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 an abstract idea without significantly more. The claims recite an abstract idea as discussed below. This judicial exception is not integrated into a practical application for the reasons discussed below. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception for reasons discussed below.
Step 1 of the 2019 Guidance requires the examiner to determine if the claims are to one of the statutory categories of invention. Applied to the present application, the claims belong to the statutory class of a process or apparatus.
Step 2A of the 2019 Guidance is divided into two Prongs. Prong 1 requires the examiner to determine if the claims recite an abstract idea, and further requires that the abstract idea belong to one of three enumerated groupings: mathematical concepts, mental processes, and certain methods of organizing human activity.
Claim 1 is copied below, with limitations belonging to an abstract idea being underlined.
A method, comprising:
receiving field seismic data that represents a subsurface;
identifying features in the field seismic data using a machine learning model that was trained using at least one first synthetic seismic data set that includes one or more features and one or more labels of the features, and at least one second synthetic seismic data set, the first and second synthetic seismic data sets both generated based on a geological model, wherein noise is injected into the second synthetic seismic data based on the geological model; and
generating a model of the subsurface based at least in part on the features that were identified in the field seismic data using the machine learning model.
The limitations underlined can be considered to describe a mental process and/or a mathematical concept, namely the identification of features in seismic data, generating synthetic data sets, training a machine learning model, , and creating a subsurface model based on the identified features.
The additional limitation of “receiving field seismic data” is insignificant extra-solution activity, e.g. data gathering, required to implement the abstract idea and does not amount to significantly more than the abstract idea itself (see MPEP 2106.05(g)).
The recited limitations “first synthetic seismic data set” and “second synthetic seismic data set” only describes generally what kind of information is used in the abstract idea, as such they do not integrate the claim into a practical application, or make the claim amount to more than the abstract idea itself.
The claim does not integrate the abstract idea into a practical application. Various considerations are used to determine whether the additional elements are sufficient to integrate the abstract idea into a practical application. The claim does not recite a particular machine applying or being used by the abstract idea. The claim does not effect a real-world transformation or reduction of any particular article to a different state or thing. The claim does not contain additional elements which describe the functioning of a computer, or which describe a particular technology or technical field, being improved by the use of the abstract idea.
Step 2B of the 2019 Guidance requires the examiner to determine whether the additional elements cause the claim to amount to significantly more than the abstract idea itself. The considerations for this particular claim are essentially the same as the considerations for Prong 2 of Step 2A, and the same analysis leads to the conclusion that the claim does not amount to significantly more than the abstract idea.
Therefore, Claim 1 is rejected as ineligible under 35 USC 101.
Claims 8 and 15 are analogous to claim 1. Claim 8 additionally recites “one or more processors” and “a memory including one or more non-transitory, computer-readable media”. Claim 15 additionally recites “non-transitory, computer-readable medium”. These additional elements are separate from the abstract idea that need to be considered at Prong 2 of the 101 analysis. However, these additional elements do not offer a meaningful limitation beyond generally linking the use of the method to a computer (see ALICE CORP. v. CLS BANK INT’L 573 U. S. 208 (2014)), which does not cause the claim as a whole to integrate the abstract idea into a particular practical application or provide significantly more than the recited abstract idea. Claims 8 and 15 are therefore rejected as ineligible under 35 USC 101 as well.
Dependent Claims 2-7 are similarly ineligible. Dependent Claim 2 adds the recited “generating”, “training”, “generating”, “injecting”, and “training” to the abstract idea limitations discussed above. Claim 2 additionally recites “obtaining” which is extra-solution activity, e.g. data gathering. Dependent Claim 3 additionally recites “one-dimensional seismic data” which only determines what type of data is used in the abstract idea, as such it does not amount to more than the abstract idea itself. Claim 4 additionally recites “zero-offset seismic data” which only determines what type of data is used in the abstract idea, as such it does not amount to more than the abstract idea itself. Claim 5 additionally recites “three-dimensional seismic data” which only determines what type of data is used in the abstract idea, as such it does not amount to more than the abstract idea itself. Claim 6 additionally recites “finite element seismic data” which only determines what type of data is used in the abstract idea, as such it does not amount to more than the abstract idea itself. Claim 7 additionally recites “noise generated by P-S mode conversion, azimuthal illumination, or both” which only determines what type of data is used in the abstract idea, as such it does not amount to more than the abstract idea itself.
None of these dependent claims recite any further additional elements which would cause the claim as a whole to integrate the recited abstract idea into a particular practical application at Prong 2, or provide significantly more than the recited abstract idea at Step 2B. Claims 2-7 are therefore rejected as ineligible under 35 USC 101 as well.
Dependent Claims 9-14 and 16-20 are analogous to claims 2-7 and are therefore rejected as ineligible under 35 USC 101 for analogous reasons.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1, 2, 7-9, 14-16, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Salman (US 20190383965 A1) in view of Park (Min Jun Park, Mauricio D. Sacchi; “Automatic velocity analysis using convolutional neural network and transfer learning”. Geophysics 2019; 85 (1): V33–V43).
Regarding Claim 1, Salman teaches a method (Para 27: “a subsurface environment may be understood via data acquisition and analysis”), comprising:
receiving field seismic data that represents a subsurface (345 Fig. 3; Para 28: “data acquired and analyzed can be or include one or more types of geophysical data”);
identifying features in the field seismic data using a machine learning model (350 Fig. 3; Para 100: “implementing the trained deep learning framework for interpretation of at least a portion of the acquired geophysical data”)
wherein noise is injected into the
generating a model of the subsurface based at least in part on the features that were identified in the field seismic data using the machine learning model (142 Fig. 1 & 360 Fig. 3; Para 43: “the analysis/visualization component 142 may allow for interaction with a model or model-based results”).
However Salman does not explicitly teach a machine learning model that was trained using at least one first synthetic seismic data set that includes one or more features and one or more labels of the features, and at least one second synthetic seismic data set, the first and second synthetic seismic data sets both generated based on a geological model, wherein noise is injected into the second synthetic seismic data based on the geological model.
Park teaches a machine learning model (Section Introduction Para 3: “we propose a CNN for automatic velocity analysis”)
that was trained (Fig. 5; Section Transfer Learning: “The base model (trained with a labeled data A) can be updated with a small portion of target data B so that it can predict task Y well”)
using at least one first synthetic seismic data set (Section Data Construction: “We construct a training data set using the seven custom synthetic velocity models”)
that includes one or more features and one or more labels of the features (Fig. 3; Section Data Construction: “We match all input data sets with all labels to create the entire training data set”),
and at least one second synthetic seismic data set (Data set B Fig. 5),
the first and second synthetic seismic data sets both generated based on a geological model (Fig. 2; Section Data Construction: “seven custom synthetic velocity models”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Salman with the method of Park by training the machine learning model of Salman with the transfer learning technique of Park and by adding the noise of Salman to the second synthetic data set of Park. The use of transfer learning and added noise would improve the accuracy of the model.
Regarding Claim 2, Salman in view of Park teaches the limitations of claim 1, and Salman in view of Park further teaches injecting the noise into the second synthetic seismic data based on the geological model, the noise representing one or more geological artifacts (Para 189: “acquisition footprint noise can be associated with acquisition geometry”).
Salman does not explicitly teach obtaining the geological model including the one or more features and the labels of the features; generating the first synthetic seismic data based on the geological model; training the machine learning model to identify the one or more features based on the first synthetic data and the labels; generating the second synthetic seismic data based on the geological model; and training the machine learning model to identify the one or more features based on the second synthetic data, the labels, and the noise.
Park teaches obtaining the geological model including the one or more features and the labels of the features (Fig. 2);
generating the first synthetic seismic data based on the geological model (Fig. 3; Section Data Construction: “We construct a training data set using the seven custom synthetic velocity models”);
training the machine learning model to identify the one or more features based on the first synthetic data and the labels (Fig. 3; Section CNN model training: “train the CNN model using our defined data set”);
generating the second synthetic seismic data based on the geological model (Data set B Fig. 5); and
training the machine learning model to identify the one or more features based on the second synthetic data, the labels, and the noise (Fig. 5; Section Transfer Learning: “The base model (trained with a labeled data A) can be updated with a small portion of target data B so that it can predict task Y well).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Salman in view of Park with the method of Park by training the machine learning model of Salman in view of Park with the transfer learning technique steps of Park. The transfer learning technique of Park would improve the accuracy of the machine learning model.
Regarding Claim 7, Salman in view of Park teaches the limitations of claim 1, and Salman further teaches wherein the noise comprises noise generated by P-S mode conversion (Para 113: “P-waves incident on an interface (e.g., at other than normal incidence, etc.) may produce reflected and transmitted S-waves” and Para 193: “synthetic seismic data may be produced with accordingly obtained residual multiple energy superimposed” The examiner notes that Salman identifies P-waves producing reflected S-waves which is interpreted as P-S mode conversion. The examiner notes that Salman then teaches creating synthetic seismic data with reflected waves as a source of noise. These teachings taken together render obvious to inject noise generated by P-S mode conversion.), azimuthal illumination, or both.
Regarding Claim 8, Salman teaches a computing system comprising:
one or more processors (304 Fig. 3; Para 102); and
a memory (306 Fig. 3; Para 102) including one or more non-transitory, computer-readable media (Para 101: “a CRM block can be a computer-readable storage medium that is non-transitory”) storing instructions that, when executed by at least one of the one or more processors, cause the computing system to perform operations (Para 102: “such instructions can include processor-executable instructions that can cause the system 301 to perform one or more actions of the method 300”).
The further limitations of claim 8 are analogous to claim 1.
Regarding Claim 9, the limitations of claim 9 are analogous to claim 2.
Regarding Claim 14, the limitations of claim 14 are analogous to claim 7.
Regarding Claim 15, Salman teaches a non-transitory, computer-readable medium (306 Fig. 3; Para 101: “a CRM block can be a computer-readable storage medium that is non-transitory”) storing instructions that, when executed by at least one processor of a computing system, cause the computing system to perform operations (Para 102: “such instructions can include processor-executable instructions that can cause the system 301 to perform one or more actions of the method 300”).
The further limitations of claim 15 are analogous to claim 1.
Regarding Claim 16, the limitations of claim 16 are analogous to claim 2.
Regarding Claim 20, the limitations of claim 20 are analogous to claim 7.
Claims 3-6, 10-13, and 17-19 are rejected under 35 U.S.C. 103 as being unpatentable over Salman in view of Park as applied to claim 1, 8, and 15 above, and further in view of Aqrawi (US 20190169962 A1).
Regarding Claim 3, Salman in view of Park teaches the limitations of claim 1, but Salman does not explicitly teach wherein the first synthetic seismic data comprises one-dimensional seismic data.
Aqrawi teaches synthetic seismic data comprising one-dimensional seismic data (Fig. 4; Para 87; “an example of one-dimensional data that can be converted into machine learning training data sets”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Salman in view of Park with the method of Aqrawi by generating the synthetic seismic data of Salman in view of Park with one-dimensional data as taught by Aqrawi. Doing so would improve the efficiency of training the machine learning model because one-dimensional data is more computationally efficient to process.
Regarding Claim 4, Salman in view of Park and Aqrawi teach the limitations of claim 3, but Salman does not explicitly teach wherein the first synthetic seismic data comprises zero-offset seismic data.
Aqrawi teaches synthetic seismic data comprising zero-offset seismic data (156 Fig. 1; Para 46: “Other equipment 156 may be located remote from a well site and include sensing, detecting, emitting” The examiner notes that as equipment 156 both emits and detects, it would produce zero-offset seismic data).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Salman in view of Park and Aqrawi with the method of Aqrawi by generating the synthetic seismic data of Salman in view of Park and Aqrawi with zero-offset seismic data as taught by Aqrawi. Doing so would improve the efficiency of training the machine learning model because zero-offset data is more computationally efficient to process.
Regarding Claim 5, Salman in view of Park teaches the limitations of claim 1, but Salman does not explicitly teach wherein the second synthetic seismic data comprises three-dimensional seismic data.
Aqrawi teaches synthetic seismic data comprising three-dimensional seismic data (Para 105: “an example of three-dimensional data that can be converted into machine learning training data sets”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Salman in view of Park with the method of Aqrawi by generating the synthetic seismic data of Salman in view of Park with three-dimensional data as taught by Aqrawi. Doing so would improve the accuracy of the machine learning model because three-dimensional data provides a more accurate representation of the geographic area.
Regarding Claim 6, Salman in view of Park and Aqrawi teach the limitations of claim 5, but Salman does not explicitly teach wherein the three-dimensional seismic data comprises finite element seismic data.
Aqrawi teaches wherein the three-dimensional seismic data comprises finite element seismic data (Labeled data 610 Fig. 6; Para 108-111).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Salman in view of Park and Aqrawi with the data of Aqrawi by having the three-dimensional seismic data of Salman in view of Park and Aqrawi comprise finite element data as taught by Aqrawi. Doing so would improve the accuracy of the machine learning model because finite element data provides a more accurate representation of the geographic area.
Regarding Claim 10, the limitations of claim 10 are analogous to claim 3.
Regarding Claim 11, the limitations of claim 11 are analogous to claim 4.
Regarding Claim 12, the limitations of claim 12 are analogous to claim 5.
Regarding Claim 13, the limitations of claim 13 are analogous to claim 6.
Regarding Claim 17, the limitations of claim 17 are analogous to claim 3.
Regarding Claim 18, the limitations of claim 18 are analogous to claim 4.
Regarding Claim 19, the limitations of claim 19 are analogous to claim 6.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Puscas (US 20210097371 A1) teaches transfer learning using synthetic data (Abstract).
Salman (US 20190250294 A1) teaches using machine learning to predict the location of a subsurface layer (Abstract).
Denli (US 20200183047 A1) teaches using seismic data and machine learning to characterize a subsurface (Abstract). Denli additionally teaches adding noise to synthetic data when training a machine learning model (Fig. 4; Para 93).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to RODGER MENSING whose telephone number is (571)270-0129. The examiner can normally be reached 8am-5pm.
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, Andrew Schechter can be reached at 571-272-2302. 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.
/RODGER STEWART MENSING/ Examiner, Art Unit 2857
/ANDREW SCHECHTER/ Supervisory Patent Examiner, Art Unit 2857
Prosecution Insights