DETAILED ACTION
Claims 1-9 are presented for examination. Claims 1, 3, and 4 stand currently amended.
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 2 March 2026 has been entered.
Response to Arguments
Applicant's remarks filed 2 March 2026 have been fully considered and Examiner’s response is as follows:
Regarding §101:
Applicant remarks page 7 argues:
Applicants maintain that the claimed invention is integrated into a practical application. That is, the claimed invention addresses a specific, concrete technical problem in drilling engineering, not a generic mathematical problem. Indeed, paragraphs [0002]-[0004] of the specification indicate that there exists the following long-standing unmet industry needs: (1) manual risk recognition is subjective, high latency, experience-dependent; (2) existing solutions require manual feature extraction, poor adaptability, insufficient real-time performance. Every step of the claimed invention is designed exclusively to solve this drilling-specific technical problem.
This argument is unpersuasive.
Preliminarily, Examiner observes the Specification does not have paragraph numbers. Examiner assumes [0002]-[0004] of the Specification refers to page 1 second paragraph to page 3 first paragraph corresponding with the “Background Art” section. This section generally describes a data processing problem “of safety risk recognition while drilling.” See Specification page 2 last sentence.
Recognition is an evaluation and not a physical drilling process. Here, the claims recite respective mathematical data processing as identified in the §101 rejection.
Whether or not there is a long-standing unmet need is not a factor for consideration of §101 abstract idea.
Furthermore, replacing a manual risk recognition with a computerized process is similar to the process considered in In re Meyer, 688 F. 2d 789, 795 (CCPA 1982):
Appellants' specification and arguments indicate that their invention is concerned with replacing, in part, the thinking processes of a neurologist with a computer. Counsel for appellants acknowledged in oral argument that the claims recite a mathematical algorithm, which represents a mental process that a neurologist should follow.
Similar to In re Meyer, the argument here is suggesting that the invention is based on replacing a manual risk recognition and a manual feature extraction process with a computerized one in which a mathematical algorithm is recited. The claims at issue in In re Meyer, were for identifying “probable malfunction in a complex system.” The instant claims are analogous in “recognition method for while-drilling safety risks.” While §101 jurisprudence has evolved somewhat since 1982, what remains is that an improvement to an otherwise manual process with a mathematical computerized process will generally not render claims eligible on that basis. See MPEP §2106.05(f):
claims that amount to nothing more than an instruction to apply the abstract idea using a generic computer do not render an abstract idea eligible. Alice Corp., 573 U.S. at 223, 110 USPQ2d at 1983.
Applicant remarks page 7 further argues:
Moreover, all claim steps are tied to drilling-specific physical hardware and proprietary monitoring data, not generic data. For example, claim 1 recites, inter alia, "wherein the monitoring-while-drilling parameters are 13 core parameters collected from on-site physical drilling monitoring hardware, including conventional drilling parameter monitoring equipment." All mathematical operations are customized for this drilling-specific data, imposing a meaningful field-specific limit on the claimed method, preventing monopolization of generic mathematical concepts.
This argument is unpersuasive. Conventional drilling parameter monitoring equipment is not alleged to be inventive or novel. Accordingly, nothing in the data gathering process is alleged to be improved. See MPEP §2106.05(g).
An improved mathematical operation is not patent eligible under §101.
Applicant remarks page 7 further argues:
Furthermore, the final claim step is tied to physical drilling operations, not a mental process. Indeed, claim 1 defines output of physical early warning signal to on-site control system, adjustment of physical drilling parameters, execution of physical risk disposal operations. According to paragraphs [0098]-[0100] of the specification, this is a real-world drilling application, where the warning signal directly drives physical on-site risk mitigation actions. Thus, at least this step integrates the claimed method directly into the physical drilling process, constituting a concrete practical application.
Examiner agrees the final claim step of claim 1 is tied to a physical step. Accordingly, Examiner has analyzed that limitation under step 2A prong 2 and 2B of the §101 framework.
Under 2A(ii), outputting an early warning signal of the calculated risk is insignificant extra solution activity in the form of outputting the calculated result of the abstract idea. See MPEP §2106.05(g).
Under 2A(ii), executing a standard risk disposal physical operation flow based on the abstract idea result amounts to mere instruction to apply the result of the abstract idea. See MPEP §2106.05(f). Adjusting physical drilling construction parameters is recited in the alternative and thus not required for infringement of the claim. However, because of the generality of the “adjusting” the adjustment would also be considered mere instruction to apply the result of the abstract idea. See MPEP §2106.05(f).
While a warning signal might drive subsequent on-site risk mitigation actions and other physical transformations, those physical steps and subsequent risk mitigation actions are not recited in the claims beyond what is found in the last clause of claim 1.
Applicant remarks page 8 further argues:
Paragraphs [0034], [0097] and [0101] of the specification explain that (1) >90% recognition accuracy for all 4 core drilling risks; (2) 2-3 minutes earlier risk identification than manual judgment; (3) reduced drilling accident rate, improved drilling efficiency, reduced costs.
This establishes the utility of the claimed invention. Examiner has not made a rejection based on §101 lack of utility. Examiner’s §101 rejection is based on judicially excepted abstract ideas.
Applicant remarks page 8 further argues:
Notwithstanding the above, the claimed invention recites significantly more than the alleged abstract idea (Step 2B). That is, the following limitations constitute significantly more than generic mathematical operations/mental processes:
1. Drilling-specific dual convolutional layer CNN architecture: Customized for while-drilling 2D time-series data, solves the industry problem of failing to capture both single-parameter trends and multi-parameter correlations;
2. Risk-specific three-time-span, three-network concurrent training scheme: Solves the industry tradeoff between recognition accuracy and real-time performance;
3. Drilling-specific small-sample learning and data enhancement pipeline: Addresses the unique industry challenge of scarce while-drilling risk samples; and
4. End-to-end technical chain: From physical data collection, to feature extraction, to risk recognition, to physical on-site risk mitigation.
This argument is unpersuasive.
(1) The dual convolutional layer CNN architecture is explicit recitation of mathematical structure. Additional recitation of mathematical subject matter will not cure a rejection based on recitation of a mathematical concept.
(2) It is unclear what claim limitations are referenced by “risk-specific three-time-span, three-network concurrent training scheme.” Examiner will not speculate as to the intended meaning and will merely state arguments based on limitations not recited in the claims are not persuasive.
(3) It is unclear what claim limitations are referenced by “small-sample learning and data enhancement pipeline.” Examiner will not speculate as to the intended meaning and will merely state arguments based on limitations not recited in the claims are not persuasive.
(4) The end-to-end technical chain appears to refer to the use of a computer from end-to-end. MPEP §2106.05(f) states:
claims that amount to nothing more than an instruction to apply the abstract idea using a generic computer do not render an abstract idea eligible. Alice Corp., 573 U.S. at 223, 110 USPQ2d at 1983.
Accordingly, providing an end-to-end technical chain is insufficient to demonstrate subject matter eligibility under §101.
Regarding 102/103:
Applicant remarks page 9 argues:
That is, the primary reference Qodirov fails to teach or suggest the dual convolutional layer CNN architecture with defined m1 and 1n convolution kernels. Indeed, Qodirov only uses a fully connected neural network.
This argument is persuasive. The §103 rejection of claims 1-9 has been withdrawn.
Claim Objections
Claims 1 and 3 have been appropriately corrected. Accordingly, examiner's objection(s) to the claim(s) are withdrawn.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-9 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor, or for pre-AIA the applicant regards as the invention.
Claim 1 step 3 twice recites “a convolutional layer.” This creates unclear antecedent basis when subsequently “the convolutional layer” is recited. Examiner suggests labeling the convolutional layers as “a first convolutional layer” and “a second convolutional layer” to distinguish between each respectively.
Dependent claims 2-8 are rejected for depending from a rejected claim.
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 1-9 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
To determine if a claim is directed to patent ineligible subject matter, the Court has guided the Office to apply the Alice/Mayo test, which requires:
1. Determining if the claim falls within a statutory category;
2A. Determining if the claim is directed to a patent ineligible judicial exception consisting of a law of nature, a natural phenomenon, or abstract idea; and
2B. If the claim is directed to a judicial exception, determining if the claim recites limitations or elements that amount to significantly more than the judicial exception.
See MPEP §2106.
Step 2A is a two prong inquiry. MPEP §2106.04(II)(A). Under 2A(i), the first prong, examiners evaluate whether a law of nature, natural phenomenon, or abstract idea is set forth or described in the claim. Abstract ideas include mathematical concepts, certain methods of organizing human activity, and mental processes. MPEP §2106.04(a)(2). Under 2A(ii), the second prong, examiners determine whether any additional limitations integrates the judicial exception into a practical application. MPEP §2106.04(d).
Claim 1 step 2A(i):
The claim(s) recite:
1. An intelligent recognition method for while-drilling safety risks based on a convolutional neural network, comprising the following steps:
1: processing while-drilling safety risk parameter features and data, and establishing a correlation analysis model for monitoring-while-drilling parameters by using a Pearson coefficient correlation analysis method, wherein the monitoring-while-drilling parameters are 13 core parameters collected from on-site physical drilling monitoring hardware, including conventional drilling parameter monitoring equipment and sand discharge pipeline return gas component monitoring equipment;
2: processing while-drilling safety monitoring data, analyzing a time span of each sample, constructing training sample data and test sample data, and preprocessing the samples, step 2 further comprising for each type of while-drilling safety risk including formation gas production, formation water production, sticking and picking up stands, constructing sample data with three risk-specific different time spans, and performing while-drilling safety risk recognition training by using three networks corresponding to the three time spans at the same time;
3: designing a while-drilling safety risk recognition network structure, and training a network model, wherein the network structure comprises an input layer, a convolutional layer, a convolutional layer, a hidden layer and an output layer; the convolutional layer uses a one-dimensional longitudinal convolution kernel of m1 to perform separate convolution calculations on each monitoring parameter respectively, so as to extract the time-dependent change trend of each single parameter; the convolutional layer uses a one-dimensional transverse convolution kernel of 1n to perform separate feature extraction on each row of the parameter matrix, so as to extract the associated change relationship between different monitoring parameters;
4: recognizing the while-drilling safety risks by the trained safety risk recognition network; and
Processing parameters and data to establish a correlation analysis model by using a Pearson coefficient correlation analysis method is explicit recitation of mathematical subject matter. Establishing a correlation analysis is mathematical. The Pearson coefficient correlation analysis method is a mathematical method. The source of the monitoring-while drilling parameters does not change these parameters as they still encompass the numerical values. The monitoring equipment is not actively recited, merely passively referenced as a data source for an unclaimed previous collection which previously took place outside what is actively claimed.
Processing monitoring data, analyzing sample data, and preprocessing the sample data encompasses mathematical subject matter at an extremely high level of generality. Identifying respective data samples for training, testing, and performing training is performing respective mathematical calculations of training the neural networks.
Designing a network structure and training the network model is recitation of performing mathematical calculations of the network model training. The layers of the network structure in respective dimensions denote the dimensions of the respective vectors and matrices. Matrices and vectors are mathematical entities.
Recognizing safety risks using the trained recognition network is recitation of mental process evaluation, judgment, or opinion enacted by performing the mathematical calculations of the recognition network model.
This falls within the mathematical concept grouping of abstract ideas. See MPEP §2106.04(a)(2).
Claim 1 step 2A(ii):
This judicial exception is not integrated into a practical application because:
Claim 1 recites:
5: outputting an early warning signal of the recognized while-drilling safety risks to a drilling site on-site operation control system, and adjusting physical drilling construction parameters or executing a standard risk disposal physical operation flow based on the early warning signal.
Outputting an early warning signal of the calculated risk is insignificant extra solution activity in the form of outputting the calculated result of the abstract idea. See MPEP §2106.05(g).
Executing a standard risk disposal physical operation flow based on the abstract idea result amounts to mere instruction to apply the result of the abstract idea. See MPEP §2106.05(f). Adjusting physical drilling construction parameters is recited in the alternative and thus not required for infringement of the claim. However, because of the generality of the “adjusting” the adjustment would also be considered mere instruction to apply the result of the abstract idea. See MPEP §2106.05(f).
Claim 1 step 2B:
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception, when considered individually and in combination, because:
Limitations analyzed under MPEP §2106.05(f) are analyzed the same under step 2B as under step 2A(ii) above.
Claim 1 recites:
5: outputting an early warning signal of the recognized while-drilling safety risks to a drilling site on-site operation control system, ….
Outputting the result of an abstract idea is well understood, routine, and conventional. US patent 5,850,560 Kang [herein “Kang”] teaches “It is of course conventional to display information and results of an operation performed by the computer as an image on a video monitor.” This is sufficient Berkheimer evidence for a generic recitation of “outputting” a calculated result of an abstract idea.
When further considering the claims as a whole and as an ordered combination the claims fail to amount to significantly more than the judicially excepted abstract idea.
Claim 2 step 2A(i):
Dependent claims recite at least the identified judicially excepted subject matter of their parent claim(s).
The claim(s) recite:
2. The intelligent recognition method for the while-drilling safety risks based on the convolutional neural network according to claim 1, wherein the step 1 specifically comprises the following sub-steps:
…, initially screening out monitoring parameters that can reflect the changes in working conditions during the drilling process in a timely manner, and removing invalid or incorrect data;
102: further selecting a plurality of core parameters based on the importance of parameters in the monitoring-while-drilling process, to reduce the amount of subsequent data processing;
103: further classifying data sets in respective stages according to different stages of the drilling process; and
104: forming a macro law of changes in monitoring data corresponding to various safety risks by using a while-drilling safety risk theoretical model, and determining the composition of respective parameters in the most refined sample that characterizes various safety risk conditions in conjunction with Pearson parameter correlation analysis results.
Screening and removing monitoring parameters that somehow reflect the changes in working conditions during the drilling process corresponds with mental process evaluation, judgment, or opinion. Combining mathematical concepts with mental process decisions about the result is a combination of abstract idea which itself is an abstract idea.
Selecting core parameters based on an “importance” of parameters to reduce an amount of subsequent data processing is further recitation of a step in a mathematical algorithm. Alternatively, the selecting comprises mental process in the form of evaluation, judgment, and/or opinion.
Classifying data sets has a broad claim scope which encompasses both a mathematical classification and/or mental process determination.
Forming a “macro law” corresponds with a mathematical construction of a mathematical modeling in conjunction with Pearson parameter correlation analysis results. The theoretical model corresponds with a mathematical model.
This falls within the mathematical concept grouping of abstract ideas. See MPEP §2106.04(a)(2).
Claim 2 step 2A(ii):
This judicial exception is not integrated into a practical application because:
The claim(s) recite:
101: acquiring historical data of monitoring-while-drilling in multiple wells, …
A step of “acquiring” data is a high level recitation of data gathering. Data gathering, recited at a high level of generality, is insignificant extra solution activity. See MPEP §2106.05(g).
Claim 2 step 2B:
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception, when considered individually and in combination, because:
MPEP §2106.05(d) provides examples of data gathering:
i. Receiving or transmitting data over a network, …
iv. Storing and retrieving information in memory
When further considering the claims as a whole and as an ordered combination the claims fail to amount to significantly more than the judicially excepted abstract idea.
Claim 3 step 2A(i):
Dependent claims recite at least the identified judicially excepted subject matter of their parent claim(s).
The claim(s) recite:
3. The intelligent recognition method for the while-drilling safety risks based on the convolutional neural network according to claim 1, wherein the step 2 specifically comprises the following sub-steps:
201: performing a comparative experiment to ensure that the networks can not only contain most of the features of the while-drilling safety risks, but also reduce the system delay; and meanwhile, performing offline analysis on drilling monitoring data, and constructing the training sample data and the test sample data;
202: preprocessing sample data by using few sample learning, processing the samples by using scaling, cropping, interpolation and Synthetic Minority Over-sampling Technique (SMOTE) algorithms in data enhancement, and transferring a weight in a trained similar network by using a transfer learning algorithm to a new network with a certain correlation for training; and
203: normalizing a part of data that has too a difference greater than Y in numerical value in the samples, wherein the preset threshold Y is determined according to the full scale range of the monitoring parameter.
Performing a comparative experiment to ensure the machine learning network can contain features of the safety risks and reduce system delay corresponds with mathematical operations tuning of training the machine learning model accordingly. Comparison to evaluate is further a mental process in the form of evaluation, judgment, or opinion.
Preprocessing data using few sample learning, scaling, cropping, interpolation, and Synthetic Minority Over-sampling Technique (SMOTE) algorithms is performing corresponding mathematical operations. Similarly, the transfer learning algorithm is a mathematical algorithm.
Normalizing data is a mathematical operation on the data.
This falls within the mathematical concept grouping of abstract ideas. See MPEP §2106.04(a)(2).
Claim 3 step 2A(ii):
This judicial exception is not integrated into a practical application because:
Claim(s) do not recite any “additional” limitations.
Claim 3 step 2B:
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception, when considered individually and in combination, because:
Claim(s) do not recite any “additional” limitations.
When further considering the claims as a whole and as an ordered combination the claims fail to amount to significantly more than the judicially excepted abstract idea.
Claim 4 step 2A(i):
Dependent claims recite at least the identified judicially excepted subject matter of their parent claim(s).
The claim(s) recite:
4. The intelligent recognition method for the while-drilling safety risks based on the convolutional neural network according to claim 3, wherein said processing the samples by using scaling, cropping, interpolation and SMOTE algorithms in data enhancement is specifically as follows: for a part of historical parameters with an increase of more than 30% of full scale within a sample period, a part of the data in the changing process can be extracted and expanded to the same time span by using data scaling and cropping to form a new training sample, and then the scaled data is filled to make it the same as an original sample by using a piecewise interpolation method; and after the data scaling and interpolation, fewer samples are analyzed by using a SMOTE algorithm, and a new sample is artificially synthesized based on the fewer samples and added to a data set, wherein the data enhancement processing is only performed on the historical parameters of while-drilling safety risks with an increase of more than 30% of full scale within a sample period.
Using scaling, cropping, interpolation and SMOTE algorithms is using mathematical algorithms on corresponding data.
The piecewise interpolation method is further recitation of mathematical algorithm.
The so-called “synthesis” of a new sample corresponds with calculating data with corresponding mathematical calculations.
This falls within the mathematical concept grouping of abstract ideas. See MPEP §2106.04(a)(2).
Claim 4 step 2A(ii):
This judicial exception is not integrated into a practical application because:
Claim(s) do not recite any “additional” limitations.
Claim 4 step 2B:
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception, when considered individually and in combination, because:
Claim(s) do not recite any “additional” limitations.
When further considering the claims as a whole and as an ordered combination the claims fail to amount to significantly more than the judicially excepted abstract idea.
Claim 5 step 2A(i):
Dependent claims recite at least the identified judicially excepted subject matter of their parent claim(s).
The claim(s) recite:
5. The intelligent recognition method for the while-drilling safety risks based on the convolutional neural network according to claim 1, wherein the step 3 specifically comprises the following sub-steps: 301:
performing feature extraction, including pre-learning, on the sample data by using a convolutional layer, and then optimizing all network parameters by using a back-propagation algorithm; and
302: designing a network structure, which comprises an input layer, a convolutional layer 1, a convolutional layer 2, a hidden layer and an output layer; and performing a dimension reduction process on data before being inputted to a fully connected layer by using a principal component analysis method and by taking an elu function as an activation function.
Using a convolution layer and back-propagation algorithm is performing corresponding mathematical calculations.
Using PCA to perform a dimension reduction is performing corresponding mathematical calculations of the mathematical algorithm.
The elu function is another mathematical function.
This falls within the mathematical concept grouping of abstract ideas. See MPEP §2106.04(a)(2).
Claim 5 step 2A(ii):
This judicial exception is not integrated into a practical application because:
Claim(s) do not recite any “additional” limitations.
Claim 5 step 2B:
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception, when considered individually and in combination, because:
Claim(s) do not recite any “additional” limitations.
When further considering the claims as a whole and as an ordered combination the claims fail to amount to significantly more than the judicially excepted abstract idea.
Claim 6 step 2A(i):
Dependent claims recite at least the identified judicially excepted subject matter of their parent claim(s).
The claim(s) recite:
6. The intelligent recognition method for the while-drilling safety risks based on the convolutional neural network according to claim 5, wherein the convolutional layer 1 is used to extract the changing trend of each parameter, and a one-dimensional longitudinal convolution kernel of m*1 is used to perform separate convolution calculations on n parameters respectively.
The convolution layer is a mathematical structure of the CNN. The dimensional size of the convolution kernel is a further mathematical structure.
This falls within the mathematical concept grouping of abstract ideas. See MPEP §2106.04(a)(2).
Claim 6 step 2A(ii):
This judicial exception is not integrated into a practical application because:
Claim(s) do not recite any “additional” limitations.
Claim 6 step 2B:
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception, when considered individually and in combination, because:
Claim(s) do not recite any “additional” limitations.
When further considering the claims as a whole and as an ordered combination the claims fail to amount to significantly more than the judicially excepted abstract idea.
Claim 7 step 2A(i):
Dependent claims recite at least the identified judicially excepted subject matter of their parent claim(s).
The claim(s) recite:
7. The intelligent recognition method for the while-drilling safety risks based on the convolutional neural network according to claim 5, wherein the convolutional layer 2 is used to extract a change relationship between parameters, and a one-dimensional transverse convolution kernel of 1*n is used to perform separate feature extraction on each row of a matrix.
The convolution layer is a mathematical structure of the CNN. The dimensional size of the convolution kernel is a further mathematical structure.
This falls within the mathematical concept grouping of abstract ideas. See MPEP §2106.04(a)(2).
Claim 7 step 2A(ii):
This judicial exception is not integrated into a practical application because:
Claim(s) do not recite any “additional” limitations.
Claim 7 step 2B:
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception, when considered individually and in combination, because:
Claim(s) do not recite any “additional” limitations.
When further considering the claims as a whole and as an ordered combination the claims fail to amount to significantly more than the judicially excepted abstract idea.
Claim 8 step 2A(i):
Dependent claims recite at least the identified judicially excepted subject matter of their parent claim(s).
The claim(s) recite:
8. The intelligent recognition method for the while-drilling safety risks based on the convolutional neural network according to claim 5, wherein the principal component analysis method aims to reduce a set of N-dimensional vectors to K-dimensional vectors, where
0
<
K
<
N
, and the calculation process includes the following steps:
3021: normalizing each row of a variable matrix of a p*n order to form a new matrix X according to columns;
3022: solving a covariance matrix of the m-order matrix X;
3023: calculating feature values and corresponding feature vectors of the covariance matrix C;
3024: arranging the feature vectors from top to bottom in rows according to magnitudes of the corresponding feature values to form a matrix, and then taking their corresponding k feature vectors as column vectors respectively to form a feature vector matrix P; and
3025: multiplying the matrix X and the matrix P to acquire data after reduction to k dimension.
Normalizing is a mathematical operation on the data.
Solving the covariance matrices is further mathematical operations.
Calculating feature values of the vectors is further mathematical calculation.
Arranging the feature vectors to form a matrix is further mathematical calculation and mathematical construction
Lastly, multiplying the matrices is further explicit mathematical calculation.
This falls within the mathematical concept grouping of abstract ideas. See MPEP §2106.04(a)(2).
Claim 8 step 2A(ii):
This judicial exception is not integrated into a practical application because:
Claim(s) do not recite any “additional” limitations.
Claim 8 step 2B:
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception, when considered individually and in combination, because:
Claim(s) do not recite any “additional” limitations.
When further considering the claims as a whole and as an ordered combination the claims fail to amount to significantly more than the judicially excepted abstract idea.
Claim 9 step 2A(i):
Dependent claims recite at least the identified judicially excepted subject matter of their parent claim(s).
The claim(s) recite:
9. The intelligent recognition method for the while-drilling safety risks based on the convolutional neural network according to claim 5, wherein the number of nodes in the hidden layer is
S
=
2
x
+
1
, where x is the number of nodes in the input layer; and the number of nodes in the hidden layer is
S
<
N
-
1
, where N is the number of network training samples.
The layers of the CNN are the mathematical structure of the CNN. The number of hidden layers and nodes correspond with the mathematical structure of this neural network.
This falls within the mathematical concept grouping of abstract ideas. See MPEP §2106.04(a)(2).
Claim 9 step 2A(ii):
This judicial exception is not integrated into a practical application because:
Claim(s) do not recite any “additional” limitations.
Claim 9 step 2B:
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception, when considered individually and in combination, because:
Claim(s) do not recite any “additional” limitations.
When further considering the claims as a whole and as an ordered combination the claims fail to amount to significantly more than the judicially excepted abstract idea.
Allowable Subject Matter
Claims 1-9 would be allowable if rewritten or amended to overcome the rejection(s) under 35 U.S.C. §101, and under 35 U.S.C. §112(b) or 35 U.S.C. §112 (pre-AIA ), 2nd paragraph, set forth in this Office action.
The following is a statement of reasons for the indication of allowable subject matter:
Qodirov, S. & Shestakov, A. “Development of Artificial Neural Network for Predicting Drill Pipe Sticking in Real-Time Well Drilling Process” IEEE, Global Smart Industry Conf., GloSIC (2020) [herein “Qodirov”] teaches predicting drill pipe sticking using ANN. Qodirov page 144 table 1 “Neural Network Configuration” teaches seven layers with respective numbers of neurons and activation functions. Qodirov fails to teach two different one-dimensional convolutional layers as claimed.
Siruvuri, C., et al. “Stuck Pipe Prediction and Avoidance: A Convolutional Neural Network Approach” IADC/SPE Drilling Conf. (2006) [herein “Siruvuri”] stuck pipe prediction using CNN. Siruvuri page 4 figure 4 “Neural Network Architecture” where “The output layer is fully connected to all the units in the hidden layers as shown in Fig. 4.” Siruvuri fails to teach two different one-dimensional convolutional layers as claimed.
US patent 11,989,657 B2 Chavoshi, et al. [herein “Chavoshi”] teaches technology background on machine learning for timeseries data. Chavoshi does not teach drilling. Chavoshi fails to teach two different one-dimensional convolutional layers as claimed.
US 2022/0390633 A1 Laigle, et al. [herein “Laigle”] teaches deep learning of parameters in the subsurface. Laigle paragraph 28 teaches “a two-layer fully-connected dense neural network.” Laigle 23 teaches PCA for dimensionality reduction. Laigle fails to teach two different one-dimensional convolutional layers as claimed.
US patent 11,796,714 B2 Smith, et al. [herein “Smith”] figure 5 teaches “example layering, filter size, output shape, and a number of parameters.” Smith column 8 lines 20-24 teaches “The use of stacked 1D dilated convolutions enable the TCN to build a large receptive field (the size of the input that affects a particular feature or output) using only a few layers.” Stacked 1D convolutions, plural, are at least two convolutional layers. However, Smith fails to teach the network structure claimed as these stacked 1D convolutional layers are not specifically
m
×
1
and
1
×
n
as claimed.
None of the references taken either alone or in combination with the prior art of record disclose “wherein the network structure comprises an input layer, a [first] convolutional layer, a [second] convolutional layer, a hidden layer and an output layer; the [first] convolutional layer uses a one-dimensional longitudinal convolution kernel of m1 to perform separate convolution calculations on each monitoring parameter respectively, …, the [second] convolutional layer uses a one-dimensional transverse convolution kernel of 1n to perform separate feature extraction on each row of the parameter matrix” in combination with the remaining elements and features of the claimed invention.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Jay B Hann whose telephone number is (571)272-3330. The examiner can normally be reached M-F 10am-7pm EDT.
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, Renee Chavez can be reached at (571) 270-1104. 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.
/Jay Hann/Primary Examiner, Art Unit 2186 25 March 2026
Prosecution Insights