DETAILED ACTION
This action is responsive to the claims filed on April 21, 2022.
Claims 1-15 are under examination.
Claim 10 is objected to.
Claims 8-15 are rejected under 35 USC 112(b) for indefiniteness.
Claims 1-15 are rejected under 35 USC 101 for reciting ineligible subject matter.
Claims 1-7 are rejected under 35 USC 103 over Mullins in view of Nichita.
Claims 8-15 are rejected under 35 USC 103 over Wang in view of Rodriguez.
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 Objections
Claim 10 is objected to because of the following informalities:
Antecedence
Claim 10 recites “[…] collecting […] prior to collecting data related to the downhole fluid.” However, primary antecedence is already provided for the limitation “collecting data related to the downhole fluid” in claim 8, from which claim 10 depends.
Appropriate correction is required.
Claim Rejections - 35 USC § 112
Claims 8-15 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 applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Qualified dataset
“Qualified dataset” is a subjective term and is not a term of art in the technological arts of machine learning, spectroscopy, or downhole fluid envelope determination. For the purposes of examination, “qualified dataset” will be interpreted to mean “dataset.” The Applicant is invited to amend claim 8 to clarify the meaning of qualified or the manner in which such qualification is accomplished, without introducing new matter.
Optimization of the ANN
Claim 9 recites, “optimization of the artificial neural network.” Optimization is a relative term. Accordingly, a person skilled in the art would not recognize the metes and bounds of the term optimization. Applicant is advised to incorporate a definition in the specification into the claim from paragraph [040], which states, “[o]ptimization of the weights is made by backward propagation of error during the training or learning phase.”
Claims 10-15 are rejected under 35 USC 112(b), based on their dependency from explicitly rejected claims.
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 1-15 are rejected under 35 USC 101 because the claimed invention is directed to an abstract idea of both a mathematical concept and mental process without significantly more.
In General
INITIAL NOTE: Claims 1-4, 6-11, and 15 fail to recite a computer as conducting the steps of the methods as recited. Accordingly, these steps of these claims are recited broadly enough to be performed mentally or with the aid of pen, paper, and/or calculator, or can be characterized as organizing human activity.
Further, the recitation of a module in claims 5 and 12 for collecting data are recited at such a high level that they are, at best, generic computing hardware elements under MPEP 2106.05(f), and can do nothing to further integrate the mental process or organization of human activity into a practical application at Step 2A, Prong 2, or combine with the other elements of the claim to provide significantly more than the abstract idea that would confer an inventive concept at Step 2B. At worst, claims 5 and 12 recite software per se, which is not one of the four categories. See MPEP 2106.03.
The Applicant is advised to amend to specify that the methods are computer-implemented to make the claims fit for eligibility analysis. In the interest of compact prosecution, the eligibility analysis will be carried out as if the claims recite that the method steps are conducted by or from a computer or other non-transitory medium.
Step 1
Claims 1-15 are directed towards the statutory category of a process (provided they are amended to recite that they are computer implemented, as discussed above.).
Step 2A – Prong 1
As an initial matter, the Examiner notes that these claims share many similarities with the claims found to be an abstract idea without significantly more in Example 47, Claim 2 of the Subject Matter Eligibility Examples (July 2024 Subject Matter Eligibility Examples) Electric Power Group, LLC v. Alstom S.A. (Fed. Cir. 2016).
In particular, the following:
Regarding claim 1: The estimating saturation pressures and producing a phase envelope […] based upon the estimated saturation pressures steps are purely results-oriented, specifying what the desired results are, but lacking any recitation of how these results are to be determined. This is especially true when the saturation pressures are elements of the phase envelope. In other words, a mental process given the generality of these steps. MPEP § 2106.04(a)(2)(111)(C): "• a claim to "collecting information, analyzing it, and displaying certain results of the collection and analysis," where the data analysis steps are recited at a high level of generality such that they could practically be performed in the human mind, Electric Power Group v. Alstom, S.A., 830 F.3d 1350, 1353-54, 119 USPQ2d 1739, 1741-42 (Fed. Cir. 2016);" and MPEP § 2106.05(f): "Electric Power Group., 830 F.3d at 1356, 1356, USPQ2d at 1743-44 (cautioning against claims "so result focused, so functional, as to effectively cover any solution to an identified problem") None of the dependent claims remedy this and are similarly analogous.
Regarding claim 8: The performing an output validation on the testing portion, training an artificial neural network model to produce a training data output and performing an output validation on the training data output steps are purely results-oriented, specifying what the desired results are, but lacking any recitation of how these results are to be determined beyond the most conventional training, retraining, and validating steps (e.g., K-fold validation between epochs of training to determine convergence and prevent overfit). In other words, a mental process given the generality of these steps. None of the dependent claims remedy this and are similarly generic by today’s technological standards. See Subject Matter Eligibility, Example 47, claim 2.
The ordered combination at prong 1 is conventional, except that it is limited to the field of oil/phase envelope. See the Computer Vision Metrics textbook recited below (Page 416). Also, see the Rodriguez reference citations in the 35 USC 103 rejection and the Skansi reference on record at Chapter 4. Using an input layer, one or more hidden layers, an output layer, weights connecting nodes, and activation functions with feed-forward, loss determination, and backpropagation of loss until convergence by some standard, are all conventional elements of machine learning. This conventionality should be considered at Step 2, Prong 1 for inclusion in the abstract idea, and Step 2B for demonstration of conventionality for independent and dependent claims in this set.
Claim 1 recites (claim limitations italicized, references are to the Applicant’s specification),
A method, comprising: […] processing the collected data; (Mental Process, Mathematical Concept) Claim 3 and paragraph [0047] specifies that the processing can include mere discretizing of temperature data. Discretizing data merely sets a precision limit for the temperature data provided (e.g., by rounding, truncating, and/or interpolating). This is an evaluation that can be performed in the mind with aid of pen, paper, and/or a calculator, so it is a mental process under MPEP 2106.04(a)(2)(III). Also, rounding, truncating, and/or interpolating are mathematical calculations that are mathematical concepts under MPEP 2106.04(a)(2)(I). Mental Processes and Mathematical Concepts are Abstract Ideas.
inputting the processed collected data to an artificial neural network; estimating saturation pressures based upon the processing of the collected data; and producing a phase envelope for the downhole fluid based upon the estimated saturation pressures. (Evaluation, Mental Process that can be performed in the mind or with the aid of pen, paper, and/or a calculator – See Applicant’s specification paragraph [053], method 850 describing FIG. 8B. This uses a trained ANN for inference of saturation pressures of a phase envelope based on the input of temperatures and fluid composition data at those temperatures. The phase envelope is concurrently or subsequently constructed from the output saturation pressures, e.g., by graphing the temperature-pressure values.). This is analogous to the claims in Electric Power Group and to steps (d), (e), and (f) of Example 47 in the subject matter eligibility guidance from the USPTO (July 2024 Subject Matter Eligibility Examples). These steps of using an ANN for inference are mental processes that can be performed in the mind or with the aid of pen, paper, and/or a calculator.
Claim 1 recites an abstract idea.
Claim 8 recites,
A method of training an artificial neural network for processing data related to a downhole fluid, comprising: (Mental Process, Mathematical Concept – According to paragraphs [039]-[043] and [052], the training is done by standard AI methods including forward propagation, loss determination, and backpropagation using an Adam optimizer, which is a weighted gradient descent algorithm. This is an evaluation that can be performed in the mind or with the aid of pen, paper, and/or a calculator under MPEP 2106.04(a)(2)(III), so it is a mental process. Further because the training is an evaluation of mathematical calculations (gradient descent) it recites a mathematical concept. This element recites a Mental Process and a Mathematical Concept, which are abstract ideas.)
[…]
processing the collected data related to the downhole fluid;
[…]
performing an output validation on the testing data portion; training an artificial neural network model to produce a training data output; and performing an output validation on the training data output. (Mental Process, Mathematical Concept – According to paragraphs [039]-[043] and [052], the training is done by standard AI methods including forward propagation, loss determination, and backpropagation using an Adam optimizer, which is a weighted gradient descent algorithm. The method further validates the result with a validation data set, which is a standard machine learning step. These steps are an evaluation that can be practically performed in the mind or with the aid of pen, paper, and/or a calculator under MPEP 2106.04(a)(2)(III), so the claim includes a mental process. Further because the training is an evaluation of mathematical calculations (gradient descent) it recites a mathematical concept. This element recites a Mental Process and a Mathematical Concept, which are abstract ideas.)
Claim 8 recites an abstract idea.
Step 2A, Prong 2
Claim 1 recites the following additional limitations:
collecting data of a downhole fluid; (This is mere data gathering, which is pre-solution insignificant extra-solution activity, and does not integrate the abstract idea into a practical application under MPEP 2106.05(g).
Should it be found that the machine learning model or the use thereof is not an element of the abstract idea, the machine learning model and use thereof is recited at such a high level that it is a generic computing element (“apply it”) and fails to integrate the abstract idea into a practical application under MPEP 2106.05(f).
Should it be found that the processing step is discretization by digitalization using a generic analog-to-digital converter, this is also a generic computing element (“apply it”) that fails to integrate the abstract idea into a practical application under MPEP 2106.05(f).
Further, any elements that specify to the types of data merely limit the abstract idea to a particular field (e.g., the oil industry/phase envelopes) and fail to integrate the abstract idea into a practical application under MPEP 2106.05(f).
Claim 1 fails to provide additional limitations that integrate the abstract idea into a practical application MPEP 2106.04(d).
Claim 1 is directed to the abstract idea.
Claim 8 recites the following additional limitations:
collecting data related to the downhole fluid; (This is mere data gathering, which is pre-solution insignificant extra-solution activity, and does not integrate the abstract idea into a practical application under MPEP 2106.05(g).)
[...]
producing a qualified dataset of the processed collected data; partitioning the qualified dataset of the collected data into a testing data portion and a training data portion; (This is mere data gathering, which is pre-solution insignificant extra-solution activity, and does not integrate the abstract idea into a practical application under MPEP 2106.05(g). Should it be found that the production of the qualified dataset is an evaluation, then it is alternatively an element of the abstract idea of claim 8.)
Should it be found that the machine learning model or the training or inference use thereof is not an element of the abstract idea, the machine learning model and training or inference use thereof is recited at such a high level that it is a generic computing element (“apply it”) and fails to integrate the abstract idea into a practical application under MPEP 2106.05(f).
Should it be found that the processing step is discretization by digitalization using a generic analog-to-digital converter, this is also a generic computing element (“apply it”) that fails to integrate the abstract idea into a practical application under MPEP 2106.05(f).
Further, any elements that specify to the types of data merely limit the abstract idea to a particular field (e.g., the oil industry/phase envelopes) and fail to integrate the abstract idea into a practical application under MPEP 2106.05(f).
Claim 8 fails to provide additional limitations that integrate the abstract idea into a practical application MPEP 2106.04(d).
Claim 8 is directed to the abstract idea.
Step 2B
Claim 1 recites the following additional limitations:
collecting data of a downhole fluid; (This is a well-understood, routine, and conventional function as in the examples in MPEP 2106.05(d): “i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362; iii. Electronic recordkeeping, Alice Corp. Pty. Ltd. v. CLS Bank Int'l, 573 U.S. 208, 225, 110 USPQ2d 1984 (2014); and iv. Storing and retrieving information in memory, Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015)” This is also mere data gathering, which is pre-solution insignificant extra-solution activity. Because the collecting is a well-understood, conventional, and routine activity, and is insignificant extra-solution activity, it does not combine with the other claim elements to provide significantly more than the abstract idea that would confer an inventive concept under MPEP 2106.05(g) and 2106.05(d))
Should it be found that the machine learning model or the use thereof is not an element of the abstract idea, the machine learning model and use thereof is recited at such a high level that it is a generic computing element (“apply it”) and fails to combine with the other claim elements to provide significantly more than the abstract idea that would confer an inventive concept under MPEP 2106.05(f).
Should it be found that the processing step is discretization by digitalization using a generic analog-to-digital converter, this is also a generic computing element (“apply it”) that fails to combine with the other claim elements to provide significantly more than the abstract idea that would confer an inventive concept under MPEP 2106.05(f).
Further, any elements that specify to the types of data merely limit the abstract idea to a particular field (e.g., the oil industry/phase envelopes) and fail to combine with the other claim elements to provide significantly more than the abstract idea that would confer an inventive concept under MPEP 2106.05(f).
Claim 1 fails to provide additional limitations that provide significantly more than the abstract idea that would confer an inventive concept under MPEP 2106.05.
Claim 1 is ineligible.
Claim 8 recites the following additional limitations:
collecting data related to the downhole fluid; (This is a well-understood, routine, and conventional function as in the examples in MPEP 2106.05(d): “i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362; iii. Electronic recordkeeping, Alice Corp. Pty. Ltd. v. CLS Bank Int'l, 573 U.S. 208, 225, 110 USPQ2d 1984 (2014); and iv. Storing and retrieving information in memory, Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015)” This is also mere data gathering, which is pre-solution insignificant extra-solution activity. Because the collecting is a well-understood, conventional, and routine activity, and is insignificant extra-solution activity, it does not combine with the other claim elements to provide significantly more than the abstract idea that would confer an inventive concept under MPEP 2106.05(g) and 2106.05(d))
[...]
producing a qualified dataset of the processed collected data; partitioning the qualified dataset of the collected data into a testing data portion and a training data portion; (This is a well-understood, routine, and conventional function as in the examples in MPEP 2106.05(d): “i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362; iii. Electronic recordkeeping, Alice Corp. Pty. Ltd. v. CLS Bank Int'l, 573 U.S. 208, 225, 110 USPQ2d 1984 (2014); iv. Storing and retrieving information in memory, Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015); and vi. Arranging a hierarchy of groups, sorting information, eliminating less restrictive pricing information and determining the price, Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1331, 115 USPQ2d 1681, 1699 (Fed. Cir. 2015). ” This is also mere data gathering, which is pre-solution insignificant extra-solution activity. Because the collecting is a well-understood, conventional, and routine activity, and is insignificant extra-solution activity, it does not combine with the other claim elements to provide significantly more than the abstract idea that would confer an inventive concept under MPEP 2106.05(g) and 2106.05(d). Should it be found that the production of the qualified dataset is an evaluation, then it is alternatively an element of the abstract idea of claim 8.)
Should it be found that the machine learning model or the training or inference use thereof is not an element of the abstract idea, the machine learning model and training or inference use thereof is recited at such a high level that it is a generic computing element (“apply it”) and fails to combine with the other claim elements to provide significantly more than the abstract idea that would confer an inventive concept under MPEP 2106.05(f).
Should it be found that the processing step is discretization by digitalization using a generic analog-to-digital converter, this is also a generic computing element (“apply it”) that fails to combine with the other claim elements to provide significantly more than the abstract idea that would confer an inventive concept under MPEP 2106.05(f).
Further, any elements that specify to the types of data merely limit the abstract idea to a particular field (e.g., the oil industry/phase envelopes) and fail to combine with the other claim elements to provide significantly more than the abstract idea that would confer an inventive concept under MPEP 2106.05(f).
Claim 8 fails to provide additional limitations that provide significantly more than the abstract idea that would confer an inventive concept under MPEP 2106.05.
Claim 8 is ineligible.
Regarding the dependent claims
Claim 2 is adding another step to qualify the mental process of the claim 1 processing step. As described with respect to the claim 1 processing step, discretization is a mental process. Should it be found that the processing step is discretization by digitalization using a generic analog-to-digital converter, this is also a generic computing element (“apply it”) that fails to integrate the abstract idea into a practical application or combine with the other claim elements to provide significantly more than the abstract idea that would confer an inventive concept and fails to combine with the other elements of the claim to provide significantly more than the abstract idea under MPEP 2106.05(f). Claim 2 is ineligible.
Claim 3 is adding another step to qualify the mental process of the claim 1 processing step. As described with respect to the claim 1 processing step, discretization of any data, including temperature data, is a mental process. Should it be found that the processing step is discretization by digitalization using a generic analog-to-digital converter, this is also a generic computing element (“apply it”) that fails to integrate the abstract idea into a practical application of combine with the other claim elements to provide significantly more than the abstract idea that would confer an inventive concept and fails to combine with the other elements of the claim to provide significantly more than the abstract idea under MPEP 2106.05(f). Claim 3 is ineligible.
Claim 4 recites that the phase envelope is produced based on the discretized temperature values. This is considered as further limiting the abstract idea by merely stating what data is to be a part of it, so it is part of the mental evaluation. Should it be found that this is not part of the mental evaluation, this merely links it to a particular field of use and fails to integrate the abstract idea into a practical application and fails to combine with the other elements of the claim to provide significantly more than the abstract idea under MPEP 2106.05(h). Claim 4 is ineligible.
Claim 5 recites a source of the data “wherein the collecting of the data of the downhole fluid is through a downhole fluid analysis module.” This is merely an element of the data gathering of the collecting step of claim 1, which, as demonstrated is insignificant extra-solution activity and well-understood, routine, and conventional activity. If it should be found that this is not mere data gathering, this limitation also merely limits the claim to the particular field of oil/phase envelopes. Therefore, claim 5 fails to provide any additional limitations that integrate the abstract idea into a practical application or combine with the other elements of the claim to provide significantly more than the abstract idea under MPEP 2106.05(g), MPEP 2106.05(d), MPEP 2106.05(h). Claim 5 is ineligible.
Claim 6 recites “wherein the collecting data of the downhole fluid comprises collecting data related to a pressure and a temperature.” This is merely an element of the data gathering of the collecting step of claim 1, which, as demonstrated is insignificant extra-solution activity and well-understood, routine, and conventional activity. If it should be found that this is not mere data gathering, this limitation also merely limits the claim to the particular field of oil/phase envelopes. Therefore, claim 5 fails to provide any additional limitations that integrate the abstract idea into a practical application or combine with the other elements of the claim to provide significantly more than the abstract idea under MPEP 2106.05(g), MPEP 2106.05(d), MPEP 2106.05(h). Claim 6 is ineligible.
Claim 7 recites “wherein the collecting data from the downhole fluid comprises collecting data related to H2S and C02.” This is merely an element of the data gathering of the collecting step of claim 1, which, as demonstrated is insignificant extra-solution activity and well-understood, routine, and conventional activity. If it should be found that this is not mere data gathering, this limitation also merely limits the claim to the particular field of oil/phase envelopes. Therefore, claim 5 fails to provide any additional limitations that integrate the abstract idea into a practical application or combine with the other elements of the claim to provide significantly more than the abstract idea under MPEP 2106.05(g), MPEP 2106.05(d), MPEP 2106.05(h). Claim 7 is ineligible.
Claim 9 recites “wherein the training the artificial neural network model includes optimization of the artificial neural network.” Paragraph [041] of the specification notes that the optimization is backpropagation using an Adam optimizer, which is an element of the mental evaluation and a mathematical calculation (e.g., Adam optimizer is a weighted gradient descent), which are elements of the abstract idea. Claim 9 recites no additional limitations that integrate the abstract idea into a practical application or combine with the other elements of the claim to provide significantly more than the abstract idea. Claim 9 is ineligible.
Claim 10 recites, “further comprising collecting one of laboratory data, pressure volume temperature reports and equation of state models prior to collecting data related to the downhole fluid.” This merely adds another mere data gathering step that is insignificant extra-solution activity and well-understood, routine, and conventional activity for the same reasons as the collecting step of claim 9. Should it be found otherwise, the collection of these types of data merely limit the abstract idea to a particular field of endeavor of oil/phase envelopes under MPEP 2106.05(h). Claim 10 recites no additional limitations that integrate the abstract idea into a practical application or combine with the other elements of the claim to provide significantly more than the abstract idea. Claim 10 is ineligible.
Claim 11 recites, “wherein the processing the collected data occurs in a computing arrangement.” This recites the generic use of a generic computing element, which fails to integrate the abstract idea into a practical application or combine with the other elements of the claim to provide significantly more than the abstract idea under MPEP 2106.05(f). Claim 11 recites no additional limitations that integrate the abstract idea into a practical application or combine with the other elements of the claim to provide significantly more than the abstract idea. Claim 11 is ineligible.
Claim 12 recites, “wherein the collecting data related to a downhole fluid is performed with a downhole fluid analysis module.” This recites the generic use of a generic computing element, which fails to integrate the abstract idea into a practical application or combine with the other elements of the claim to provide significantly more than the abstract idea under MPEP 2106.05(f). Claim 12 recites no additional limitations that integrate the abstract idea into a practical application or combine with the other elements of the claim to provide significantly more than the abstract idea. Claim 12 is ineligible.
Claim 13 recites, “wherein the artificial neural network has an input layer, a hidden layer and an output layer.” These are elements of the machine learning model and are therefore elements of the mental evaluation and are elements of the abstract idea because it is conventional elements of a standard DNN- Bilski and Diamon v. Diehr says the conventionality can steer and frame the analysis of whether an element is part of the abstract idea. This conventionality is demonstrated by the following recitation. Should it be found that it is not an element of the abstract idea, it is a generic computing element under MPEP 2106.05(f), so it does not integrate the abstract idea into a practical application or combine to provide the claim with significantly more than the abstract idea. Further, the generic elements of the machine learning model merely limit the model to computer technology as a field under MPEP 2106.05(h). Also, the features of claim 13 are well-understood, routine, and conventional as demonstrated in the following example.
See subject matter eligibility example 47, claim 2 – In this instance, the computer is recited at a high level of generality- the structure of an input layer, a hidden layer, and an output layer is the most common DNN, as illustrated in the following reference. Claim 13 is ineligible for at least the same reasons.
Page 416, Table 10.5 (shown below)- Krig, Scott. (2016). Computer Vision Metrics. 10.1007/978-3-319-33762-3. – illustrates an input layer, a hidden layer (one of many), and an output layer as a conventional model. Also, see FIG. 7 and the associated description from the Rodriguez reference used in the 35 USC 103 rejection (shown in the rejection) and the Skansi reference on record at Chapter 4.
Claim 13 recites no additional limitations that integrate the abstract idea into a practical application or combine with the other elements of the claim to provide significantly more than the abstract idea. Claim 13 is ineligible.
PNG
media_image1.png
1744
1348
media_image1.png
Greyscale
Claim 14 recites, “wherein the training an artificial neural network model includes using weights for data input to the artificial neural network.” These are elements of the machine learning model and are therefore elements of the mental evaluation and are elements of the abstract idea because it is conventional elements of a standard DNN- Bilski and Diamon v. Diehr says the conventionality can steer and frame the analysis of whether an element is part of the abstract idea. This conventionality is demonstrated by the following recitation. Should it be found that it is not an element of the abstract idea, it is a generic computing element under MPEP 2106.05(f), so it does not integrate the abstract idea into a practical application or combine to provide the claim with significantly more than the abstract idea. Further, the generic elements of the machine learning model merely limit the model to computer technology as a field under MPEP 2106.05(h). Also, the features of claim 14 are well-understood, routine, and conventional as demonstrated in the following example.
See subject matter eligibility example 47, claim 2 – In this instance, the computer is recited at a high level of generality- applying weights to the input layer to provide input to the hidden layer is conventional and generic in machine learning models. Claim 14 is ineligible for at least the same reasons.
Page 416, Table 10.5 and section (4) discussing the weights with respect to connections (shown above)- Krig, Scott. (2016). Computer Vision Metrics. 10.1007/978-3-319-33762-3. – illustrates weights applied to the input layer to generate input for the first hidden layer. Also, see FIG. 7 and the associated description from the Rodriguez reference used in the 35 USC 103 rejection (shown in the rejection) and the Skansi reference on record at Chapter 4.
Claim 14 recites no additional limitations that integrate the abstract idea into a practical application or combine with the other elements of the claim to provide significantly more than the abstract idea. Claim 14 is ineligible.
Claim 15 recites “wherein the artificial neural network has an input layer, at least two hidden layers and an output layer.” These are elements of the machine learning model and are therefore elements of the mental evaluation and are elements of the abstract idea because it is conventional elements of a standard DNN- Bilski and Diamon v. Diehr says the conventionality can steer and frame the analysis of whether an element is part of the abstract idea. This conventionality is demonstrated by the following recitation. Should it be found that it is not an element of the abstract idea, it is a generic computing element under MPEP 2106.05(f), so it does not integrate the abstract idea into a practical application or combine to provide the claim with significantly more than the abstract idea. Further, the generic elements of the machine learning model merely limit the model to computer technology as a field under MPEP 2106.05(h). Also, the features of claim 15 are well-understood, routine, and conventional as demonstrated in the following example.
See subject matter eligibility example 47, claim 2 – In this instance, the computer is recited at a high level of generality- applying weights to the input layer to provide input to the hidden layer is conventional and generic in machine learning models. Claim 13 is ineligible for at least the same reasons.
Page 416, Table 10.5 (shown above)- Krig, Scott. (2016). Computer Vision Metrics. 10.1007/978-3-319-33762-3. – Illustrates an input layer, two hidden layers (among many), and an output layer. Also, see FIG. 7 and the associated description from the Rodriguez reference used in the 35 USC 103 rejection (shown in the rejection) and the Skansi reference on record at Chapter 4.
Claim 15 recites no additional limitations that integrate the abstract idea into a practical application or combine with the other elements of the claim to provide significantly more than the abstract idea. Claim 15 is ineligible.
Claim Rejections - 35 USC § 103
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 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 1-7: Mullins and Nichita
Claim(s) 1-7 are rejected under 35 U.S.C. 103 as being unpatentable over US 20090288881 A1 to Mullins et al. (Mullins) in view of NPL: “Phase Envelope Construction for Mixtures with Many Components” by Nichita (Nichita).
Claim 1
Regarding claim 1, Mullins teaches:
1. A method, comprising: collecting data of a downhole fluid; (Mullins [0006] “In accordance with another disclosed example, another example method involves measuring a formation fluid and determining data on a fluid composition (“fluid composition data”) based on the measurement. ” [0048] “In the illustrated example, the sampling while drilling tool 142 is also provided with one or more sensors 205 to measure pressure/temperature, density/viscosity, and/or any other fluid properties.”)
processing the collected data; (Mullins [0049] “In the illustrated example, the controller 210 is configured to receive digital data from one or more sensors (e.g., the spectrometer 204 and the sensors 205 provided in the sampling while drilling tool 142.” – NOTE – digitalization of the signal data includes discretization/ processing)
inputting the processed collected data to an artificial neural network; (Mullins [0026] “In some example implementations, fluid properties may additionally or alternatively be represented or described using parameters or sets of parameters used in equations that describe characteristics of a fluid such as, for example, sets of parameters used in equations of state (EoS) or coefficients used, for example, as part of neural network methods and/or radial basis functions which are fit to entries contained in one or more fluid property databases.”)
estimating saturation pressures based upon the processing of the collected data; and (Mullins [0023] “The example methods and apparatus described herein can be implemented to use in-situ measurements indicative of formation fluid properties and/or a reservoir fluid property map. A formation fluid property can be determined by measuring a property of downhole fluid in or extracted from formation rock surrounding the borehole of a well.” [0026] “In the illustrated examples described herein, the formation and/or reservoir fluid properties include properties that are related (e.g., first-order related) to the reservoir fluid composition. In particular, the fluid properties can be one or more properties (e.g., in combination) of fluid compositions, and can relate to either partial or a full description of the composition, constituent isotope ratios, gas-liquid ratios, etc. Fluid composition data can alternatively be described with thermo-physical data such as, for example, fluid bulk density, saturation pressures, viscosity, fluid acoustic impedance (i.e. the square root of the product of the fluid compressibility by the fluid density), and fluid compressibility at a given pressure and temperature. […] n some example implementations, fluid properties may additionally or alternatively be represented or described using parameters or sets of parameters used in equations that describe characteristics of a fluid such as, for example, sets of parameters used in equations of state (EoS) or coefficients used, for example, as part of neural network methods and/or radial basis functions which are fit to entries contained in one or more fluid property databases.”)
producing a phase envelope for the downhole (Mullins [0063] “Fluid analysis reports stored in the fluid analysis report database 308 include data indicative of fluid compositions and thermo physical properties (e.g., temperature, pressure, volume, compressibility, density, viscosity, formation volume factor, gas-oil ratio, API gravity, phase envelope, thermal capacity, etc.) of fluids drawn from the reservoir R. The fluid analysis data can be used to determine how fluid properties vary along different depths of a formation and different portions of a reservoir. Fluid composition data can be measured in-situ or in a laboratory environment. In-situ fluid analysis (i.e., downhole fluid analysis) data can include data in the fluid analysis reports indicative of concentration levels of methane, (C1), ethane (C2), carbon dioxide (CO2), and water (H2O). In addition, the in-situ fluid analysis data can include concentration levels of fluid components such as, for example, the lumped group of propane, butane, and pentane (C3-5) and the lumped group of hydrocarbons with 6 or more carbons in their molecules (C6+). Gas-oil ratios of hydrocarbons can be derived from the fluid composition data. In addition, in-situ fluid analysis data can also include formation fluid pressure data, and fluid color related to, for example, concentration levels of asphaltene. In-situ fluid analysis data may also include density and viscosity of the sampled fluid.”)
Mullins teaches determining saturation pressures and storing determined phase envelopes. Phase envelopes are plots of saturation pressures at different temperatures. The saturations pressures at the different temperatures essentially are the phase envelope for a given downhole fluid composition. ([0026] “In the illustrated examples described herein, the formation and/or reservoir fluid properties include properties that are related (e.g., first-order related) to the reservoir fluid composition. In particular, the fluid properties can be one or more properties (e.g., in combination) of fluid compositions, and can relate to either partial or a full description of the composition, constituent isotope ratios, gas-liquid ratios, etc. Fluid composition data can alternatively be described with thermo-physical data such as, for example, fluid bulk density, saturation pressures, viscosity, fluid acoustic impedance (i.e. the square root of the product of the fluid compressibility by the fluid density), and fluid compressibility at a given pressure and temperature.” [0063] “Fluid analysis reports stored in the fluid analysis report database 308 include data indicative of fluid compositions and thermo physical properties (e.g., temperature, pressure, volume, compressibility, density, viscosity, formation volume factor, gas-oil ratio, API gravity, phase envelope, thermal capacity, etc.) of fluids drawn from the reservoir R.” – However, Mullins fails to explicitly teach, but Mullins in view of Nichita teaches:
producing a phase envelope for the downhole fluid based upon the estimated saturation pressures. (Nichita Abstract “A reduction method for constructing vapor–liquid equilibrium phase envelopes with cubic equations of state is presented. The paper describes the calculation procedures for saturation (dewpoint/bubblepoint) pressures and temperatures, quality lines (for given mole fraction or volume fraction of one of the equilibrium phases), cricondentherm and cricondenbar points, the critical point, and the spinodal. The phase envelope construction is fully automatic. The saturation points are calculated throughout the critical region by stepping around the phase envelope in pressure or temperature increments. An extrapolation procedure taking advantage of the Jacobian matrix available from a previous step is used. Problem formulation in terms of reduced variables leads to simpler partial derivatives with respect to pressure and temperature.”)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claims to modify the generic determinations of saturation pressures and phase envelopes in Mullins by the methods of determining phase envelopes from saturation pressures in Nichita because a person of ordinary skill in the art would be motivated by the recitation in Mullins of storing phase envelopes determined from the downhole data to look to Nichita for methods for determining phase envelopes that have been successfully tested for several different representative hydrocarbon mixtures with various phase envelope shapes. (Mullins [0063] “Fluid analysis reports stored in the fluid analysis report database 308 include data indicative of fluid compositions and thermo physical properties (e.g., temperature, pressure, volume, compressibility, density, viscosity, formation volume factor, gas-oil ratio, API gravity, phase envelope, thermal capacity, etc.) of fluids drawn from the reservoir R.”; Nichita Abstract “The proposed method is successfully tested for several representative hydrocarbon mixtures with various phase envelope shapes.”)
Claim 2
Regarding claim 2, Mullins in view of Nichita teaches:
wherein the processing of the collected data involves discretization. (Mullins [0049] “In the illustrated example, the controller 210 is configured to receive digital data from one or more sensors (e.g., the spectrometer 204 and the sensors 205 provided in the sampling while drilling tool 142.” – NOTE – digitalization of the signal data includes discretization/ processing; ALSO Nichita Abstract “The saturation points are calculated throughout the critical region by stepping around the phase envelope in pressure or temperature increments.”)
Claim 3
Regarding claim 3, Mullins in view of Nichita teaches:
wherein temperature values of the collected data are discretized. (Mullins [0048] “In the illustrated example, the sampling while drilling tool 142 is also provided with one or more sensors 205 to measure pressure/temperature, density/viscosity, and/or any other fluid properties.” [0049] “In the illustrated example, the controller 210 is configured to receive digital data from one or more sensors (e.g., the spectrometer 204 and the sensors 205 provided in the sampling while drilling tool 142.” – NOTE – digitalization of the temperature signal data by the sensor or an intermediate includes discretization of the temperature data; ALSO Nichita Abstract “The saturation points are calculated throughout the critical region by stepping around the phase envelope in pressure or temperature increments.”)
Claim 4
Regarding claim 4, Mullins in view of Nichita teaches:
wherein the phase envelope is produced based upon the discretized temperature values. (Nichita Abstract “A reduction method for constructing vapor–liquid equilibrium phase envelopes with cubic equations of state is presented. The paper describes the calculation procedures for saturation (dewpoint/bubblepoint) pressures and temperatures, quality lines (for given mole fraction or volume fraction of one of the equilibrium phases), cricondentherm and cricondenbar points, the critical point, and the spinodal. The phase envelope construction is fully automatic. The saturation points are calculated throughout the critical region by stepping around the phase envelope in pressure or temperature increments. An extrapolation procedure taking advantage of the Jacobian matrix available from a previous step is used. Problem formulation in terms of reduced variables leads to simpler partial derivatives with respect to pressure and temperature. The proposed method is successfully tested for several representative hydrocarbon mixtures with various phase envelope shapes.)
Claim 5
Regarding claim 5, Mullins in view of Nichita teaches:
wherein the collecting of the data of the downhole fluid is through a downhole fluid analysis module. (Mullins [0048]-[0049] “In the illustrated example, the sampling while drilling tool 142 is provided with a spectrometer 204. The spectrometer 204 may be implemented using, for example, a light absorption/fluorescence spectrometer, a NMR spectrometer, or a mass spectrometer. In other example implementations, the sampling while drilling tool 142 may be provided with a gas chromatographer (e.g., to perform one-dimensional or two-dimensional gas chromatography measurements) in addition to or instead of the spectrometer 204. In the illustrated example, the sampling while drilling tool 142 is also provided with one or more sensors 205 to measure pressure/temperature, density/viscosity, and/or any other fluid properties. The sampling while drilling tool 142 may optionally include one or more fluid store(s) 206 connected to a tool fluid bus 230, each store including one or more fluid sample chambers in which reservoir fluid recovered during sampling operations can be stored and brought to the surface for further analysis and/or confirmation of downhole analyses. To store, analyze, process, and/or compress test and measurement data (or any other data acquired by the sampling while drilling tool 142), the sampling while drilling tool 142 is provided with an electronics system 208. In the illustrated example, the electronics system 208 includes a controller 210 (e.g., a CPU and random access memory) to control operations of the sampling while drilling tool 142 and implement measurement routines (e.g., to control the spectrometer 204, etc.). To store machine accessible instructions that, when executed by the controller 210, cause the controller 210 to implement measurement processes or any other processes, the electronics system 208 is provided with an electronic programmable read only memory (EPROM) 212. In the illustrated example, the controller 210 is configured to receive digital data from one or more sensors (e.g., the spectrometer 204 and the sensors 205) provided in the sampling while drilling tool 142.”)
Claim 6
Regarding claim 6, Mullins in view of Nichita teaches:
wherein the collecting data of the downhole fluid comprises collecting data related to a pressure and a temperature. (Mullins [0048] “In the illustrated example, the sampling while drilling tool 142 is also provided with one or more sensors 205 to measure pressure/temperature, density/viscosity, and/or any other fluid properties.”)
Claim 7
Regarding claim 7, Mullins in view of Nichita teaches:
wherein the collecting data from the downhole fluid comprises collecting data related to H2S and C02. (Mullins [0042] “Indeed, mud gas logging looks only at a subset of the hydrocarbons and gases usually encountered in Earth formations (e.g., volatile hydrocarbons, carbon dioxide, hydrogen sulphide, nitrogen, etc.)” [0048] “In the illustrated example, the sampling while drilling tool 142 is provided with a spectrometer 204. The spectrometer 204 may be implemented using, for example, a light absorption/fluorescence spectrometer, a NMR spectrometer, or a mass spectrometer. In other example implementations, the sampling while drilling tool 142 may be provided with a gas chromatographer (e.g., to perform one-dimensional or two-dimensional gas chromatography measurements) in addition to or instead of the spectrometer 204.” [0050] “To analyze measurement data, the sampling while drilling tool 142 is provided with a data processor 214. In the illustrated example, the data processor 214 is configured to determine fluid properties (e.g., fluid elements and/or composition, GOR, saturation pressures, formation mobility, fluid color, asphaltene or wax concentration levels, pressure, temperature, density, viscosity, compressibility, EoS parameters, thermal and chemical properties, etc . . . ) of formation fluid samples based on the measurement data collected by the spectrometer 204 and/or the one or more sensors 205.”)
Claims 8-15
Claim(s) 8-15 are rejected under 35 U.S.C. 103 as being unpatentable over US 2017/0370214 A1 to Wang et al. (Wang) in view of NPL: “Artificial Neural Networks – Architectures And Applications – Chapter 4 Robust Design of Artificial Neural Networks Methodology in Neutron Spectrometry” by Ortiz-Rodriguez et al. (Rodriguez).
Claim 8
Regarding claim 8, Wang teaches:
A method of training an artificial neural network for processing data related to a downhole fluid, comprising: (Wang [0034] “n some example implementations, a machine learning algorithm is trained on data of historical samples, and the machine learning algorithm is used to predict one or more properties of the fluid, such as one or more compositional components of the fluid. For example, during downhole fluid analysis (DFA), properties of the fluid may be obtained. These properties may be input to the machine learning algorithm, and the machine learning algorithm may output the predicted one or more properties, such as the one or more compositional components.”
collecting data related to the downhole fluid; (Wang [0041] “The drill collars 136, 138 may include various instruments, such as sample-while-drilling (SWD) tools that include sensors, telemetry equipment, and so forth. For example, the drill collars 136, 138 may include logging-while-drilling (LWD) modules 140 and/or measurement-while drilling (MWD) modules 142. The LWD modules 140 may include tools operable to measure formation parameters and/or fluid properties, such as resistivity, porosity, permeability, sonic velocity, optical density (OD), pressure, temperature, and/or other example properties.” [0042] “The LWD modules 140 and/or the MWD modules 142 may include a downhole formation fluid sampling tool operable to selectively sample fluid from the subsurface formation 112. The drilling system 110 may be operable to determine, estimate, or otherwise obtain various properties associated with the sampled formation fluid.”)
processing the collected data related to the downhole fluid; producing a qualified dataset of the processed collected data; partitioning the qualified dataset of the collected data into a testing data portion and a training data portion; (Wang [0034] “In some example implementations, a machine learning algorithm is trained on data of historical samples, and the machine learning algorithm is used to predict one or more properties of the fluid” [0084] “In some example implementations, some of the data of the oil historical samples and the gas historical samples may be used to validate the oil-type machine learning algorithm and the gas-type machine learning algorithm. For example, of a dataset of 1,800 samples that are separated into oil samples and gas samples, eighty percent (80%) of the grouped samples can be used to train the respective machine learning algorithms, and the remaining twenty percent (20%) of the grouped samples can be used to validate the respective machine learning algorithms.”)
testing data portion; (Wang [0034] “In some example implementations, a machine learning algorithm is trained on data of historical samples, and the machine learning algorithm is used to predict one or more properties of the fluid” [0084] “In some example implementations, some of the data of the oil historical samples and the gas historical samples may be used to validate the oil-type machine learning algorithm and the gas-type machine learning algorithm. For example, of a dataset of 1,800 samples that are separated into oil samples and gas samples, eighty percent (80%) of the grouped samples can be used to train the respective machine learning algorithms, and the remaining twenty percent (20%) of the grouped samples can be used to validate the respective machine learning algorithms.”)
training an artificial neural network model ; and (Wang [0034] “In some example implementations, a machine learning algorithm is trained on data of historical samples, and the machine learning algorithm is used to predict one or more properties of the fluid” [0084] “In some example implementations, some of the data of the oil historical samples and the gas historical samples may be used to validate the oil-type machine learning algorithm and the gas-type machine learning algorithm. For example, of a dataset of 1,800 samples that are separated into oil samples and gas samples, eighty percent (80%) of the grouped samples can be used to train the respective machine learning algorithms, and the remaining twenty percent (20%) of the grouped samples can be used to validate the respective machine learning algorithms.”)
performing an output validation (Wang [0034] “In some example implementations, a machine learning algorithm is trained on data of historical samples, and the machine learning algorithm is used to predict one or more properties of the fluid” [0084] “In some example implementations, some of the data of the oil historical samples and the gas historical samples may be used to validate the oil-type machine learning algorithm and the gas-type machine learning algorithm. For example, of a dataset of 1,800 samples that are separated into oil samples and gas samples, eighty percent (80%) of the grouped samples can be used to train the respective machine learning algorithms, and the remaining twenty percent (20%) of the grouped samples can be used to validate the respective machine learning algorithms.”)
Wang does not appear to explicitly teach, but Wang in view of Rodriguez teaches:
performing an output validation on the testing data portion; (Rodriguez Page 89, First Paragraph Under The Bullet Points “Once a pattern has been applied to the input of the network as a stimulus, this is propagated from the first layer through the superior layers of the net until generate an output. The output signal is compared with the desired output and a signal error is calculated for each one of the outputs.”)
training an artificial neural network model to produce a training data output; and (Rodriguez Page 89, Second-Third Paragraphs Under The Bullet Points “The outputs errors are back propagated from the output layer toward all the neurons of the hidden layer that contribute directly with the output. However, the neurons of the hidden layer only receive a fraction of the signal from the whole error signal, based on the relative contribution that has contributed each neuron to the original output.”)
performing an output validation on the training data output. (Rodriguez Page 103 “Once optimum design parameters were determined, the confirmation stage was performed to determine the final optimum values, highlighted in table 7. After the best ANN topology was determined a final training and testing was made to validate the data obtained with the ANN designed. At final ANN validation and using the designed computational tool, correlation and Chi square statistical tests were carried out”)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claims to modify the high-level machine learning model descriptions and methods taught in Wang by the specific machine learning descriptions and methods taught in Rodriguez, because the person of ordinary skill in the art would be motivated to find particulars about machine learning model descriptions and methods the generic description is lacking in Wang from the optimum settings of ANN parameters for achieving a network with the minimum error. (Wang [0034] “In some example implementations, some of the data of the oil historical samples and the gas historical samples may be used to validate the oil-type machine learning algorithm and the gas-type machine learning algorithm. For example, of a dataset of 1,800 samples that are separated into oil samples and gas samples, eighty percent (80%) of the grouped samples can be used to train the respective machine learning algorithms, and the remaining twenty percent (20%) of the grouped samples can be used to validate the respective machine learning algorithms.”; Rodriguez Page 84, First Paragraph “The robust design methodology, proposed by Taguchi, is one of the appropriate methods for achieving this goal. [16, 20, 21] Robust design is a statistical technique widely used to study the relationship between factors affecting the outputs of the process. It can be used to systematically identify the optimum setting of factors to obtain the desired output. In this work, it was used to find the optimum setting of ANNs parameters in order to achieve minimum error network.”)
Claim 9
Regarding claim 9, Wang in view of Rodriguez teaeches:
wherein the training the artificial neural network model includes optimization of the artificial neural network. (Rodriguez Page 84, First Paragraph “The robust design methodology, proposed by Taguchi, is one of the appropriate methods for achieving this goal. [16, 20, 21] Robust design is a statistical technique widely used to study the relationship between factors affecting the outputs of the process. It can be used to systematically identify the optimum setting of factors to obtain the desired output. In this work, it was used to find the optimum setting of ANNs parameters in order to achieve minimum error network.” Page 89, Second Paragraph Under The Bullets “The outputs errors are back propagated from the output layer toward all the neurons of the hidden layer that contribute directly with the output. However, the neurons of the hidden layer only receive a fraction of the signal from the whole error signal, based on the relative contribution that has contributed each neuron to the original output. This process is repeated for each layer until all neurons of the network have received an error signal which describes its relative contribution to the total error. Based on the perceived signal error the connection synaptic weights of each neuron are upgrade to make that the net converges toward a state that allows to classify correctly all the patterns of training.”)
Claim 10
Regarding claim 10, Wang in view of Rodriguez teaches:
further comprising collecting one of laboratory data, pressure volume temperature reports and equation of state models prior to collecting data related to the downhole fluid. (Wang [0075] “A thermodynamic fluid model may be used to generate a phase envelope. For example, an equation of state (EoS), such as a calibrated cubic EoS, may be used to generate a phase envelope. In some example implementations, an expected phase envelope can be generated using the expected composition, and additional phase envelopes can be generated using the one or more uncertainties. The additional phase envelopes can define a deviation region in which the actual phase envelope of the fluid, based on the actual one or more properties corresponding to the one or more second properties, is expected to reside based on, e.g., a standard deviation from what is expected.” [0077] “The following figures and description illustrate example implementations in the context of sampling a petroleum formation fluid, such as oil or gas. Generally speaking, an oil-type machine learning algorithm and a gas-type machine learning algorithm are trained based on historical samples of oil and gas, respectively, using normalized compositional component weight fractions and mole fractions obtained from fluid sampling. The machine learning algorithms are trained to have the compositional component weight fractions input and to output an expected hydrocarbons C6+ mole fraction. During fluid sampling, one of the oil-type and gas-type machine learning algorithms are selected based on the type of fluid being sampled, and the compositional component weight fractions are input to the selected machine learning algorithm.” Also, see the methods of FIGs. 6-7 in ordered combination – Build ML Algorithms at 608, Input [data] Into THE ML algorithms at 704)
Claim 11
Regarding claim 11, Wang in view of Rodriguez teaches:
wherein the processing the collected data occurs in a computing arrangement. (Wang [0058]-[0059] “The processing system 400 may execute example machine-readable instructions to implement at least a portion of one or more of the methods and/or processes described herein, and/or to implement a portion of one or more of the example downhole tools described herein. […] The processing system 400 may be or comprise, […] computers”)
Claim 12
Regarding claim 12, Wang in view of Rodriguez teaches:
wherein the collecting data related to a downhole fluid is performed with a downhole fluid analysis module. (Wang [0041] “The LWD modules 140 may include tools operable to measure formation parameters and/or fluid properties, such as resistivity, porosity, permeability, sonic velocity, optical density (OD), pressure, temperature, and/or other example properties. The MWD modules 142 may include tools operable to measure wellbore trajectory, borehole temperature, borehole pressure, and/or other example properties. The LWD modules 140 may each be housed in one of the drill collars 136, 138, and may each contain one or more logging tools and/or fluid sampling devices. The LWD modules 140 include capabilities for measuring, processing, and/or storing information, as well as for communicating with the MWD modules 142 and/or with surface equipment such as, for example, a logging and control unit 144. That is, the SWD tools (e.g., LWD modules 140 and MWD modules 142) may be communicatively coupled to the logging and control unit 144 disposed at the wellsite surface 116. In other implementations, portions of the logging and control unit 144 may be integrated with downhole features.”)
Claim 13
Regarding claim 13, Wang in view of Rodriguez teaches:
wherein the artificial neural network has an input layer, a hidden layer and an output layer. (Rodriguez FIG. 7 (shown below) and Page 88, First Paragraph After The Bullets “Figure 7 shows an ANN with two hidden layers. The outputs of first hidden layer are the entrances of the second hidden layer. In this configuration, each layer have its own weight matrix W, the summing, a gain vector b, net inputs vector n, the transfer function and the output vector a.”)
PNG
media_image2.png
200
400
media_image2.png
Greyscale
Claim 14
Regarding claim 14, Wang in view of Rodriguez teaches:
wherein the training an artificial neural network model includes using weights for data input to the artificial neural network. (Rodriguez FIG. 7 (shown above) and Page 88, First Paragraph After The Bullets “Figure 7 shows an ANN with two hidden layers. The outputs of first hidden layer are the entrances of the second hidden layer. In this configuration, each layer have its own weight matrix W, the summing, a gain vector b, net inputs vector n, the transfer function and the output vector a.” Page 89, Second-Third Paragraphs Under The Bullet Points “The outputs errors are back propagated from the output layer toward all the neurons of the hidden layer that contribute directly with the output. However, the neurons of the hidden layer only receive a fraction of the signal from the whole error signal, based on the relative contribution that has contributed each neuron to the original output.”)
Claim 15
Regarding claim 15, Wang in view of Rodriguez teaches:
wherein the artificial neural network has an input layer, at least two hidden layers and an output layer. (Rodriguez FIG. 7 (shown below) and Page 88, First Paragraph After The Bullets “Figure 7 shows an ANN with two hidden layers. The outputs of first hidden layer are the entrances of the second hidden layer. In this configuration, each layer have its own weight matrix W, the summing, a gain vector b, net inputs vector n, the transfer function and the output vector a.”)
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
NPL: “Computer Vision Metrics” by Krig (Teaches common ANNs used in computer vision)
NPL: “Introduction to Deep Learning” by Skansi (Teaches common deep learning models)
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JAY MICHAEL WHITE whose telephone number is (571) 272-7073. The examiner can normally be reached Mon-Fri 11:00-7:00 EST.
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, Ryan Pitaro can be reached at (571) 272-4071. 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.
/J.M.W./Examiner, Art Unit 2188
/RYAN F PITARO/Supervisory Patent Examiner, Art Unit 2188
Prosecution Insights