DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of Claims
The following is a non-final, first office action in response to the communication filed on 01/31/2023. Claims 1—20 are currently pending.
Information Disclosure Statement
Information Disclosure Statement received 01/31/2023, 04/23/2025, 09/18/2025, and 03/24/2026 has been reviewed and considered.
Claim Objections
Claims 1, 10, and 19 objected to because of the following informalities:
Claim 1 recites limitations including, but not limited to:
“obtaining reconciled physical parameters at each of a plurality of locations within a subsurface” (emphasis provided by Examiner);
“training at least one machine learning network to classify the reconciled physical parameters into a rock type based, at least in part, on the reconciled physical parameters” (emphasis provided by Examiner); and
“classifying the reconciled physical parameters into the rock type with the at least one machine learning network” (emphasis provided by Examiner).
Due to the phrasing of the claim as emphasized in the foregoing citations, the dataset provided to the algorithm to train the model (e.g., reconciled physical parameters) appears to be the same dataset provided to the model to generate the rock-type predictions (e.g., classifying). Generally, machine learning models which are used generate classifications (e.g., not LLMs) are trained using a first subset of values for a given set of features (e.g., training data) to generate the model. Subsequently, the generated model is provided with a second subset of values for the given set of features in order to generate the classifications. Stated another way, the specific subset of data used to train the model typically does not typically overlap with the data to which the model is ultimately applied. Given that the training step and the classifying step are listed as two distinct and separate steps, it is understood that the classification is not merely a biproduct of training the model. However, if the classification is merely generated from the same data on which the model is trained, then the claims should be amended to reflect that.
In view of this understanding and as best understood by the Examiner, limitation two (2) and three (3), as identified above, would likely benefit from an amendment which delineates the portion of the data on which the model is trained from the portion of the data to which the model is applied/deployed. For example, the limitation could be amended to state:
“training at least one machine learning network to classify the reconciled physical parameters into a rock type based, at least in part, on a first portion of the reconciled physical parameters”; and
“classifying a second portion of the reconciled physical parameters into the rock type with the at least one machine learning network.”
The foregoing is merely provided as an example and other options for how to delineate the requested datatype differentiation are available to Applicant. For example, para. [0045]—[0048] of the instant application discuss a training data set and a testing data set which may be another avenue for delineating the datasets. For the purposes of examination, the dataset used to train the model and the dataset to which the model is applied, are understood to be distinct datasets which contain the same feature/data types (e.g., as generically “defined” by the data types included in the reconciled physical parameters).
Claims 10 and 19 are objected to for substantially similar reasons as those recited above with respect to claim 1. Specifically, claims 10 and 19 should be amended to delineate the datasets of the reconciled physical parameters with which the model is trained and separately to which the model is applied. As with claim 1, for the purposes of examination with respect to claims 10 and 19, the dataset used to train the model and the dataset to which the model is applied, are understood to be distinct datasets which contain the same feature/data types (e.g., as generically “defined” by the data types included in the reconciled physical parameters).
Appropriate correction is required.
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 5—7 and 14—17 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 applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 5 states “wherein the training further comprises incorporating expert information,” where the term “expert” in the phrase “expert information” is a relative term which renders the claim indefinite. The metes and bounds of “expert,” and therefore the phrase “expert information” is not defined by the claim. Additionally, the Specification does not provide for a specific, required definition of the term such that one of ordinary skill would be reasonably apprised of the scope of the term. Accordingly the term and therefore the claim are rendered indefinite. For the purposes of examination, “expert information,” is understood to be dataset and information, including the physical parameters, which are gathered by a professional service provider.
Claims 6 and 7 depend from claim 5 and are therefore rendered indefinite and rejected under 35 U.S.C. 112(b) for depending from a rejected base claim.
Claim 14 states “wherein the training further comprises incorporating expert information,” where the term “expert” in the phrase “expert information” is a relative term which renders the claim indefinite. The metes and bounds of “expert,” and therefore the phrase “expert information” is not defined by the claim. Additionally, the Specification does not provide for a specific, required definition of the term such that one of ordinary skill would be reasonably apprised of the scope of the term. Accordingly the term and therefore the claim are rendered indefinite. For the purposes of examination, “expert information,” is understood to be dataset and information, including the physical parameters, which are gathered by a professional service provider.
Claims 15 and 16 depend from claim 14 and are therefore rendered indefinite and rejected under 35 U.S.C. 112(b) for depending from a rejected base 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—20 are rejected under 35 U.S.C. 101 because the claimed is directed to an abstract idea without significantly more.
Step 1 of the USPTO’s eligibility analysis entails considering whether the claimed subject matter falls within the four statutory categories of patentable subject matter identified by 35 U.S.C. 101: Process, machine, manufacture, or composition of matter.
Claims 1, 10, and 19 are directed to a method (process), a system (machine or manufacture), and a system (machine or manufacture), respectively. As such, the claims are directed to statutory categories of invention.
If the claim recites a statutory category of invention, the claim requires further analysis in Step 2A. Step 2A of the 2019 Revised Patent SUBJECT Matter Eligibility Guidance is a two-prong inquiry. In Prong One, examiners evaluate whether the claim recites a judicial exception
Claim 1 recites abstract limitations including:
“classifying the reconciled physical parameters into the rock type with the at least one machine learning network” (e.g., a mental process and/or mathematical concept); and
“interpreting the rock type to form a subsurface geology model and inform a geosteering decision” (e.g., a mental process and/or mathematical concept).
Claim 10 recites abstract limitations including:
“classifying the reconciled physical parameters into the rock type with the at least one machine learning network” (e.g., a mental process and/or mathematical concept); and
“interpreting the rock type to form a subsurface geology model and inform a geosteering decision” (e.g., a mental process and/or mathematical concept).
Claim 19 recites abstract limitations including:
“classify the reconciled physical parameters into the rock type with the at least one machine learning network” (e.g., a mental process and/or mathematical concept); and
“interpret the rock type to form a subsurface geology model” (e.g., a mental process and/or mathematical concept).
Under the broadest reasonable interpretation, the above identified limitations cover abstract ideas directed to mental processes, mathematical concepts, and/or combinations thereof. For example, the act of making an interpretation constitutes mental processes insofar as a human mind is capable of making an interpretation. In some scenarios, mental processes, such a making an interpretation may benefit from the utilization of a mathematical concept; however in either scenario, the limitation is directed to an abstract idea.
Limitations directed to utilizing machine learning models are equivalent to limitations directed to using mathematical models and are therefore abstract ideas. Moreover, while training a machine learning model constitutes an additional element, using the generated machine learning model is no different than using any other empirically-derived model and therefor constitutes an abstract idea. Accordingly, the above identified limitations are directed to abstract ideas such that claims 1, 10, and 19 recite abstract ideas.
If the claim recites a judicial exception (i.e., an abstract idea enumerated in Section I of the 2019 Revised Patent Subject Matter Eligibility Guidance, a law of nature, or a natural phenomenon), the claim requires further analysis in Prong Two. In Prong Two, examiners evaluate whether the claim recites additional elements that integrate the exception into a practical application of that exception.
Claim 1 recites additional elements including:
“obtaining reconciled physical parameters at each of a plurality of locations within a subsurface” (e.g., mere data gathering which constitutes extra-solution activity); and
“training at least one machine learning network to classify the reconciled physical parameters into a rock type based, at least in part, on the reconciled physical parameters” (e.g., generically recited training steps are equivalent to reciting “apply it”).
Claim 10 recites additional elements including:
“obtaining reconciled physical parameters at each of a plurality of locations within a subsurface” (e.g., mere data gathering which constitutes extra-solution activity); and
“training at least one machine learning network to classify the reconciled physical parameters into a rock type based, at least in part, on the reconciled physical parameters” (e.g., generically recited training steps are equivalent to reciting “apply it”).
Claim 19 recites additional elements including:
“ a computer” (e.g., recitation of generic computer components is equivalent to reciting “apply it”)
“obtain reconciled physical parameters at each of a plurality of locations within a subsurface” (e.g., mere data gathering which constitutes extra-solution activity);
“train at least one machine learning network to classify the reconciled physical parameters into a rock type based, at least in part, on the reconciled physical parameters” (e.g., generically recited training steps are equivalent to reciting “apply it”); and
“a geosteering system” (e.g., generically recited equipment indicative of a field of use).
The above identified limitations of claims 1, 10 and 19 constitute additional elements. However, for the reasons identified above, and discussed further below, the additional elements do not impose any meaningful limits on practicing the abstract idea. Accordingly, the above identified additional elements do not integrate the identified judicial exceptions into a practical application.
If the additional elements do not integrate the exception into a practical application, then the claim is directed to the recited judicial exception, and requires further analysis under Step 2B to determine whether they provide an inventive concept (i.e., whether the additional elements amount to significantly more than the exception itself).
As discussed above, claims 1, 10, and 19 recite the additional element of, or substantially similar to “obtaining reconciled physical parameters at each of a plurality of locations within a subsurface,” which is directed to mere data gathering and therefore constitutes insignificant extra-solution activity. For example, the MPEP states: “[b]elow are examples of activities that the courts have found to be insignificant extra-solution activity: Mere Data Gathering: i. Performing clinical tests on individuals to obtain input for an equation, In re Grams, 888 F.2d 835, 839-40; 12 USPQ2d 1824, 1827-28 (Fed. Cir. 1989); ii. Testing a system for a response, the response being used to determine system malfunction, In re Meyers, 688 F.2d 789, 794; 215 USPQ 193, 196-97 (CCPA 1982);… vi. Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also PerkinElmer, Inc. v. Intema Ltd., 496 Fed. App'x 65, 73, 105 USPQ2d 1960, 1966 (Fed. Cir. 2012) (assessing or measuring data derived from an ultrasound scan, to be used in a diagnosis).” (MPEP 2106.05(g)).
Claims 1, 10, and 19 recite the additional element of, or substantially similar to “training at least one machine learning network to classify the reconciled physical parameters into a rock type based, at least in part, on the reconciled physical parameters,” which is directed to training a machine learning model and therefore recites an additional element. However, the limitation is recited at a high level of generality where the generic recitation of a machine learning training step constitutes well-understood, routine, and conventional activity. For example, Published US Patent Application to Soto et al. (US 20180187498 A1), which is directed to detecting events during a drilling operation teaches “[d]ata analytics module 255 is designed to operate with an artificial intelligence software program and/or machine learning software program. Known techniques from data analysis are expected to be applicable here, including machine learning, cognitive systems, pattern recognition, cluster recognition (SVM clustering), genetic algorithms, heuristics, and big data analysis.” (Soto, para. [0058]). Accordingly, data analysis techniques including machine learning (e.g., which requires the generation of a machine learning model) are considered well-understood, routine, and conventional in the technical field of wellbore construction. As discussed in MPEP 2106.05(d), well-understood, routine, and conventional activity cannot provide for a practical application of the identified judicial exceptions. For example, the MPEP states “[i]f, however, the additional element (or combination of elements) is no more than well-understood, routine, conventional activities previously known to the industry, which is recited at a high level of generality, then this consideration does not favor eligibility.” (MPEP 2106.05(d)). Accordingly, claims 1, 10, and 19 do not recite any additional elements which integrate the identified abstract ideas into a practical application.
Claim 19 recites the additional element of “ a computer,” which is equivalent to a mere directive to apply the identified judicial exceptions. For example, the MPEP states: “ [w]hen determining whether a claim simply recites a judicial exception with the words ‘apply it’ (or an equivalent), such as mere instructions to implement an abstract idea on a computer, examiners may consider the following:… (2) Whether the claim invokes computers or other machinery merely as a tool to perform an existing process. Use of a computer or other machinery in its ordinary capacity for economic or other tasks (e.g., to receive, store, or transmit data) or simply adding a general purpose computer or computer components after the fact to an abstract idea (e.g., a fundamental economic practice or mathematical equation) does not integrate a judicial exception into a practical application or provide significantly more. See Affinity Labs v. DirecTV, 838 F.3d 1253, 1262, 120 USPQ2d 1201, 1207 (Fed. Cir. 2016) (cellular telephone); TLI Communications LLC v. AV Auto, LLC, 823 F.3d 607, 613, 118 USPQ2d 1744, 1748 (Fed. Cir. 2016) (computer server and telephone unit).” (MPEP 2106.05(f)). Accordingly, claim 19 does not recite any additional elements which integrate the identified abstract ideas into a practical application.
Claim 19 recites the additional element of “a geosteering system,” which is indicative of a field of use in which the identified judicial exception is applied. Limitations directed to a field of use cannot provide for a practical application of the judicial exception. For example, the MPEP states “limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not amount to significantly more than the exception itself, and cannot integrate a judicial exception into a practical application.” (MPEP 2106.05(h)). Accordingly, claim 19 does not recite any additional elements which integrate the identified abstract ideas into a practical application
Thus, even when viewed as an ordered combination, nothing in the claims add significantly more (i.e., an inventive concept) to the abstract idea.
Claims 2 and 11 recite the limitation “wherein obtaining reconciled physical parameters further comprises preprocessing the reconciled physical parameters to remove outliers,” which is directed to the abstract idea of data analysis and/or data processing. Specifically, the limitation is directed to either a mental process, a mathematical concept, and/or a combination thereof. Moreover, generically recited data pre-processing can be performed in a human mind with or without the benefit of a pen and paper and/or a mathematical concept. Accordingly claims 2 and 11 are further directed to an abstract idea and do not provide for additional elements which integrate the judicial exceptions of claims 1 and 10 into a practical application.
Claims 3, 4, 12, and 13 are directed to the specific algorithm used in the training step recited in claims 1 and 10. While the limitations are directed to an additional element, the additional element does not provide for a practical application of the identified judicial exception because the recited algorithm is well-known. For example, Published US Patent Application to Chen (US 20180137941 A1) which is directed to machine learning algorithms utilized in analyzing medical data states “[i]t is well known that the two best unsupervised learning methods are denoising Autoencoders (dAE) and Restricted Boltzmann Machine (BRM).” (Chen, para. [0101]). Accordingly, it is understood that Restricted Boltzmann Machines are well-known algorithms. As discussed in MPEP 2106.05(d), well-understood, routine, and conventional activity cannot provide for a practical application of the identified judicial exceptions. For example, the MPEP states “[i]f, however, the additional element (or combination of elements) is no more than well-understood, routine, conventional activities previously known to the industry, which is recited at a high level of generality, then this consideration does not favor eligibility.” (MPEP 2106.05(d)). Moreover, while training a machine learning model constitutes an additional element, merely reciting well-known algorithms and processes related to machine learning cannot provide for a practical application because the limitations are equivalent to a mere directive to apply the identified judicial exceptions (e.g., discussed in MPEP 2106.05(f)). As provided above, the training-related limitations of claims 3, 4, 12, and 13 are well-known. Accordingly, claims 3, 4, 12, and 13 do not recite any additional elements which integrate the identified abstract ideas into a practical application.
Regarding claims 5 and 14, and addressed above in the section directed to 35 U.S.C. 112(b), the limitation directed to “expert information” is understood to be data and/or information, including the physical parameters, which are gathered by a professional service provider. Limitations directed to restricting the data which may be used to perform an abstract idea (e.g., classifying… and interpreting…) are directed to court-identified insignificant extra-solution activity. For example, the MPEP states: “[b]elow are examples of activities that the courts have found to be insignificant extra-solution activity:… Selecting a particular data source or type of data to be manipulated: i. Limiting a database index to XML tags, Intellectual Ventures I LLC v. Erie Indem. Co., 850 F.3d at 1328-29, 121 USPQ2d at 1937; ii. Taking food orders from only table-based customers or drive-through customers, Ameranth, 842 F.3d at 1241-43, 120 USPQ2d at 1854-55; iii. Selecting information, based on types of information and availability of information in a power-grid environment, for collection, analysis and display, Electric Power Group, LLC v. Alstom S.A., 830 F.3d 1350, 1354-55, 119 USPQ2d 1739, 1742 (Fed. Cir. 2016).” (MPEP 2106.05(g)). Accordingly, claims 5 and 14 do not recite any additional elements which integrate the identified abstract ideas into a practical application.
The limitations of claims 6 and 15 function to further define the training step in a manner which is equivalent to reciting “apply it,” where the additional feature is well-known in the art of machine learning and statistical learning. For example, the limitation states “wherein incorporating the expert information comprises assigning values to nodes.” However, it is well-known that supplying training data to certain machine learning algorithms, including restricted Boltzmann machines and neural networks, will result in a weighting value being assigned to one or more nodes in the model because that is how the algorithms function to generate a model. For example, the above cited reference of Published US Patent Application to Chen (US 20180137941 A1) states that restricted Boltzmann machines are well-known further states “ [t]he first step of model optimization is to construct a primary deep learning frame and establish a data model comprising an input layer, at least a hidden layer and an output layer with respect to the data features of the medical treatment training data, wherein the input layer comprises a plurality of nodes… the output layer comprises a plurality of nodes… and each hidden layer comprises a plurality of nodes mapping with an output of the previous layer thereof.” (Chen, para. [0068]). As discussed in MPEP 2106.05(d), well-understood, routine, and conventional activity cannot provide for a practical application of the identified judicial exceptions. For example, the MPEP states “[i]f, however, the additional element (or combination of elements) is no more than well-understood, routine, conventional activities previously known to the industry, which is recited at a high level of generality, then this consideration does not favor eligibility.” (MPEP 2106.05(d)). Moreover, while training a machine learning model constitutes an additional element, merely reciting well-known algorithms and processes related to machine learning cannot provide for a practical application because the limitations are equivalent to a mere directive to apply the identified judicial exceptions (e.g., discussed in MPEP 2106.05(f)). As provided above, the training-related limitations of claims 6 and 15 are well-known where the algorithm is well-known and the algorithm functions by assigning values to nodes. Accordingly, claims 6 and 15 do not recite any additional elements which integrate the identified abstract ideas into a practical application.
The limitations of claims 7 and 16 function to further define the training step in a manner which is equivalent to reciting “apply it,” where the additional feature, including utilizing Shapley values (e.g., alternatively “SHaP plots”) to refine the model is well-known in the art of machine learning and statistical learning. For example, Published US Patent Application to Boguslawski (US 20230272792 A1) teaches “[t]he event explainer module 328 then notifies operators by providing the explanation to the control system 134 (e.g., SCADA system). In some embodiments, the event explainer module 328 uses SHAP (SHapley Additive exPlanations) to quantify the extent to which each parameter contributed to the event. SHAP is well known in the art as an efficient way to interpret ML model predictions through the use of Shapely values.” (Boguslawski, para. [0047]). As discussed in MPEP 2106.05(d), well-understood, routine, and conventional activity cannot provide for a practical application of the identified judicial exceptions. For example, the MPEP states “[i]f, however, the additional element (or combination of elements) is no more than well-understood, routine, conventional activities previously known to the industry, which is recited at a high level of generality, then this consideration does not favor eligibility.” (MPEP 2106.05(d)). Moreover, while training a machine learning model constitutes an additional element, merely reciting well-known algorithms and processes related to machine learning cannot provide for a practical application because the limitations are equivalent to a mere directive to apply the identified judicial exceptions (e.g., discussed in MPEP 2106.05(f)). As provided above, the training-related limitations of claims 7 and 16 are well-known where utilization of SHaP plots/Shapley values with respect to the contribution provided by each feature is well-known. Accordingly, claims 7 and 16 do not recite any additional elements which integrate the identified abstract ideas into a practical application.
Claims 8, 9, 17, and 18 are directed to the type of data which may populate the dataset for the reconciled physical parameters. Limitations directed to restricting the data which may be used to perform an abstract idea (e.g., classifying… and interpreting…) are directed to court-identified insignificant extra-solution activity. For example, the MPEP states: “[b]elow are examples of activities that the courts have found to be insignificant extra-solution activity:… Selecting a particular data source or type of data to be manipulated: i. Limiting a database index to XML tags, Intellectual Ventures I LLC v. Erie Indem. Co., 850 F.3d at 1328-29, 121 USPQ2d at 1937; ii. Taking food orders from only table-based customers or drive-through customers, Ameranth, 842 F.3d at 1241-43, 120 USPQ2d at 1854-55; iii. Selecting information, based on types of information and availability of information in a power-grid environment, for collection, analysis and display, Electric Power Group, LLC v. Alstom S.A., 830 F.3d 1350, 1354-55, 119 USPQ2d 1739, 1742 (Fed. Cir. 2016).” (MPEP 2106.05(g)). Accordingly, claims 8, 9, 17, and 18 do not recite any additional elements which integrate the identified abstract ideas into a practical application.
Claim 20 states the limitation “wherein the drill bit is guided according to an interpreted rock type,” which, at best, constitutes a mere directive to apply the judicial exception in a manner which does not provide for a practical application. With respect to limitations which constitutes mere directives to apply the exception (e.g., equivalent to “apply it”) the MPEP states: “[w]hen determining whether a claim simply recites a judicial exception with the words ‘apply it’ (or an equivalent), such as mere instructions to implement an abstract idea on a computer, examiners may consider the following: (1) Whether the claim recites only the idea of a solution or outcome i.e., the claim fails to recite details of how a solution to a problem is accomplished. The recitation of claim limitations that attempt to cover any solution to an identified problem with no restriction on how the result is accomplished and no description of the mechanism for accomplishing the result, does not integrate a judicial exception into a practical application or provide significantly more because this type of recitation is equivalent to the words "apply it". See Electric Power Group, LLC v. Alstom, S.A., 830 F.3d 1350, 1356, 119 USPQ2d 1739, 1743-44 (Fed. Cir. 2016); Intellectual Ventures I v. Symantec, 838 F.3d 1307, 1327, 120 USPQ2d 1353, 1366 (Fed. Cir. 2016); Internet Patents Corp. v. Active Network, Inc., 790 F.3d 1343, 1348, 115 USPQ2d 1414, 1417 (Fed. Cir. 2015). In contrast, claiming a particular solution to a problem or a particular way to achieve a desired outcome may integrate the judicial exception into a practical application or provide significantly more. See Electric Power, 830 F.3d at 1356, 119 USPQ2d at 1743.” (MPEP 2106.05(f)).
Examiner submits the limitation of claim 20 is merely directed to the idea of a solution or outcome and does not properly integrate the judicial exception into a practical application. Examples of limitations which do properly integrate the recited judicial exception into a practical application include the limitations of Diehr. For example, the MPEP states “[i]n contrast, the additional elements in Diamond v. Diehr as a whole provided eligibility and did not merely recite calculating a cure time using the Arrhenius equation ‘in a rubber molding process’. Instead, the claim in Diehr recited specific limitations such as monitoring the elapsed time since the mold was closed, constantly measuring the temperature in the mold cavity, repetitively calculating a cure time by inputting the measured temperature into the Arrhenius equation, and opening the press automatically when the calculated cure time and the elapsed time are equivalent. 450 U.S. at 179, 209 USPQ at 5, n. 5. These specific limitations act in concert to transform raw, uncured rubber into cured molded rubber. 450 U.S. at 177-78, 209 USPQ at 4.” (MPEP 2106.05(h)). Examiner notes the limitations of Diehr which integrated the abstract idea (e.g., calculations using the Arrhenius equation) into a practical application (e.g., opening the press when the calculated cure time and the elapsed time are equivalent) provide a more specific application which was directly tied to the outcome of the judicial exception than merely stating “operate the mold according to the Arrhenius equation.” Accordingly the limitations of claim 20 do not provide for a practical application of the judicial exception because the limitations are equivalent to a mere directive to apply the exception.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1—2, 5—6, 8—11, 14—15, and 17—20 is/are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Published US Patent Application to Walmsley (US 20240035366 A1).
Regarding claim 1, Walmsley discloses obtaining reconciled physical parameters at each of a plurality of locations within a subsurface (step 310 of method 300; para. [0038], “[i]n step 310, offset well data is obtained from at least one offset well. Offset wells are preferably chosen in the same vicinity of the target well and/or selected due to having similar formation characteristics.”; para. [0039], “[t]he offset well data can be from data logs corresponding to sensor measurements collected while drilling the offset well. The sensor measurements may include but are not limited to gamma-ray, resistivity, density, and porosity.”; para. [0040], “[t]he processing can include one or more of the different types of processing that is performed on the offset well data, such as filtering, smoothing, or other types of data processing that can be used to clean (e.g., remove noise)”)
training at least one machine learning network to classify the reconciled physical parameters (offset well data 310) into a rock type based, at least in part, on the reconciled physical parameters (para. [0041], “[w]ith offset well data, a facies cluster model can be trained before drilling of the target well begins and then updated when the target well data is received. The target well data can be received in batches or continuously streamed; both can be automatic.”; para. [0041], “[t]he facies cluster model provides facies classifications with respect to the subterranean formation.”)
classifying the reconciled physical parameters (target well data) into the rock type with the at least one machine learning network (para. [0041], “[g]enerating the facies cluster model includes categorizing the target well data using a machine learning model that is trained using the clustering process.” The machine learning model which classifies the target well data is the above described facies cluster model which is trained on the offset well data); and
interpreting the rock type to form a subsurface geology model and inform a geosteering decision (para. [0020], “[h]aving generated the facies cluster models with respect to depth, the facies cluster models can be moved to the well placement or geosteering software for representation within a 2D or 3D visualization environment and used for performing well operations, such as drilling.”; para. [0044], “[t]he facies clusters can be moved to well placement or geosteering software for representation within the 2D or 3D visualization environment as shown in FIGS. 4, 5, and 6 to aid well placement or as an input for net-to-gross or other petrophysical and geological parameter calculations.”).
Regarding claim 2, Walmsley discloses wherein obtaining reconciled physical parameters further comprises preprocessing the reconciled physical parameters to remove outliers (para. [0040], “[t]he processing can include one or more of the different types of processing that is performed on the offset well data, such as filtering, smoothing, or other types of data processing that can be used to clean (e.g., remove noise)”).
Regarding claim 5, Walmsley discloses wherein the training further comprises incorporating expert information (para. [0039], “[t]he offset well data can be from data logs corresponding to sensor measurements collected while drilling the offset well. The sensor measurements may include but are not limited to gamma-ray, resistivity, density, and porosity.” In accordance with the rejection set forth with repsect to claim 5 under 35 U.S.C. 112(b), “expert information,” includes well log data collected while drilling a hydrocarbon wellbore).
Regarding claim 6, Walmsley discloses wherein incorporating the expert information comprises assigning values to nodes (Walmsley discloses utilizing algorithms such as self-organizing maps (“SOMs”) in para. [0017] where SOMs are a type of artificial neural network where the model generated from such an algorithm inherently includes the algorithm assigning weights/values to various nodes. This is a necessary part of generating a model from an algorithm such as a self-organizing map where the weights assigned to the nodes are directly and inherently related to the model construction and structure. See para. [0019], “[t]he SOMs can be Kohonen type SOMs based on square, hexagonal or spherical/toroidal node arrangements.”).
Regarding claim 8, Walmsley discloses wherein the reconciled physical parameters are obtained from logging-while-drilling (LWD) data (para. [0039], “[t]he offset well data can be from data logs corresponding to sensor measurements collected while drilling the offset well. The sensor measurements may include but are not limited to gamma-ray, resistivity, density, and porosity.”; para. [0032], “[t]he target well data can be received in real-time during drilling of the target well. The target well data can be from real-time sensor measurements (e.g., survey data) from various downhole sensors, such as sensors of a MWD or LWD tool and/or directional sensors. The sensors can include, for example, at least one of gamma-ray sensors, resistivity sensors, density sensors, porosity sensors, drilling dynamic sensors, acoustic sensors, or nuclear magnetic resonance sensors. A combination of the different type of sensors can also be used.” Both the training data obtained from offset wells and the data obtained from the target well in real-time, which is subsequently used to populate the model, may be obtained from logging while drilling operations).
Regarding claim 9, Walmsley discloses wherein the LWD data comprises at least one selected from the group consisting of: neutron porosity data (see para. [0039] as cited below), borehole caliber data, nuclear magnetic resonance data (see para. [0032] as cited below), gamma ray data (see para. [0039] as cited below), weight on bit data, rate of penetration data, inclination data, measured depth data, true vertical depth data, bearing data, temperature data, and pressure data (para. [0039], “[t]he offset well data can be from data logs corresponding to sensor measurements collected while drilling the offset well. The sensor measurements may include but are not limited to gamma-ray, resistivity, density, and porosity.”; para. [0032], “[t]he target well data can be received in real-time during drilling of the target well. The target well data can be from real-time sensor measurements (e.g., survey data) from various downhole sensors, such as sensors of a MWD or LWD tool and/or directional sensors. The sensors can include, for example, at least one of gamma-ray sensors, resistivity sensors, density sensors, porosity sensors, drilling dynamic sensors, acoustic sensors, or nuclear magnetic resonance sensors. A combination of the different type of sensors can also be used.” Both the training data and the data used in real-time to populate the model may be obtained from logging while drilling operations).
Regarding claim 10, Walmsley discloses [a] non-transitory computer-readable memory comprising computer-executable instructions stored thereon that, when executed on a processor, cause the processor to perform the steps of (para. [0004], “the disclosure provides a computer program product having a series of operating instructions stored on a non-transitory computer readable medium that direct operation of one or more processors when initiated thereby to perform operations…”):
obtaining reconciled physical parameters at each of a plurality of locations within a subsurface (step 310 of method 300; para. [0038], “[i]n step 310, offset well data is obtained from at least one offset well. Offset wells are preferably chosen in the same vicinity of the target well and/or selected due to having similar formation characteristics.”; para. [0039], “[t]he offset well data can be from data logs corresponding to sensor measurements collected while drilling the offset well. The sensor measurements may include but are not limited to gamma-ray, resistivity, density, and porosity.”; para. [0040], “[t]he processing can include one or more of the different types of processing that is performed on the offset well data, such as filtering, smoothing, or other types of data processing that can be used to clean (e.g., remove noise)”)
training at least one machine learning network to classify the reconciled physical parameters (offset well data 310) into a rock type based, at least in part, on the reconciled physical parameters (para. [0041], “[w]ith offset well data, a facies cluster model can be trained before drilling of the target well begins and then updated when the target well data is received. The target well data can be received in batches or continuously streamed; both can be automatic.”; para. [0041], “[t]he facies cluster model provides facies classifications with respect to the subterranean formation.”)
classifying the reconciled physical parameters (target well data) into the rock type with the at least one machine learning network (para. [0041], “[g]enerating the facies cluster model includes categorizing the target well data using a machine learning model that is trained using the clustering process.” The machine learning model which classifies the target well data is the above described facies cluster model which is trained on the offset well data); and
interpreting the rock type to form a subsurface geology model and inform a geosteering decision (para. [0020], “[h]aving generated the facies cluster models with respect to depth, the facies cluster models can be moved to the well placement or geosteering software for representation within a 2D or 3D visualization environment and used for performing well operations, such as drilling.”; para. [0044], “[t]he facies clusters can be moved to well placement or geosteering software for representation within the 2D or 3D visualization environment as shown in FIGS. 4, 5, and 6 to aid well placement or as an input for net-to-gross or other petrophysical and geological parameter calculations.”).
Regarding claim 11, Walmsley discloses wherein obtaining reconciled physical parameters further comprises preprocessing the reconciled physical parameters to remove outliers (para. [0040], “[t]he processing can include one or more of the different types of processing that is performed on the offset well data, such as filtering, smoothing, or other types of data processing that can be used to clean (e.g., remove noise)”).
Regarding claim 14, Walmsley discloses wherein the training further comprises incorporating expert information (para. [0039], “[t]he offset well data can be from data logs corresponding to sensor measurements collected while drilling the offset well. The sensor measurements may include but are not limited to gamma-ray, resistivity, density, and porosity.” In accordance with the rejection set forth with repsect to claim 5 under 35 U.S.C. 112(b), “expert information,” includes well log data collected while drilling a hydrocarbon wellbore).
Regarding claim 15, Walmsley discloses wherein incorporating the expert information comprises assigning values to nodes (Walmsley discloses utilizing algorithms such as self-organizing maps (“SOMs”) in para. [0017] where SOMs are a type of artificial neural network where the model generated from such an algorithm inherently includes the algorithm assigning weights/values to various nodes. This is a necessary part of generating a model from an algorithm such as a self-organizing map where the weights assigned to the nodes are directly and inherently related to the model construction and structure. See para. [0019], “[t]he SOMs can be Kohonen type SOMs based on square, hexagonal or spherical/toroidal node arrangements.”).
Regarding claim 17, Walmsley discloses wherein the reconciled physical parameters are determined from physical parameters that are estimated from at least one selected from the group consisting of: logging while drilling (LWD) data, seismic data, and electromagnetic data (para. [0039], “[t]he offset well data can be from data logs corresponding to sensor measurements collected while drilling the offset well. The sensor measurements may include but are not limited to gamma-ray, resistivity, density, and porosity.”; para. [0032], “[t]he target well data can be received in real-time during drilling of the target well. The target well data can be from real-time sensor measurements (e.g., survey data) from various downhole sensors, such as sensors of a MWD or LWD tool and/or directional sensors. The sensors can include, for example, at least one of gamma-ray sensors, resistivity sensors, density sensors, porosity sensors, drilling dynamic sensors, acoustic sensors, or nuclear magnetic resonance sensors. A combination of the different type of sensors can also be used.” Both the training data obtained from offset wells and the data obtained from the target well in real-time, which is subsequently used to populate the model, may be obtained from logging while drilling operations).
Regarding claim 18, Walmsley discloses wherein the LWD data comprises at least one selected from the group consisting of: neutron porosity data (see para. [0039] as cited below), borehole caliber data, nuclear magnetic resonance data (see para. [0032] as cited below), gamma ray data (see para. [0039] as cited below), weight on bit data, rate of penetration data, inclination data, measured depth data, true vertical depth data, bearing data, temperature data, and pressure data (para. [0039], “[t]he offset well data can be from data logs corresponding to sensor measurements collected while drilling the offset well. The sensor measurements may include but are not limited to gamma-ray, resistivity, density, and porosity.”; para. [0032], “[t]he target well data can be received in real-time during drilling of the target well. The target well data can be from real-time sensor measurements (e.g., survey data) from various downhole sensors, such as sensors of a MWD or LWD tool and/or directional sensors. The sensors can include, for example, at least one of gamma-ray sensors, resistivity sensors, density sensors, porosity sensors, drilling dynamic sensors, acoustic sensors, or nuclear magnetic resonance sensors. A combination of the different type of sensors can also be used.” Both the training data and the data used in real-time to populate the model may be obtained from logging while drilling operations).
Regarding claim 19, Walmsley discloses a computer (processor 212), configured to:
obtain reconciled physical parameters at each of a plurality of locations within a subsurface (step 310 of method 300; para. [0038], “[i]n step 310, offset well data is obtained from at least one offset well. Offset wells are preferably chosen in the same vicinity of the target well and/or selected due to having similar formation characteristics.”; para. [0039], “[t]he offset well data can be from data logs corresponding to sensor measurements collected while drilling the offset well. The sensor measurements may include but are not limited to gamma-ray, resistivity, density, and porosity.”; para. [0040], “[t]he processing can include one or more of the different types of processing that is performed on the offset well data, such as filtering, smoothing, or other types of data processing that can be used to clean (e.g., remove noise)”),
train at least one machine learning network to classify the reconciled physical parameters (offset well data 310) into a rock type based, at least in part, on the reconciled physical parameters (para. [0041], “[w]ith offset well data, a facies cluster model can be trained before drilling of the target well begins and then updated when the target well data is received. The target well data can be received in batches or continuously streamed; both can be automatic.”; para. [0041], “[t]he facies cluster model provides facies classifications with respect to the subterranean formation.”),
classify the reconciled physical parameters into the rock type with the at least one machine learning network (para. [0041], “[g]enerating the facies cluster model includes categorizing the target well data using a machine learning model that is trained using the clustering process.” The machine learning model which classifies the target well data is the above described facies cluster model which is trained on the offset well data), and
interpret the rock type to form a subsurface geology model (para. [0020], “[h]aving generated the facies cluster models with respect to depth, the facies cluster models can be moved to the well placement or geosteering software for representation within a 2D or 3D visualization environment and used for performing well operations, such as drilling.”; para. [0044], “[t]he facies clusters can be moved to well placement or geosteering software for representation within the 2D or 3D visualization environment as shown in FIGS. 4, 5, and 6 to aid well placement or as an input for net-to-gross or other petrophysical and geological parameter calculations.”); and
a geosteering system (elements 120—126 and 128 in FIG. 1 including drill bit 124 and bottom hole assembly 120), configured to guide a drill bit through the subsurface (elements 120—126 and 128 in FIG. 1 are configured to directionally drill a well where the generated facies model as depicted in FIG. 4—6 inform geosteering operations).
Regarding claim 20, Walmsley discloses wherein the drill bit is guided according to an interpreted rock type (para. [0020], “[h]aving generated the facies cluster models with respect to depth, the facies cluster models can be moved to the well placement or geosteering software for representation within a 2D or 3D visualization environment and used for performing well operations, such as drilling. Benefits of the disclosed data clustering approach for HAHZ target well data can include: identification of major geometrical tool effects and formation bed boundaries; identification of unique geological units, and; automated well log correlation.” It should be implicitly understood that, in an application directed to geosteering and facies interpretation, the purpose of providing the facies interpretation as depicted in FIGs. 4—6 as combined with the drilling system of FIG. 1, is to geosteer the well according to the facies model).
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.
Claim(s) 3, 4, 12, and 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Published US Patent Application to Walmsley (US 20240035366 A1) as applied to claim 1 above, and further in view of Published US Patent Application to Chen (US 20180137941 A1).
Walmsley discloses utilizing an unsupervised machine learning algorithm to generate a machine learning model capable of facies classification (e.g., see para. [0017]—[0019]) including “Self-Organizing Maps (SOMs), Generative adversarial networks (GANS), or K-nearest neighbors.” (para. [0017]). However, Walmsley does not disclose utilizing a deep belief network comprising a restricted Boltzmann machine as required by claims 3 and 4. Chen, which is in the same field of endeavor as the instant application insofar as it is directed to generating machine learning models using unsupervised algorithms and deep learning structures, teaches the deficient limitation. For example, Chen teaches “[i]t is well known that the two best unsupervised learning methods are denoising Autoencoders (dAE) and Restricted Boltzmann Machine (BRM).” (Chen, para. [0101]). Chen further teaches “[i]n order to reduce the generation of overfitting as far as possible, the two types of unsupervised learning methods, the RBM and DAE, are both utilized in our deep learning and model construction.” (Chen, para. [0105]). Finally, Chen teaches “[d]eep learning technology regarding as a revolutionary technology in the field of artificial intelligence…” (para. [0047]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have replaced the unsupervised machine learning algorithms of Walmsley with the unsupervised machine learning algorithm stack of Chen. Both unsupervised machine learning algorithms function to generate a machine learning model using relevant data where the functions of both algorithms were known in the art. The substitution would generate the predictable result of a machine learning model trained from data gathered while drilling. Furthermore, Chen provides motivation for the replacement in stating that a restricted Boltzmann machine is well known to be one of the best unsupervised machine learning models.
Walmsley discloses utilizing an unsupervised machine learning algorithm to generate a machine learning model capable of facies classification (e.g., see para. [0017]—[0019]) including “Self-Organizing Maps (SOMs), Generative adversarial networks (GANS), or K-nearest neighbors.” (para. [0017]). However, Walmsley does not disclose utilizing a deep belief network comprising a restricted Boltzmann machine as required by claims 12 and 13. Chen, which is in the same field of endeavor as the instant application insofar as it is directed to generating machine learning models using unsupervised algorithms and deep learning structures, teaches the deficient limitation. For example, Chen teaches “[i]t is well known that the two best unsupervised learning methods are denoising Autoencoders (dAE) and Restricted Boltzmann Machine (BRM).” (Chen, para. [0101]). Chen further teaches “[i]n order to reduce the generation of overfitting as far as possible, the two types of unsupervised learning methods, the RBM and DAE, are both utilized in our deep learning and model construction.” (Chen, para. [0105]). Finally, Chen teaches “[d]eep learning technology regarding as a revolutionary technology in the field of artificial intelligence…” (para. [0047]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have replaced the unsupervised machine learning algorithms of Walmsley with the unsupervised machine learning algorithm stack of Chen. Both unsupervised machine learning algorithms function to generate a machine learning model using relevant data where the functions of both algorithms were known in the art. The substitution would generate the predictable result of a machine learning model trained from data gathered while drilling. Furthermore, Chen provides motivation for the replacement in stating that a restricted Boltzmann machine is well known to be one of the best unsupervised machine learning models.
Claim(s) 7 and 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Published US Patent Application to Walmsley (US 20240035366 A1) as applied to claim 1 above, and further in view of Published US Patent Application to Boguslawski et al. (US 20180137941 A1).
Walmsley may not disclose the limitations of claim 7; however Boguslawski, which is in the same field of endeavor as the instant application insofar as it is directed to generating machine learning model for use with hydrocarbon operations, teaches the deficient limitation. For example, Boguslawski teaches “[i]n some embodiments, the event explainer module 328 uses SHAP (SHapley Additive exPlanations) to quantify the extent to which each parameter contributed to the event. SHAP is well known in the art as an efficient way to interpret ML model predictions through the use of Shapely values. Shapley values are a way to attribute how much each feature played a role in a model’s prediction. SHAP provides a more efficient way to derive Shapley values compared to the original approach developed by Lloyd Shapley.” (para. [0047]). Boguslawski further teaches “In some embodiments, the event explainer training includes using the training data set 512 (or selected portion thereof) to train the one or more ML models to generate SHAP values at 614. As mentioned, SHAP is well known in the art as an efficient way to interpret ML model predictions through the use of Shapely values.” (para. [0055]). Examiner notes that the nodal weights generated by training a model using a self-organizing map algorithm are directly related to how impactful each node and associated feature are in generating the final output. Accordingly the node weights/values have an inseparable mathematical relationship with the SHaP values/Shapley values which are output by the training dataset.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have added the SHaP values of Boguslawski to the model building and analysis process of Walmsley. While the data they are applied to may be different, the SHaP values would function the same as combined in Walmsley as executed separately in Boguslawski. The combination would generate the predictable result of result of a model/dataset interrogation feature (SHaP values) informative of the weighting value of various features in the model.
Walmsley may not disclose the limitations of claim 16; however Boguslawski, which is in the same field of endeavor as the instant application insofar as it is directed to generating machine learning model for use with hydrocarbon operations, teaches the deficient limitation. For example, Boguslawski teaches “[i]n some embodiments, the event explainer module 328 uses SHAP (SHapley Additive exPlanations) to quantify the extent to which each parameter contributed to the event. SHAP is well known in the art as an efficient way to interpret ML model predictions through the use of Shapely values. Shapley values are a way to attribute how much each feature played a role in a model’s prediction. SHAP provides a more efficient way to derive Shapley values compared to the original approach developed by Lloyd Shapley.” (para. [0047]). Boguslawski further teaches “In some embodiments, the event explainer training includes using the training data set 512 (or selected portion thereof) to train the one or more ML models to generate SHAP values at 614. As mentioned, SHAP is well known in the art as an efficient way to interpret ML model predictions through the use of Shapely values.” (para. [0055]). Examiner notes that the nodal weights generated by training a model using a self-organizing map algorithm are directly related to how impactful each node and associated feature are in generating the final output. Accordingly the node weights/values have an inseparable mathematical relationship with the SHaP values/Shapley values which are output by the training dataset.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have added the SHaP values of Boguslawski to the model building and analysis process of Walmsley. While the data they are applied to may be different, the SHaP values would function the same as combined in Walmsley as executed separately in Boguslawski. The combination would generate the predictable result of result of a model/dataset interrogation feature (SHaP values) informative of the weighting value of various features in the model.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Published US Patent Application to Bize-Forest et al. (US 2019036316 A1) which is directed to machine learning applications for sedimentary facies identification and prediction based on well log data including logging while drilling data;
Published US Patent Application to Hu e al. (US 20230140905 A1) which is directed to utilizing machine learning in the oil and gas industry teaches “the models may be validated with actual production data with satisfactory prediction accuracy and then interpreted by a set of model-agnostic techniques, such as individual conditional expectation (ICE), partial dependency plot (PDP), local surrogate (LIME) and SHapley additive explanations (SHAP). These model-agnostic methods not only help to interpret complex machine-learning models, but also provide sensitivity analysis on production drivers facilitating completion optimization.” (Hu, para. [0019]);
Published US Patent Application to Ramey et al. (US 20220083873 A1) which is directed to utilizing machine learning models for oil and gas applications teaches “[m]odels with numerous input features, such as the models described herein, often suffer from a lack of explainability. In particular, when the model produces an output, it can be difficult to determine exactly which input features contributed how much to this output. In many practical scenarios, even if there are dozens of input features, a relatively small number of these (e.g., 5-15%) contribute to most of the variation in output values. Given the overall complexity of machine-learning models such as the decision trees described herein, it is beneficial to be able to identify the impact of each input feature in a fashion that can be understood by a non-technical audience.” (para. [0205]). Ramey et al further teaches “[o]ne method of doing so is through the use of Shapley data. In short, given a particular output value of a model for a particular set of input feature values, as well as the average of this output value across all input feature values, Shapley data assigns a contribution to each of the input features. This contribution quantifies how much each input feature contributed to the difference between the particular output value and the average output value. Shapley data also capture possible inter-dependencies between input features such that the Shapley data is independent of the order in which the input features are applied (should the model be sensitive to such orderings).” (para. [0206]);
Published US Patent Application to Wu et al. (US 20230313616 A1) which teaches use of a clustering machine learning algorithm to identify rock characteristics and structures using electromagnetic resistivity data. The generated model is used for geosteering purposes;
Issued US Patent Application to Utt (US 6490527 B1) which teaches a method of characterizing rock strata by providing drilling features including sensor data to a neural network; and
Published US Patent Application to Gkortsas et al. (US 20220146705 A1) which teaches a method of automatically classifying lithographic facies from well logs using a Gaussian mixture model.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to URSULA NORRIS whose telephone number is (703)756-4731. The examiner can normally be reached Monday to Friday, 7 AM to 4 PM.
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, TARA SCHIMPF can be reached at 571-270-7741. 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.
/U.L.N./Examiner, Art Unit 3676
/TARA SCHIMPF/Supervisory Patent Examiner, Art Unit 3676
Prosecution Insights