DETAILED ACTION
This Office Action is in response to the amendments filed on 07/01/2025.
Claims 1-2, 5-6, 8, 10, 12, 15-16, 18, and 20 currently amended.
Claims 1-20 currently pending in this application and have been examined.
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 .
Response to Arguments
In reference to Applicant’s arguments on page(s) 7-11 regarding rejections made under 35 U.S.C. 101:
Claims 1-20 are rejected under 35 U.S.C. § 101 because they are directed to an abstract idea without significantly more. The Office asserts that independent claim 1 is directed to the alleged abstract idea of mental processes. Applicant respectfully disagrees with this characterization but has amended claim 1 to advance prosecution.
For example, amended claim 1 recites technical steps, including "based on, at least in part, the first set of geo-exploration data including the spectroscopic IR data, training a set of deep learning models, each deep learning model comprising multiple layers and configured to predict one or more geological formation properties," and "predicting, using the set of trained deep learning models, the one or more geological formation properties based on, at least in part, the second set of geo-exploration data." The recited features require computing systems to train and deploy a set of deep learning (DL) models to predict geological formation properties. Specifically, amended claim 1 describes training the set of DL models on the first set of geo-exploration data, each DL model comprising multiple layers. This feature involves iterative computations of complex input data, including spectroscopic IR data obtained from core samples, and the adjustment of internal parameters, such as network weights, based on the input data. See paragraph [0059] of the Specification.
This feature cannot be practically performed in the mind.
Amended claim 1 further describes predicting one or more geological formation properties using the set of trained DL models. This feature inherently requires computing hardware to deploy the trained DL models to process the geo-exploration data, the DL models use weights learned during training to generate the predicted geological formation property. This feature cannot be practically performed in the human mind.
Accordingly, the features recited by amended claim 1 cannot be practically performed in the human mind. Therefore, the claimed subject matter does not involve a patent ineligible abstract idea and thus does not invoke the abstract exception under Alice.
However, Applicant respectfully submits that, even if amended claim 1 is directed to an abstract idea (which is not conceded), the features of amended claim 1 include patentable subject matter because they integrate a judicial exception into a practical application, as required under Step 2A, Prong Two under the MPEP.
The Office asserts that the additional element of "accessing a first set of geo-exploration data from a first drilling site, wherein the first set of geo-exploration data includes spectroscopic infra-red (IR) data, wherein at least portions of the first set of geo-exploration data are based on measurements of core samples taken from the first drilling site" is an "extra-solution activity of gathering data i.e. pre-solution activity of gathering data for use in the claimed process" and "merely indicates a field of use or technological environment in which the judicial exception is performed (spectroscopy)." The applicant respectfully disagrees, as the cited limitation recites a feature that is integral to the functionality of the method described by amended claim 1.
Accordingly, this limitation is not merely an extra-solution activity or a reference to a technological environment. Rather, it recites a feature that is integral to the operation of the method described in amended claim 1.
Furthermore, the features recited in amended claim 1 go beyond a recitation of "mere instructions to apply the exception using a generic computer component," as alleged by the Office. Instead, the features of amended claim 1 are directed to a practical application and recite a non-conventional approach that "assist[s] the exploration, development and production of energy resources and mineral deposits." As described in paragraph [0038] of the Specification, "traditional tests ... may be destructive and/or require significant time or capital investment, and may lead to sparse characterization of some physical properties." The claimed method addresses this technical challenge through specific features that provide an improvement in the technical field of subsurface geological analysis. This includes "based on, at least in part, the first set of geo-exploration data including the spectroscopic IR data, training a set of deep learning models, each deep learning model comprising multiple layers
and configured to predict one or more geological formation properties," and "predicting, using the set of trained deep learning models, the one or more geological formation properties based on, at least in part, the second set of geo-exploration data," as recited by amended claim 1.
As described in paragraph [0038] of the Specification, the claimed method "incorporate[s] a machine learning (ML) algorithm and a ML model to predict, based on the spectroscopic IR reflectance data taken on site, the rock types, the geomechanical properties," and can perform "geochemical analysis and provide a molecular characterization of rocks and fluids properties." Accordingly, the claimed method enables a set of DL models trained on geo- exploration data including spectroscopic IR data to predict a plurality of geological formation properties, thereby avoiding destructive testing, and reducing time and costs typically involved in geological analysis and improving the technical field of subsurface geological analysis.
Thus, the features of amended claim 1 provide various improvements that render the claim patent eligible, i.e., because the claim recites features that provide an improvement in the functioning of the claimed computer itself, as well as another field of technology. Independent claim 11 differs in scope relative to amended claim 1 but have been amended to include features similar to those discussed above with reference to amended claim 1. Therefore, reconsideration and withdrawal of the rejection of claim 11 and their respective dependent claims are respectfully requested for at least the reasons provided above with reference to claim 1.
Examiner’s response:
Applicant’s arguments have been fully considered but are found to be not persuasive.
Applicant argues that the actions presented in the independent claims require a neural network to be performed. Actions of making predictions based on acquired data do not need neural networks to be performed and are considered mental processes as making predictions is something that can be performed in the human mind. The inclusion of training deep learning models on a certain type of data in order to make predictions based on that data does not preclude the action of making predictions to be performed in the human mind. While the human mind cannot train a deep learning model, that limitation is simply an additional element directed to using a generic computer component to perform the action of the limitation.
Applicant argues that the present claims offer an improvement over the existing technology since they employ the use of deep learning models for geological property prediction. Again, the inventive concept of the claims is to make predictions about the geological properties using spectroscopy data. Simply using deep learning models to make these predictions is directed to using a generic computer component to apply the judicial exception.
In light of the amendments made on the claims, the rejections made under 35 U.S.C. 101 are maintained and updated below.
In reference to Applicant’s arguments on page(s) regarding rejections made under 35 U.S.C. 102 and 103:
Claims 1, 3, 4, 6, 11, 13, 14, and 16 are rejected under 35 U.S.C. § 102(a)(1) and 102(a)(2) as being anticipated by U.S. Publication No. 2024/0077642 to Fuchey et al ("Fuchey").
The Office has not shown that the combination of features of amended claim 1 is described by the cited reference.
Specifically, Fuchey does not teach the limitation of "based on, at least in part, the first set of geo-exploration data including the spectroscopic IR data, training a set of deep learning models, each deep learning model comprising multiple layers and configured to predict one or more geological formation properties," as recited by amended claim 1. Page 21 of the Office action cites paragraphs [0086] and [0176] of Fuchey as allegedly teaching the limitation of "based on, at least in part, the plurality of geo-exploration data including the spectroscopic IR data, training a set of deep learning models, each deep learning model comprising multiple layers and configured to predict one or more geological formation properties," as recited by original claim 1.
Additionally, Fuchey does not teach the limitation of "predicting, using the set of trained deep learning models, the one or more geological formation properties based on, at least in part, the second set of geo-exploration data," as recited by amended claim 1. Page 22 of the Office Action again cites paragraph [0086] of Fuchey, previously discussed above, as allegedly teaching the limitation of "predicting the one or more geological formation properties based on, at least in part, the newly received geo-exploration data," as recited by original claim 1. As discussed above, while Fuchey discloses a well prognosis application that predicts the type and characteristics of geological formations encountered by a drill-bit and the location where such rocks may be encountered, Fuchey does not disclose how such predictions are generated, let alone that they are generated using a set of trained DL models based on geo-exploration data that includes spectroscopic IR data, as described by amended claim 1. Accordingly, Fuchey fails to teach the recited limitation.
For at least these reasons, reconsideration and withdrawal of the rejection of claim 1 and its dependent claims are respectfully requested. Independent claim 11 differs in scope relative to claim 1 but include features similar to those discussed above with reference to claim 1.
Therefore, reconsideration and withdrawal of the rejection of claim 11 and its respective dependent claims are respectfully requested for at least the reasons provided above with reference to claim 1.
Claims 9, 10, 19, and 20 are rejected under 35 U.S.C. § 103(a) as being unpatentable over Fuchey, and further in view of U.S. Publication No. 2022/0207079 to Shebl et al ("Shebl").
As discussed above, Fuchey fails to disclose the features of amended claim 1.
Specifically, Fuchey does not teach the features of "based on, at least in part, the first set of geo- exploration data including the spectroscopic IR data, training a set of deep learning models, each deep learning model comprising multiple layers and configured to predict one or more geological formation properties" or "predicting, using the set of trained deep learning models, the one or more geological formation properties based on, at least in part, the newly received geo- exploration data." Accordingly, because Fuchey does not disclose at least these features, Fuchey fails to render independent claim 1 obvious.
Claim 9 depends from claim 1 and incorporates all of its limitations, and claim 10, in turn, depends from claim 9. Since independent claim 1 is patentable for the reasons stated, claims 9 and 10 are likewise allowable over Fuchey. Moreover, Shebl has not been shown to remedy the previously identified deficiencies of Fuchey. Accordingly, the combination of Fuchey and Shebl does not teach or render obvious the features of claims 9 and 10.
Similarly, Fuchey fails to disclose the features of amended claim 11, which recites features similar to those discussed above with reference to claim 1. As with claim 1, Fuchey does not teach or suggest the limitations of amended claim 11, and Shebl has not been shown to cure these deficiencies. Accordingly, claim 11 is not rendered obvious by the combination of Fuchey and Shebl.
Claim 19 depends from claim 11 and incorporates all of its limitations, and claim 20, in turn, depends from claim 19. Thus, claims 19 and 20 are likewise allowable over the cited art.
For at least these reasons, reconsideration and withdrawal of the rejection of claims 9, 10, 19, and 20 is respectfully requested.
Examiner’s response: Applicant’s arguments have been fully considered but are moot in light of the amendments made on the claims.
The rejections made under 35 U.S.C. 102 and 103 are withdrawn and new grounds for rejection is presented below.
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 rejected under 35 U.S.C. 101 because they are directed to an abstract idea without significantly more.
Step 1 analysis: Independent Claim 1 recites, in part, a computer implemented method, therefore falling into the statutory category of process. Independent Claim 11 recites, in part, a computer system comprising one or more processors configured to perform operations, therefore falling into the statutory category of machine.
Regarding Claim 1:
Step 2A: Prong 1 analysis:
Claim 1 recites in part:
“predicting … the one or more geological formation properties based on, at least in part, the second set of geo-exploration data”. As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgement, or opinion) or with the aid of pencil and paper. For example, this limitation encompasses making a prediction based on gathered data.
Accordingly, at Step 2A: Prong 1, the claim is directed to an abstract idea.
Step 2A: Prong 2 analysis:
The judicial exception is not integrated into practical application. In particular, the claim recites the additional elements of:
“accessing a first set of geo-exploration data from a first drilling site wherein at least portions of the first set of geo-exploration data are based on measurements of core samples taken from the first drilling site” This additional elements is recited at a high level of generality and amounts to extra-solution activity of gathering data i.e. pre-solution activity of gathering data for use in the claimed process.
“wherein the first set of geo-exploration data includes spectroscopic infra-red (IR) data”. This limitation merely indicates a field of use or technological environment in which the judicial exception is performed (spectroscopy) and thus fails to add an inventive concept to the claims. See MPEP 2106.05(h).
“based on, at least in part, the first set of geo-exploration data including the spectroscopic IR data, training a set of deep learning models, each deep learning model comprising multiple layers and configured to predict one or more geological formation properties”. This additional element is recited at a high level of generality such that it amounts to no more than mere instructions to apply the exception using a generic computer component (deep learning model) (See MPEP 2106.05(f)).
“processing, using the set of trained deep learning models, a second set of geo-exploration data that also includes spectroscopic IR data”. This additional element is recited at a high level of generality such that it amounts to no more than mere instructions to apply the exception using a generic computer component (deep learning models) (See MPEP 2106.05(f)).
“using the set of trained deep learning models”. This additional element is recited at a high level of generality such that it amounts to no more than mere instructions to apply the exception using a generic computer component (deep learning models) (See MPEP 2106.05(f)).
Accordingly at Step 2A: Prong 2, the additional elements individually or in combination do not integrate the judicial exception into a practical application.
Step 2B analysis:
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception.
As discussed above, the additional element(s) of “based on, at least in part, the first set of geo-exploration data including the spectroscopic IR data, training a set of deep learning models, each deep learning model comprising multiple layers and configured to predict one or more geological formation properties”, “processing, using the set of trained deep learning models, a second set of geo-exploration data that also includes spectroscopic IR data” and “using the set of trained deep learning models” is/are recited at a high-level of generality such that it/they amount(s) to no more than mere instructions to apply the exception using generic computer components (See MPEP 2106.05(f)).
The additional element(s) of “accessing a first set of geo-exploration data from a first drilling site wherein at least portions of the first set of geo-exploration data are based on measurements of core samples taken from the first drilling site” is/are recited at a high level of generality and amount(s) to extra-solution activity of receiving data i.e., pre-solution activity of gathering data for use in the claimed process. The courts have found limitations directed to obtaining information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
The additional element(s) of “wherein the first set of geo-exploration data includes spectroscopic infra-red (IR) data” is/are directed to particular field(s) of use (spectroscopy) (MPEP 2106.05(h)) and therefore do not provide significantly more than the abstract idea, and thus the claim is subject-matter ineligible.
Accordingly, at Step 2B, the additional elements individually or in combination do not amount to significantly more than the judicial exception.
Regarding Claim 2:
Step 2A: Prong 2 analysis:
The judicial exception is not integrated into practical application. In particular, the claim recites the additional elements of:
“wherein the spectroscopic IR data includes Fourier Transform Infrared Spectroscopy (FTIR) data of core samples at a drilling site”. This limitation merely indicates a field of use or technological environment in which the judicial exception is performed (spectroscopy) and thus fails to add an inventive concept to the claims. See MPEP 2106.05(h).
“wherein the second set of geo-exploration data is from a second drilling site different from the first drilling site”. This limitation merely indicates a field of use or technological environment in which the judicial exception is performed (drill site data) and thus fails to add an inventive concept to the claims. See MPEP 2106.05(h).
Accordingly at Step 2A: Prong 2, the additional elements individually or in combination do not integrate the judicial exception into a practical application.
Step 2B analysis:
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception.
The additional element(s) of “wherein the spectroscopic IR data includes Fourier Transform Infrared Spectroscopy (FTIR) data of core samples at the drilling site” and “wherein the second set of geo-exploration data is from a second drilling site different from the first drilling site” is/are directed to particular field(s) of use (spectroscopy and drill site data) (MPEP 2106.05(h)) and therefore do not provide significantly more than the abstract idea, and thus the claim is subject-matter ineligible.
Accordingly, at Step 2B, the additional elements individually or in combination do not amount to significantly more than the judicial exception.
Regarding Claim 3:
Step 2A: Prong 2 analysis:The judicial exception is not integrated into practical application. In particular, the claim recites the additional elements of:
“wherein the set of deep learning models include a first deep learning model configured to predict a rock type of the core samples”. This limitation merely indicates a field of use or technological environment in which the judicial exception is performed (deep learning models) and thus fails to add an inventive concept to the claims. See MPEP 2106.05(h).
“wherein training the first deep learning model includes training based on, at least in part, the FTIR data of the core samples from the first drilling site”. This additional element is recited at a high level of generality such that 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.
Accordingly at Step 2A: Prong 2, the additional elements individually or in combination do not integrate the judicial exception into a practical application.
Step 2B analysis:
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception.
The additional element(s) of “wherein the set of deep learning models include a first deep learning model configured to predict a rock type of the core samples” is/are directed to particular field(s) of use (deep learning models) (MPEP 2106.05(h)) and therefore do not provide significantly more than the abstract idea, and thus the claim is subject-matter ineligible.
As discussed above, the additional element(s) of “wherein training the first deep learning model includes training based on, at least in part, the FTIR data of the core samples from the first drilling site” is/are recited at a high-level of generality such that 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 (See MPEP 2106.05(f)).
Accordingly, at Step 2B, the additional elements individually or in combination do not amount to significantly more than the judicial exception.
Regarding Claim 4:
Step 2A: Prong 2 analysis:The judicial exception is not integrated into practical application. In particular, the claim recites the additional elements of:
“wherein the set of deep learning models include a second deep learning model configured to predict a geomechanical property of the core samples”. This limitation merely indicates a field of use or technological environment in which the judicial exception is performed (deep learning models) and thus fails to add an inventive concept to the claims. See MPEP 2106.05(h).
“wherein training the second deep learning model includes training based on, at least in part, the FTIR data of the core samples at first the drilling site”. This additional element is recited at a high level of generality such that 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.
Accordingly at Step 2A: Prong 2, the additional elements individually or in combination do not integrate the judicial exception into a practical application.
Step 2B analysis:
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception.
The additional element(s) of “wherein the set of deep learning models include a second deep learning model configured to predict a geomechanical property of the core samples” is/are directed to particular field(s) of use (deep learning models) (MPEP 2106.05(h)) and therefore do not provide significantly more than the abstract idea, and thus the claim is subject-matter ineligible.
As discussed above, the additional element(s) of “wherein training the first deep learning model includes training based on, at least in part, the FTIR data of the core samples from the first drilling site” is/are recited at a high-level of generality such that 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 (See MPEP 2106.05(f)).
Accordingly, at Step 2B, the additional elements individually or in combination do not amount to significantly more than the judicial exception.
Regarding Claim 5:
Step 2A: Prong 2 analysis:The judicial exception is not integrated into practical application. In particular, the claim recites the additional elements of:
“wherein the set of deep learning models include a third deep learning model configured to predict a sonic velocity of the core samples”. This limitation merely indicates a field of use or technological environment in which the judicial exception is performed (deep learning models) and thus fails to add an inventive concept to the claims. See MPEP 2106.05(h).
“wherein training the third deep learning model includes training based on, at least in part, the FTIR data of the core samples at the first drilling site”. This additional element is recited at a high level of generality such that 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.
Accordingly at Step 2A: Prong 2, the additional elements individually or in combination do not integrate the judicial exception into a practical application.
Step 2B analysis:
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception.
The additional element(s) of “wherein the set of deep learning models include a third deep learning model configured to predict a sonic velocity of the core samples” is/are directed to particular field(s) of use (deep learning models) (MPEP 2106.05(h)) and therefore do not provide significantly more than the abstract idea, and thus the claim is subject-matter ineligible.
As discussed above, the additional element(s) of “wherein training the third deep learning model includes training based on, at least in part, the FTIR data of the core samples at the first drilling site” is/are recited at a high-level of generality such that 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 (See MPEP 2106.05(f)).
Accordingly, at Step 2B, the additional elements individually or in combination do not amount to significantly more than the judicial exception.
Regarding Claim 6:
Step 2A: Prong 2 analysis:The judicial exception is not integrated into practical application. In particular, the claim recites the additional elements of:
“wherein the set of deep learning models include a fourth deep learning model configured to predict a permeability of the core samples”. This limitation merely indicates a field of use or technological environment in which the judicial exception is performed (deep learning models) and thus fails to add an inventive concept to the claims. See MPEP 2106.05(h).
“wherein training the fourth deep learning model includes training based on, at least in part, the FTIR data of the core samples at the first drilling site”. This additional element is recited at a high level of generality such that 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.
Accordingly at Step 2A: Prong 2, the additional elements individually or in combination do not integrate the judicial exception into a practical application.
Step 2B analysis:
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception.
The additional element(s) of “wherein the set of deep learning models include a fourth deep learning model configured to predict a permeability of the core samples” is/are directed to particular field(s) of use (deep learning models) (MPEP 2106.05(h)) and therefore do not provide significantly more than the abstract idea, and thus the claim is subject-matter ineligible.
As discussed above, the additional element(s) of “wherein training the fourth deep learning model includes training based on, at least in part, the FTIR data of the core samples at the first drilling site” is/are recited at a high-level of generality such that 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 (See MPEP 2106.05(f)).
Accordingly, at Step 2B, the additional elements individually or in combination do not amount to significantly more than the judicial exception.
Regarding Claim 7:
Step 2A: Prong 1 analysis:Claim 7 recites in part:
“validating the set of deep learning models by cross correlating predicted values of the one or more geological formation properties with measured values of the one or more geological formation properties”. As drafted and under its broadest reasonable interpretation, this limitation covers performance of the limitation in the mind (including an observation, evaluation, judgement, or opinion) or with the aid of pencil and paper. For example, this limitation encompasses making sure that the measure values match the predicted values.
Accordingly, at Step 2A: Prong 1, the claim is directed to an abstract idea.
Step 2A: Prong 2 analysis:
The claim does not recite any additional elements that integrate the judicial exception into a practical application.
Step 2B analysis:
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception.
Regarding Claim 8:
Step 2A: Prong 2 analysis:
The judicial exception is not integrated into practical application. In particular, the claim recites the additional elements of:
“wherein at least one deep learning model from the set of deep learning models is trained predict a geological formation property with a spatial resolution that is higher than well logs in the first of geo-exploration data”. This additional element is recited at a high level of generality such that 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.
Accordingly at Step 2A: Prong 2, the additional elements individually or in combination do not integrate the judicial exception into a practical application.
Step 2B analysis:
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception.
As discussed above, the additional element(s) of “wherein at least one deep learning model from the set of deep learning models is trained predict a geological formation property with a spatial resolution that is higher than well logs in the first set of geo-exploration data” is/are recited at a high-level of generality such that 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 (See MPEP 2106.05(f)).
Accordingly, at Step 2B, the additional elements individually or in combination do not amount to significantly more than the judicial exception.
Regarding Claim 9:
Step 2A: Prong 2 analysis:
The judicial exception is not integrated into practical application. In particular, the claim recites the additional elements of:
“wherein the set of deep learning model each comprises a layer of one or more convolutional neural network (CNN) blocks”. This limitation merely indicates a field of use or technological environment in which the judicial exception is performed (deep learning models) and thus fails to add an inventive concept to the claims. See MPEP 2106.05(h).
Accordingly at Step 2A: Prong 2, the additional elements individually or in combination do not integrate the judicial exception into a practical application.
Step 2B analysis:
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception.
The additional element(s) of “wherein the set of deep learning model each comprises a layer of one or more convolutional neural network (CNN) blocks” is/are directed to particular field(s) of use (deep learning models) (MPEP 2106.05(h)) and therefore do not provide significantly more than the abstract idea, and thus the claim is subject-matter ineligible.
Accordingly, at Step 2B, the additional elements individually or in combination do not amount to significantly more than the judicial exception.
Regarding Claim 10:
Step 2A: Prong 2 analysis:
The judicial exception is not integrated into practical application. In particular, the claim recites the additional elements of:
“wherein the layer of one or more CNN blocks are followed by a softmax layer or a regressor layer”. This limitation merely indicates a field of use or technological environment in which the judicial exception is performed (convolutional neural networks) and thus fails to add an inventive concept to the claims. See MPEP 2106.05(h).
“wherein the softmax layer is configured to generate a classification as a geological formation property, and wherein the regressor layer is configured to quantify a value of a geological formation property”. This limitation merely indicates a field of use or technological environment in which the judicial exception is performed (convolutional neural network layers) and thus fails to add an inventive concept to the claims. See MPEP 2106.05(h).
Accordingly at Step 2A: Prong 2, the additional elements individually or in combination do not integrate the judicial exception into a practical application.
Step 2B analysis:
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception.
The additional element(s) of “wherein the layer of one or more CNN blocks are followed by a softmax layer or a regressor layer, wherein the softmax layer is configured to generate a classification as a geological formation property, and wherein the regressor layer is configured to quantify a value of a geological formation property” is/are directed to particular field(s) of use (convolutional neural networks and convolutional neural network layers) (MPEP 2106.05(h)) and therefore do not provide significantly more than the abstract idea, and thus the claim is subject-matter ineligible.
Accordingly, at Step 2B, the additional elements individually or in combination do not amount to significantly more than the judicial exception.
Regarding Claim 11:
Due to claim language similar to that of Claim 1, Claim 11 is rejected for the same reasons as presented above in the rejection of Claim 1.
Regarding Claim 12:
Due to claim language similar to that of Claim 2, Claim 12 is rejected for the same reasons as presented above in the rejection of Claim 2.
Regarding Claim 13:
Due to claim language similar to that of Claim 3, Claim 13 is rejected for the same reasons as presented above in the rejection of Claim 3.
Regarding Claim 14:
Due to claim language similar to that of Claim 4, Claim 14 is rejected for the same reasons as presented above in the rejection of Claim 4.
Regarding Claim 15:
Due to claim language similar to that of Claim 5, Claim 15 is rejected for the same reasons as presented above in the rejection of Claim 5.
Regarding Claim 16:
Due to claim language similar to that of Claim 6, Claim 16 is rejected for the same reasons as presented above in the rejection of Claim 6.
Regarding Claim 17:
Due to claim language similar to that of Claim 7, Claim 17 is rejected for the same reasons as presented above in the rejection of Claim 7.
Regarding Claim 18:
Due to claim language similar to that of Claim 8, Claim 18 is rejected for the same reasons as presented above in the rejection of Claim 8.
Regarding Claim 19:
Due to claim language similar to that of Claim 9, Claim 19 is rejected for the same reasons as presented above in the rejection of Claim 9.
Regarding Claim 20:
Due to claim language similar to that of Claim 10, Claim 20 is rejected for the same reasons as presented above in the rejection of Claim 10.
Claim Rejections - 35 USC § 103
Claim(s) 1, 3, 4, 6, 9-11, 13, 14, 16, 19, and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Fuchey et al (US 20240077642 A1, hereinafter Fuchey) in view of Shebl et al (US 20220207079 A1, hereinafter Shebl).
Regarding Claim 1:
Fuchey teaches
accessing a first set of geo-exploration data from a first drilling site, wherein the first set of geo-exploration data includes spectroscopic infra-red (IR) data, wherein at least portions of the first set of geo-exploration data are based on measurements of core samples taken from the first drilling site (Fuchey [0057]: "As an example, data can include geochemical data. For example, consider data acquired using X-ray fluorescence (XRF) technology, Fourier transform infrared spectroscopy (FTIR) technology and/or wireline geochemical technology."; [0082]: "As an example, such an interpolation may be constrained by interpretations from log and core data, and by prior geological knowledge"; [0187]: "a framework may be implemented at a field site where imagery, etc., may be acquired at the field site for purposes of searching, adding to a dataset, adding to a database, adjusting a data structure, determining one or more virtual distances, etc."; (EN): it is noted that the "log and core data" is obtained from well sites as depicted in Fig. 4);
based on, at least in part, the first set of geo-exploration data including the spectroscopic IR data, training a set of deep learning models, each deep learning model comprising multiple layers and configured to predict one or more geological formation properties (Fuchey [0086]: "As to the various applications of the applications block 340, the well prognosis application 342 may include predicting type and characteristics of geological formations that may be encountered by a drill-bit, and location where such rocks may be encountered (e.g., before a well is drilled)"; [0149]: "As shown, the block 1220 can process data in the data structure 1250 using machine learning (ML). For example, consider a machine learning model that can cluster fields using data of the data structure 1250 via unsupervised machine learning. As shown, the block 1220 can generate, augment, update, etc., the data structure 1260, which can include, for example, field asset clusters. The block 1230 can provide for graph analysis of the fields and assets, for example, via rendering one or more graphs such as the example graph 1280 to a display."; [0176]: "As an example, a machine learning model can be a deep learning model (e.g., deep Boltzmann machine, deep belief network, convolutional neural network, stacked auto-encoder, etc.)");
processing, using applying the set of trained deep learning models … that also includes spectroscopic IR data (Fuchey [0057]: "As an example, data can include geochemical data. For example, consider data acquired using X-ray fluorescence (XRF) technology, Fourier transform infrared spectroscopy (FTIR) technology and/or wireline geochemical technology."; [0082]: "As an example, such an interpolation may be constrained by interpretations from log and core data, and by prior geological knowledge"; [0187]: "a framework may be implemented at a field site where imagery, etc., may be acquired at the field site for purposes of searching, adding to a dataset, adding to a database, adjusting a data structure, determining one or more virtual distances, etc.");
predicting, using the set of trained deep learning models, the one or more geological formation properties based on, at least in part, the second set of geo-exploration data (Fuchey [0086]: "As to the various applications of the applications block 340, the well prognosis application 342 may include predicting type and characteristics of geological formations that may be encountered by a drill-bit, and location where such rocks may be encountered (e.g., before a well is drilled)"; [0149]: "As shown, the block 1220 can process data in the data structure 1250 using machine learning (ML). For example, consider a machine learning model that can cluster fields using data of the data structure 1250 via unsupervised machine learning. As shown, the block 1220 can generate, augment, update, etc., the data structure 1260, which can include, for example, field asset clusters. The block 1230 can provide for graph analysis of the fields and assets, for example, via rendering one or more graphs such as the example graph 1280 to a display."; [0176]: "As an example, a machine learning model can be a deep learning model (e.g., deep Boltzmann machine, deep belief network, convolutional neural network, stacked auto-encoder, etc.)").
Fuchey does not distinctly disclose
a second set of geo-exploration data
However, Shebl teaches
a second set of geo-exploration data (Shebl [0128]: "More generally, in examples, the trained convolution deconvolution neural network for the trained salient feature extraction module may be generated using supervised learning based on a second subset of the labelled image training database"; (EN): a second subset is analogous to a second set of data and the database of Shebl consists of images related to geological formations, which reads on “geo-exploration data”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, and having the teachings of Fuchey and Shebl before him or her, to modify the method for searching for subsurface geological deposits for field sites of Fuchey to include the use of convolutional neural networks that utilize a softmax layer as shown in Shebl. The motivation for doing so would have been to apply the convolutional neural networks of Shebl in part to provide a classification for a geological formation property via the softmax layer (Shebl [0083]: "In examples, an output 326 of the trained convolution neural network 301 provides carbonate rock classification, such as that relating to texture, reservoir rock quality, mineralogy (e.g. dolomite vs limestone).").
Regarding Claim 3:
Fuchey teaches
The computer-implemented method of claim 2, wherein the set of deep learning models include a first deep learning model configured to predict a rock type of the core samples (Fuchey [0082]: "As to the facies and petrophysical property interpolation 353, it may include an assessment of type of rocks and of their petrophysical properties (e.g. porosity, permeability)")
wherein training the first deep learning model includes training based on, at least in part, the FTIR data of the core samples from the first drilling site (Fuchey [0057]: "As an example, data can include geochemical data. For example, consider data acquired using X-ray fluorescence (XRF) technology, Fourier transform infrared spectroscopy (FTIR) technology and/or wireline geochemical technology."; [0187]: "a framework may be implemented at a field site where imagery, etc., may be acquired at the field site for purposes of searching, adding to a dataset, adding to a database, adjusting a data structure, determining one or more virtual distances, etc."; (EN): “field site” as mentioned in the reference reads as analogous to “drilling site”).
Regarding Claim 4:
Fuchey teaches
The computer-implemented method of claim 2, wherein the set of deep learning models include a second deep learning model configured to predict a geomechanical property of the core samples (Fuchey [0084]: "As an example a geomechanical simulation may be used for a variety of purposes such as, for example, prediction of fracturing, reconstruction of the paleo-geometries of the reservoir as they were prior to tectonic deformations, etc.")
wherein training the second deep learning model includes training based on, at least in part, the FTIR data of the core samples at first the drilling site (Fuchey [0057]: "As an example, data can include geochemical data. For example, consider data acquired using X-ray fluorescence (XRF) technology, Fourier transform infrared spectroscopy (FTIR) technology and/or wireline geochemical technology."; [0187]: "a framework may be implemented at a field site where imagery, etc., may be acquired at the field site for purposes of searching, adding to a dataset, adding to a database, adjusting a data structure, determining one or more virtual distances, etc."; (EN): “field site” as mentioned in the reference reads as analogous to “drilling site”).
Regarding Claim 6:
Fuchey teaches
The computer-implemented method of claim 2, wherein the set of deep learning models include a fourth deep learning model configured to predict a permeability of the core samples (Fuchey [0082]: "As to the facies and petrophysical property interpolation 353, it may include an assessment of type of rocks and of their petrophysical properties (e.g. porosity, permeability)")
wherein training the fourth deep learning includes training based on, at least in part, the FTIR data of the core samples at the first drilling site (Fuchey [0057]: "As an example, data can include geochemical data. For example, consider data acquired using X-ray fluorescence (XRF) technology, Fourier transform infrared spectroscopy (FTIR) technology and/or wireline geochemical technology."; [0187]: "a framework may be implemented at a field site where imagery, etc., may be acquired at the field site for purposes of searching, adding to a dataset, adding to a database, adjusting a data structure, determining one or more virtual distances, etc."; (EN): “field site” as mentioned in the reference reads as analogous to “drilling site”).
Regarding Claim 9:
Fuchey does not distinctly disclose
The computer-implemented method of claim 1, wherein the set of deep learning model each comprises a layer of one or more convolutional neural network (CNN) blocks.
However, Shebl teaches
The computer-implemented method of claim 1, wherein the set of deep learning model each comprises a layer of one or more convolutional neural network (CNN) blocks (Shebl [0083]: "In examples, an output 326 of the trained convolution neural network 301 provides carbonate rock classification, such as that relating to texture, reservoir rock quality, mineralogy (e.g. dolomite vs limestone).").
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, and having the teachings of Fuchey and Shebl before him or her, to modify the method for searching for subsurface geological deposits for field sites of Fuchey to include the use of convolutional neural networks that utilize a softmax layer as shown in Shebl. The motivation for doing so would have been to apply the convolutional neural networks of Shebl in part to provide a classification for a geological formation property via the softmax layer (Shebl [0083]: "In examples, an output 326 of the trained convolution neural network 301 provides carbonate rock classification, such as that relating to texture, reservoir rock quality, mineralogy (e.g. dolomite vs limestone).").
Regarding Claim 10:
Fuchey does not distinctly disclose
The computer-implemented method of claim 9, wherein the layer of one or more CNN blocks are followed by a softmax layer or a regressor layer, wherein the softmax layer is configured to generate a classification as a geological formation property, and wherein the regressor layer is configured to quantify a value of a geological formation property.
However, Shebl teaches
The computer-implemented method of claim 9, wherein the layer of one or more CNN blocks are followed by a softmax layer or a regressor layer, wherein the softmax layer is configured to generate a classification as a geological formation property, and wherein the regressor layer is configured to quantify a value of a geological formation property (Shebl [0083]: "In examples, an output 326 of the trained convolution neural network 301 provides carbonate rock classification, such as that relating to texture, reservoir rock quality, mineralogy (e.g. dolomite vs limestone)."; [0087]: "In examples, the output of the trained convolution neural network 301 is via Softmax activation functions 324, for example to generate the output 326, although other activation functions could be used.").
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, and having the teachings of Fuchey and Shebl before him or her, to modify the method for searching for subsurface geological deposits for field sites of Fuchey to include the use of convolutional neural networks that utilize a softmax layer as shown in Shebl. The motivation for doing so would have been to apply the convolutional neural networks of Shebl in part to provide a classification for a geological formation property via the softmax layer (Shebl [0083]: "In examples, an output 326 of the trained convolution neural network 301 provides carbonate rock classification, such as that relating to texture, reservoir rock quality, mineralogy (e.g. dolomite vs limestone).").
Regarding Claim 11:
Due to c