy (also called loss) can be the mean absolute difference, or mean squared difference, even though other measures are possible. Determining model accuracy); and
validating the trained machine learning model in response to the accuracy of the predicted third shifts being above a threshold (Nivlet [0052] The optimization continues one epoch after another until a convergence criterion, or until a maximum number of epochs is reached. One of the classical convergence criteria includes monitoring the loss on the validation set. In general, the validation loss starts by decreasing similarly to the training loss, until a point where the two curves diverge, with the validation loss starting to increase or reaching a plateau. This point is where overfitting starts and is where the training generally is stopped. The model is trained until it is sufficiently accurate).
Regarding Claim 4, Nivlet further teaches wherein the shift input is at least partially human-generated (Nivlet [0076] One or more operations are performed for data preparation at 710. These operations can include sequences 715 with length dz in depth are extracted with a stride defined by a user.).
Regarding Claim 5, Nivlet further teaches adjusting a depth-time conversion relationship for converting the well log data in the depth domain to the time domain based on the predicted second shift (Nivlet [0052] The neural network can provide a corresponding vector of output TWT sequence lengths, and compare it to the expected vector of sequence lengths. The measure of discrepancy (also called loss) can be the mean absolute difference, or mean squared difference, even though other measures are possible. The neural network can then automatically modify internal weights using a back-propagation algorithm in order to decrease the measured discrepancy. The model is continuously trained to be able to better predict the conversion parameters.).
Regarding Claim 9, Nivlet teaches a computing system, comprising:
one or more processors (Nivlet [0078] According to one or more embodiments, controller 905, which may relate to a processor or control device, is configured to execute one or more operations stored in memory 915. Also see [0006] The system includes one or more processors); and
a memory including one or more non-transitory computer-readable media storing instructions that, when executed by at least one of the one or more processors, cause the computing system to perform operations (Nivlet [0078] According to one or more embodiments, controller 905, which may relate to a processor or control device, is configured to execute one or more operations stored in memory 915. Also see [0006] a non-transitory computer-readable memory storing instructions that, when executed by the one or more processors, causes the one or more processors to […]), the operations comprising:
obtaining a synthetic seismogram representing a seismic well tie, a shifted synthetic seismogram representing the seismic well tie, and a shift input including domain shift data for converting well log data from a depth domain to a time domain (Nivlet [0048] Process 200 may be initiated by receiving input data at block 205. Input data received at block 205 can include data 206 in the depth domain and data 207 in time domain (e.g., TWT data). Data 206 may relate to available time-depth curves. Data 207 may relate to depth—TWT curves. Data received at block 205 may also include at least one seismic wave trace in a depth domain and at least one time-depth curve. First data);
generating a shift label based on the synthetic seismogram and the shifted synthetic seismogram using a machine learning model, wherein the shift label includes domain shift data for converting well log data from a depth domain to a time domain (Nivlet [0041] The method also includes operations for data preparation, predicting an output TWT length for each sequence, and converting an input sequence to the output sequence with a defined length. The method also includes realigning different sequences in the TWT domain by estimating an optimal time-lag from one sequence to the next. The method can include output for any given TWT value. Also see [0050] At block 215, one or more operations are performed to train a model to predict the length of an output sequence. By way of example, training is performed by a neural network that learns the length of the output TWT sequences when it is fed with an input sequence in depth. First training iteration);
determining that an accuracy of the shift label is less than a threshold based on a comparison of the shift input and the shift label (Nivlet [0052] The neural network can provide a corresponding vector of output TWT sequence lengths, and compare it to the expected vector of sequence lengths. The measure of discrepancy (also called loss) can be the mean absolute difference, or mean squared difference, even though other measures are possible. Determining model accuracy);
adjusting the machine learning model in response to determining that the accuracy of the shift label is less than the threshold (Nivlet [0052] The neural network can provide a corresponding vector of output TWT sequence lengths, and compare it to the expected vector of sequence lengths. The measure of discrepancy (also called loss) can be the mean absolute difference, or mean squared difference, even though other measures are possible. The neural network can then automatically modify internal weights using a back-propagation algorithm in order to decrease the measured discrepancy. Adjust model based on determined errors);
predicting a second shift for a second seismic well tie from a second seismogram using the machine learning model (Nivlet [0055] Process 200 may include modelling/predicting output sequence length using the model at block 216 and modeling transformation of data at block 225. A modeling transformation operation is performed at block 225 for transformation of data based on training in block 215 and 220 and for domain conversion. Also see [0080] Process 1000 may be initiated by receiving input data at block 1005. Input data received at block 1005 can include data for a field region, such as data 206 in the depth domain and data 207 in time domain (e.g., TWT data). Data received at block 1005 may also include at least one seismic wave trace (e.g., sonic trace) in a depth domain and at least one time-depth curve. And [0081] Data preprocessing at block 1010 may include preprocessing of the data received at block 1005 to prepare the data for conversion relative to a depth domain and time domain. According to embodiments, preprocessing at block 1010 may include determining a length of output sequence for received input data. Block 1010 may include one or more operations described with reference to FIG. 3, data preprocessing in FIG. 6A, and data preparation in FIG. 7. At block 1015 a model may be applied to input data for transformation of the input data from transforming, using the one or more processors, input data in the depth domain to a time domain using a model. The model at block 1015 may be a neural network configured to determine a length of an output in a time domain for well data received in a depth domain. Apply trained model to new data); and
generating a seismic image based on the second seismic well tie, the second seismogram, and the second shift (Nivlet [0082] At block 1020, transformed data may be output. Output of transformed data at block 1010 may include converting an input sequence of a well to an output sequence with a defined length. Transforming can also include realigning sequences in two-way-time by estimating a time-lag relative to the sequences and resampling the sequences following realignment to a common grid for output as a set of values in two-way-time. Output of trained model).
Regarding Claim 10, Nivlet further teaches wherein adjusting the machine learning model includes using backpropagation to determine an adjustment to at least one weight of the machine learning model to increase the accuracy of the predicted shifts by the machine learning model (Nivlet [0052] The neural network can then automatically modify internal weights using a back-propagation algorithm in order to decrease the measured discrepancy).
Regarding Claim 11, Nivlet further teaches predicting a third shift using the machine learning model based at least in part on a third synthetic seismogram and a third seismogram (Nivlet [0055] Process 200 may include modelling/predicting output sequence length using the model at block 216 and modeling transformation of data at block 225. A modeling transformation operation is performed at block 225 for transformation of data based on training in block 215 and 220 and for domain conversion.);
comparing the third shift with validating shift data to determine an accuracy of the predicted third shifts (Nivlet [0052] The neural network can provide a corresponding vector of output TWT sequence lengths, and compare it to the expected vector of sequence lengths. The measure of discrepancy (also called loss) can be the mean absolute difference, or mean squared difference, even though other measures are possible. Determining model accuracy); and
validating the trained machine learning model in response to the accuracy of the predicted third shifts being above a threshold (Nivlet [0052] The optimization continues one epoch after another until a convergence criterion, or until a maximum number of epochs is reached. One of the classical convergence criteria includes monitoring the loss on the validation set. In general, the validation loss starts by decreasing similarly to the training loss, until a point where the two curves diverge, with the validation loss starting to increase or reaching a plateau. This point is where overfitting starts and is where the training generally is stopped. The model is trained until it is sufficiently accurate).
Regarding Claim 12, Nivlet further teaches wherein the shift input is at least partially human-generated (Nivlet [0076] One or more operations are performed for data preparation at 710. These operations can include sequences 715 with length dz in depth are extracted with a stride defined by a user.).
Regarding Claim 13, Nivlet further teaches adjusting a depth-time conversion relationship for converting the well log data in the depth domain to the time domain based on the predicted second shift (Nivlet [0052] The neural network can provide a corresponding vector of output TWT sequence lengths, and compare it to the expected vector of sequence lengths. The measure of discrepancy (also called loss) can be the mean absolute difference, or mean squared difference, even though other measures are possible. The neural network can then automatically modify internal weights using a back-propagation algorithm in order to decrease the measured discrepancy. The model is continuously trained to be able to better predict the conversion parameters.).
Regarding Claim 17, Nivlet teaches a non-transitory computer-readable medium storing instructions that, when executed by at least one processor of a computing system, cause the computing system to perform operations (Nivlet [0078] According to one or more embodiments, controller 905, which may relate to a processor or control device, is configured to execute one or more operations stored in memory 915. Also see [0006] a non-transitory computer-readable memory storing instructions that, when executed by the one or more processors, causes the one or more processors to […]), the operations comprising:
obtaining a synthetic seismogram representing a seismic well tie, a shifted synthetic seismogram representing the seismic well tie, and a shift input including domain shift data for converting well log data from a depth domain to a time domain (Nivlet [0048] Process 200 may be initiated by receiving input data at block 205. Input data received at block 205 can include data 206 in the depth domain and data 207 in time domain (e.g., TWT data). Data 206 may relate to available time-depth curves. Data 207 may relate to depth—TWT curves. Data received at block 205 may also include at least one seismic wave trace in a depth domain and at least one time-depth curve. First data);
generating a shift label based on the synthetic seismogram and the shifted synthetic seismogram using a machine learning model, wherein the shift label includes domain shift data for converting well log data from a depth domain to a time domain (Nivlet [0041] The method also includes operations for data preparation, predicting an output TWT length for each sequence, and converting an input sequence to the output sequence with a defined length. The method also includes realigning different sequences in the TWT domain by estimating an optimal time-lag from one sequence to the next. The method can include output for any given TWT value. Also see [0050] At block 215, one or more operations are performed to train a model to predict the length of an output sequence. By way of example, training is performed by a neural network that learns the length of the output TWT sequences when it is fed with an input sequence in depth. First training iteration);
determining that an accuracy of the shift label is less than a threshold based on a comparison of the shift input and the shift label (Nivlet [0052] The neural network can provide a corresponding vector of output TWT sequence lengths, and compare it to the expected vector of sequence lengths. The measure of discrepancy (also called loss) can be the mean absolute difference, or mean squared difference, even though other measures are possible. Determining model accuracy);
adjusting the machine learning model in response to determining that the accuracy of the shift label is less than the threshold (Nivlet [0052] The neural network can provide a corresponding vector of output TWT sequence lengths, and compare it to the expected vector of sequence lengths. The measure of discrepancy (also called loss) can be the mean absolute difference, or mean squared difference, even though other measures are possible. The neural network can then automatically modify internal weights using a back-propagation algorithm in order to decrease the measured discrepancy. Adjust model based on determined errors);
predicting a second shift for a second seismic well tie from a second seismogram using the machine learning model (Nivlet [0055] Process 200 may include modelling/predicting output sequence length using the model at block 216 and modeling transformation of data at block 225. A modeling transformation operation is performed at block 225 for transformation of data based on training in block 215 and 220 and for domain conversion. Also see [0080] Process 1000 may be initiated by receiving input data at block 1005. Input data received at block 1005 can include data for a field region, such as data 206 in the depth domain and data 207 in time domain (e.g., TWT data). Data received at block 1005 may also include at least one seismic wave trace (e.g., sonic trace) in a depth domain and at least one time-depth curve. And [0081] Data preprocessing at block 1010 may include preprocessing of the data received at block 1005 to prepare the data for conversion relative to a depth domain and time domain. According to embodiments, preprocessing at block 1010 may include determining a length of output sequence for received input data. Block 1010 may include one or more operations described with reference to FIG. 3, data preprocessing in FIG. 6A, and data preparation in FIG. 7. At block 1015 a model may be applied to input data for transformation of the input data from transforming, using the one or more processors, input data in the depth domain to a time domain using a model. The model at block 1015 may be a neural network configured to determine a length of an output in a time domain for well data received in a depth domain. Apply trained model to new data); and
generating a seismic image based on the second seismic well tie, the second seismogram, and the second shift (Nivlet [0082] At block 1020, transformed data may be output. Output of transformed data at block 1010 may include converting an input sequence of a well to an output sequence with a defined length. Transforming can also include realigning sequences in two-way-time by estimating a time-lag relative to the sequences and resampling the sequences following realignment to a common grid for output as a set of values in two-way-time. Output of trained model).
Regarding Claim 18, Nivlet further teaches wherein adjusting the machine learning model includes using backpropagation to determine an adjustment to at least one weight of the machine learning model to increase the accuracy of the predicted shifts by the machine learning model (Nivlet [0052] The neural network can then automatically modify internal weights using a back-propagation algorithm in order to decrease the measured discrepancy).
Regarding Claim 19, Nivlet further teaches predicting a third shift using the machine learning model based at least in part on a third synthetic seismogram and a third seismogram (Nivlet [0055] Process 200 may include modelling/predicting output sequence length using the model at block 216 and modeling transformation of data at block 225. A modeling transformation operation is performed at block 225 for transformation of data based on training in block 215 and 220 and for domain conversion.);
comparing the third shift with validating shift data to determine an accuracy of the predicted third shifts (Nivlet [0052] The neural network can provide a corresponding vector of output TWT sequence lengths, and compare it to the expected vector of sequence lengths. The measure of discrepancy (also called loss) can be the mean absolute difference, or mean squared difference, even though other measures are possible. Determining model accuracy); and
validating the trained machine learning model in response to the accuracy of the predicted third shifts being above a threshold (Nivlet [0052] The optimization continues one epoch after another until a convergence criterion, or until a maximum number of epochs is reached. One of the classical convergence criteria includes monitoring the loss on the validation set. In general, the validation loss starts by decreasing similarly to the training loss, until a point where the two curves diverge, with the validation loss starting to increase or reaching a plateau. This point is where overfitting starts and is where the training generally is stopped. The model is trained until it is sufficiently accurate).
Regarding Claim 20, Nivlet further teaches adjusting a depth-time conversion relationship for converting the well log data in the depth domain to the time domain based on the predicted second shift (Nivlet [0052] The neural network can provide a corresponding vector of output TWT sequence lengths, and compare it to the expected vector of sequence lengths. The measure of discrepancy (also called loss) can be the mean absolute difference, or mean squared difference, even though other measures are possible. The neural network can then automatically modify internal weights using a back-propagation algorithm in order to decrease the measured discrepancy. The model is continuously trained to be able to better predict the conversion parameters.).
The Examiner notes that there are currently no prior art rejections for claims 6-8 and 14-16.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Nivlet et al (US 20230003912 A1) discloses a System And Method For Automated Domain Conversion For Seismic Well Ties.
Nivlet et al. ("Automated well-to-seismic tie using deep neural networks." Paper presented at the SEG International Exposition and Annual Meeting, Virtual, October 2020. doi: https://doi.org/10.1190/segam2020-3422495.1) discloses deep neural networks to predict sonic well logs in the TWT domain from the measured well logs in depth, rather than predicting the drift function.
Thanoon et al. ("Deep Seismic2Well Tie: A physics-guided CNN approach to a classic geophysical workflow." Paper presented at the SEG/AAPG/SEPM First International Meeting for Applied Geoscience & Energy, Denver, Colorado, USA and online, September 2021. doi: https://doi.org/10.1190/segam2021-3587358.1) discloses a purely data-driven technique using the physics-guided convolutional neural network (PG-CNN) for the estimation of the depth-to-time function.
Di et al. (Automating seismic-well tie via self-supervised learning: Geophysical Prospecting, 71(4): 698-712. 2023) discloses a new self-supervised learning workflow for automated seismic-well tie at multiple wells that requires no human labels.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHRISTIAN T BRYANT whose telephone number is (571)272-4194. The examiner can normally be reached Monday-Thursday and Alternate Fridays 7:00-4:30.
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, CATHERINE RASTOVSKI can be reached at (571) 270-0349. 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.
/CHRISTIAN T BRYANT/Examiner, Art Unit 2857
Prosecution Insights