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 .
Response to Amendment
The Amendment filed on 09/18/2025 has been entered. Claims 6, 13 and 19 are canceled. Claims 21-23 are added. Claims 1-5, 7-12, 14-18 and 20-23 remain pending in the application.
Claim Objections
Claims 1, 8 and 15 are objected to because of the following informalities:
“the geological age model” should be “the geophysical age model”.
Appropriate correction is required.
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 1-5, 7-12, 14-18 and 20-23 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1: Claims 1-5, 7 and 21 are directed to a method, claims 8-12, 14 and 22 are directed to a medium and claims 15-18, 20 and 23 are directed to a system. Therefore, the claims are eligible under Step 1 for being directed to a process, a machine and a manufacture respectively.
Independent claims 1, 8 and 15:
Step 2A Prong 1:
Claims recite:
identifying an area of interest at a site, wherein a post-stack seismic reflection volume is associated with the area of interest - Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating data and identifying an area of interest based on judgement, which is observing, evaluating and judging that is practically capable of being performed in the human mind with the assistance of pen and paper.
generating a geophysical age model associated with the post-stack seismic reflection volume - Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating data and generating a geophysical age model based on judgement, which is observing, evaluating and judging that is practically capable of being performed in the human mind with the assistance of pen and paper.
locating well data associated with one or more wellbores in the area of interest, the well data comprising lithology labels - Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating data and identifying well data based on judgement, which is observing, evaluating and judging that is practically capable of being performed in the human mind with the assistance of pen and paper.
extracting, along the one or more wellbores, at least one coincident seismic trace from the post-stack seismic reflection volume and at least one geophysical age trace from the geological age model - Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating data and extracting data based on judgement, which is observing, evaluating and judging that is practically capable of being performed in the human mind with the assistance of pen and paper.
generating a predicted lithology volume using a multivariate model or a machine learning model trained on the at least one coincident seismic trace, the at one geophysical age trace, and the lithology labels - Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating data and generating a predicted lithology volume based on judgement, which is observing, evaluating and judging that is practically capable of being performed in the human mind with the assistance of pen and paper.
altering one or more measurement or logging operations at the area of interest based, at least in part, on the predicted lithology volume - Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating data and modifying one or more measurement or logging operations based on judgement, which is observing, evaluating and judging that is practically capable of being performed in the human mind with the assistance of pen and paper.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
A non-transitory computer readable storage medium storing one or more instructions, that when executed by a processor, cause the processor to; An information handling system comprising: a memory; a processor coupled to the memory, wherein the memory comprises one or more instructions executable by the processor to
- These limitations amount to components of a general purpose computer that applies a judicial exception, by use of conventional computer functions (see MPEP § 2106.05(b)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
A non-transitory computer readable storage medium storing one or more instructions, that when executed by a processor, cause the processor to; An information handling system comprising: a memory; a processor coupled to the memory, wherein the memory comprises one or more instructions executable by the processor to - These limitations amount to components of a general purpose computer that applies a judicial exception, by use of conventional computer functions (see MPEP § 2106.05(b)).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claims 2, 9 and 16:
Step 2A Prong 1:
Claims recite:
interpreting one or more seismic horizons associated with the post-stack seismic reflection volume, wherein the geophysical age model is generated based, at least in part, on the one or more interpreted seismic horizons - Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating data and generating the geophysical age model based on judgement, which is observing, evaluating and judging that is practically capable of being performed in the human mind with the assistance of pen and paper.
Step 2A Prong 2 & Step 2B: There are no additional elements recited so the claims do not provide a practical application and is not considered to be significantly more. As such, the claims are ineligible.
Dependent claims 3, 10 and 17:
Step 2A Prong 1: The claim recites the abstract ideas of claims 1, 8 and 15.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
exporting at least one of one or more seismic attributes associated with the post-stack seismic reflection volume and the geophysical age model for training the multivariate model or the machine learning model - the steps recited at a high level of generality, and amounts to mere data outputting, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
exporting at least one of one or more seismic attributes associated with the post-stack seismic reflection volume and the geophysical age model for training the multivariate model or the machine learning model - the steps recited at a high level of generality, and amounts to mere data outputting, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claims 4, 11 and 18:
Step 2A Prong 1:
Claims recite:
interpreting a lithology of a formation within the area of interest using seismic data associated with the post-stack reflection volume and the well data - Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating data, which is observing, evaluating and judging that is practically capable of being performed in the human mind with the assistance of pen and paper.
Step 2A Prong 2 & Step 2B: There are no additional elements recited so the claims do not provide a practical application and is not considered to be significantly more. As such, the claims are ineligible.
Dependent claims 5 and 12:
Step 2A Prong 1: The claim recites the abstract ideas of claims 4 and 14.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
exporting lithology information associated with the lithology as training input to the multivariate model or the machine learning model - the steps recited at a high level of generality, and amounts to mere data outputting, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
exporting lithology information associated with the lithology as training input to the multivariate model or the machine learning model - the steps recited at a high level of generality, and amounts to mere data outputting, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claims 7, 14 and 20:
Step 2A Prong 1:
Claims recite:
determining a performance value of the machine learning model - Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating data and generating data based on judgement, which is observing, evaluating and judging that is practically capable of being performed in the human mind with the assistance of pen and paper.
comparing the performance value to a threshold - Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating data and judging, which is observing, evaluating and judging that is practically capable of being performed in the human mind with the assistance of pen and paper.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
retraining the multivariate model or the machine learning model based on the comparison of the performance value to the threshold – the step recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
retraining the multivariate model or the machine learning model based on the comparison of the performance value to the threshold - the step recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claims 21, 22 and 23:
Step 2A Prong 1: The claim recites the abstract ideas of claims 1, 8 and 15.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
training the multivariate model or the machine learning model using the at least one coincident seismic trace, the at least one geophysical age trace, and the lithology labels - the step recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
training the multivariate model or the machine learning model using the at least one coincident seismic trace, the at least one geophysical age trace, and the lithology labels - the step recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-5, 8-12, 15-18 and 21-23 are rejected under 35 U.S.C. 103 as being unpatentable over Priezzhev et al. (hereinafter Priezzhev), US 20090119018 A1, in view of Imhof et al. (hereinafter Imhof), US 20110002194 A1.
Regarding independent claim 1, Priezzhev teaches a lithology prediction method (Abstract), comprising:
identifying an area of interest at a site, wherein a post-stack seismic reflection volume is associated with the area of interest ([0088] FIG. 7 shows a flow chart depicting a method for predicting subterranean formation properties for an operation of a wellsite. The method may be performed using, for example, the system of FIG. 6. The method may involve obtaining seismic data for an area of interest (block 702), obtaining an initial seismic cube using the seismic data (block 704), obtaining a plurality of shifted seismic cubes using the seismic data, where each of the plurality of shifted seismic cubes is shifted from the initial seismic cube (block 706));
generating a ([0088] generating a neural network using the initial seismic cube, the plurality of shifted seismic cubes, and well log data (block 708), applying the neural network to the seismic data to obtain a model for the area of interest (block 710));
locating well data associated with one or more wellbores in the area of interest, ([0089] The seismic data may be obtained (block 702) from a variety of sources. As discussed with respect to FIGS. 1A-1B and 6, seismic data associated with an area of interest may be generated by sensors (S) at the wellsite or from other sources; [0090] An area of interest may correspond to a volume of the subsurface. Further, the area of interest may include any number of subterranean formations as described above for FIGS. 1A-1D);
extracting, along the one or more wellbores, at least one coincident seismic trace from the post-stack seismic reflection volume and at least one ([0042] Data plots 308 a-c are examples of static data plots that may be generated by the data acquisition tools 302 a-d, respectively. Static data plot (308 a) is a seismic two-way response time and may be the same as the seismic trace (202) of FIG. 2A. Static plot (308 b) is core sample data measured from a core sample of the formation (304) similar to core sample (133) of FIG. 2B. Static data plot (308 c) is a logging trace, similar to the well log(204) of FIG. 2C):
generating a predicted lithology volume using a multivariate model or a machine learning model trained on the at least one coincident seismic trace, the at one core sample data ([0042] Data plots 308 a-c are examples of static data plots that may be generated by the data acquisition tools 302 a-d, respectively. Static data plot (308 a) is a seismic two-way response time and may be the same as the seismic trace (202) of FIG. 2A. Static plot (308 b) is core sample data measured from a core sample of the formation (304) similar to core sample (133) of FIG. 2B. Static data plot (308 c) is a logging trace, similar to the well log(204) of FIG. 2C; [0048] Each of the static models 402a-c is depicted as volumetric representations of an oilfield with one or more reservoirs, and their surrounding formation structures. These volumetric representations are a prediction of the geological structure of the subterranean formation at the specified location based upon available measurements); and
altering one or more measurement or logging operations at the area of interest based, at least in part, on the predicted lithology volume ([0048] Adjustments may be made to the models based on an analysis of the various static models in FIGS. 4A-C, and an adjusted formation layer may be generated; [0051] Referring back to the static models of FIG. 4A-C, the models have been adjusted based on the dynamic data provided in the production of the graph (308d) of FIG. 3. The dynamic data collected by data acquisition tool (302d) is applied to each of the static models 4A-4C. As shown, the dynamic data indicates that the fault (307) and layer (306a) as predicted by the static models may need adjustment. The layer (306a) has been adjusted in each model as shown by the dotted lines. The modified layer is depicted as 306a', 306a'' and 306a''' for the static models of FIGS. 4A-C, respectively).
Priezzhev does not explicitly disclose generating a geophysical age model associated with the post-stack seismic reflection volume; the well data comprising lithology labels.
However, in the same field of endeavor, Imhof teaches generating a geophysical age model associated with the post-stack seismic reflection volume ([0181] Aspects disclosed herein describe a method that creates and utilizes mapping volumes between the domains of geophysical depth and geologic age of deposition; [0182] By construction, each surface is assigned an age that enables the generation of mapping volumes from a depth domain to an age domain and from the age domain the depth domain. Each sample in the depth domain is assigned an age; [0191] FIG. 25 depicts a flowchart of a method 250 according to aspects disclosed herein. At block 252 seismic data is obtained. At block 254 the seismic data is subjected to the skeletonization processes described previously herein to extract a set of topologically consistent surfaces with sequential top-down labels; [0192] At block 255 an age is assigned to each surface; [0197] Using the age of each surface, at block 256 (FIG. 25) an age mapping volume is created. Once created, the age mapping volume may be used for interpretation in the depth domain, as represented by block 258. The age mapping volume maps samples from the depth domain to the age domain, and thus, is typically of the same size as the seismic dataset (as shown in FIG. 23).); the well data comprising lithology labels ([0107] FIG. 11 shows the progression from a schematic multi-valued surface in map view (111) to lines by morphological thinning (112) and removal of line joints (113), from lines to points by morphological thinning (114), point labeling (115), and propagation of labels back onto the surface (116). The set of events with the same label define a patch. The result in FIG. 11 is a set of eight small patches in step 116, corresponding to the eight characteristic points in step 115).
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of geophysical and geological interpretation of seismic volumes in the domains of depth, time, and age as suggested in Imhof into Priezzhev’s system because both of these systems are addressing geophysical and geologic prospecting, and more particularly to the analysis of seismic data to reduce a seismic data volume to its internal reflection-based surfaces or horizons. This modification would have been motivated by the desire for a method that generates topologically consistent reflection horizons from seismic (or attribute) data or any geophysical data, preferably one that generates multiple horizons simultaneously (Imhof, [0022]).
Regarding dependent claim 2, the combination of Priezzhev and Imhof teaches all the limitations as set forth in the rejection of claim 1 that is incorporated. Imhof further teaches further comprising:
interpreting one or more seismic horizons associated with the post-stack seismic reflection volume, wherein the geophysical age model is generated based, at least in part, on the one or more interpreted seismic horizons ([0082] In application for geophysical or geological interpretation, there is often a distinction made between the terms `horizon` and `surface`. As used herein, a surface and horizon may be used interchangeable. The present invention is a method that generates multiple surfaces simultaneously, while forcing individual surfaces to be single valued and all surfaces to be topologically consistent. Surfaces that using traditional methods are multi-valued or topologically inconsistent are replaced with a set of smaller patches, each of which is single-valued and topologically consistent with all other surfaces. This method creates surfaces that represent many or all reflection surfaces contained in a seismic data volume. It generates the skeletonized representation of the seismic data, which greatly reduces the amount of data. Beneficially, it organizes and presents the seismic data in a geologically intuitive manner, which facilitates seismic interpretation and characterization of the subsurface, and thus the delineation of underground features relevant to the exploration and production of hydrocarbons; [0173] Seismic interpretation often involves the picking of horizons to characterize the subsurface for the delineation of underground features relevant to the exploration, identification and production of hydrocarbons; [0186] During the flattening process the data may be distorted in the vertical direction to align the corresponding surface to a specific geologic age. Each horizontal slice in the flattened domain corresponds to a horizon slice in the original domain. Due to the sheer number of surfaces and noises in the seismic data, perfect alignment is often not desirable, and instead, the surfaces may be aligned in an approximate manner only. Additionally, some of the surfaces may have originally not been completely flat. To facilitate the flattening, analyzing and/or interpreting of the flattened data, an age mapping volume may be defined that specifies where each voxel in the depth domain positioned in the age domain. Alternatively or additionally, a depth mapping volume may be defined that specifies where each voxel in the age volume originated in the depth domain. While either mapping volume can be used to transform between the domains, defining and using both mapping volumes enhances computational efficiency and ease of use. In addition to enabling transformations between the depth domain and the age domain, the mapping volumes may be used to interpret and characterize the subsurface, and may be further used to construct earth models).
Regarding dependent claim 3, the combination of Priezzhev and Imhof teaches all the limitations as set forth in the rejection of claim 1 that is incorporated. Priezzhev further teaches further comprising:
exporting at least one of one or more seismic attributes associated with the post-stack seismic reflection volume and the the multivariate model or the machine learning model ([0074] Examples of well log data include acoustic impedance, density, porosity, resistivity, etc., at various depths of the well trajectory; [0079] The modeling unit (648) may also obtain seismic data … The modeling unit (648) may also be used to obtain seismic well logs from seismic cubes; [0082] Input and output layers may be generated from data received from the processing modules (642). For example, an input layer may be generated from seismic well logs (as defined above) derived from the original and shifted seismic cubes. Further, an output layer may be generated from well log data (e.g., acoustic impedance, density, resistivity, etc.); [0084] Optionally, the training module (650) may perform a statistical analysis of the input layer of a neural network to determine the potential bias (e.g., overfitting, underfitting) that may result in the output layer of a trained neural network. Specifically, the training module (650) may determine whether the training data for generating the input layer is properly proportioned to the weights of a weight matrix in order to minimize the potential for bias. Alternatively, if the amount of training data is fixed, the training module (650) may use other techniques (e.g., model selection, jittering, early stopping, weight decay, Bayesian learning, etc.) to minimize the potential for bias. For example, the training module (650) may use weight decay to decrease the size of larger weights (i.e., higher relative importance) in the neural network. In decreasing the size of larger weights, the generalization of the neural network may be improved by decreasing the variance of the output layer; [0085] Once trained, a neural network may be used to generate a model. For example, the processing modules (642) may apply a trained neural network to seismic data to generate an acoustic impedance model. In this example, the acoustic impedance model may correspond to a three-dimensional representation of the acoustic impedance data for an area of interest associated with the seismic data).
Imhof teaches training a machine learning model with a geophysical age model ([0197] Using the age of each surface, at block 256 (FIG. 25) an age mapping volume is created. Once created, the age mapping volume may be used for interpretation in the depth domain, as represented by block 258. The age mapping volume maps samples from the depth domain to the age domain, and thus, is typically of the same size as the seismic dataset (as shown in FIG. 23))).
Regarding dependent claim 4, the combination of Priezzhev and Imhof teaches all the limitations as set forth in the rejection of claim 1 that is incorporated. Priezzhev further teaches further comprising:
interpreting a lithology of a formation within the area of interest using seismic data associated with the post-stack reflection volume and the well data ([0022] the seismic cube can be used in combination with well log data to analyze geologic structures; [0045] The data collected from various sources, such as the data acquisition tools of FIG. 3, may then be processed and/or evaluated. Typically, seismic data displayed in the static data plot (308 a) from the data acquisition tool (302 a) is used by a geophysicist to determine characteristics of the subterranean formations and features. Core data shown in static plot (308 b) and/or log data from the well log(308 c) are typically used by a geologist to determine various characteristics of the subterranean formation).
Regarding dependent claim 5, the combination of Priezzhev and Imhof teaches all the limitations as set forth in the rejection of claim 4 that is incorporated. Priezzhev further teaches further comprising:
exporting lithology information associated with the lithology as training input to the multivariate model or the machine learning model ([0081] The training modules (650) may generate and train neural networks. More specifically, the training modules (650) may generate input layers and output layers to be used in neural networks. The input layer may correspond to input data to be processed in a neural network; [0082] Input and output layers may be generated from data received from the processing modules (642). For example, an input layer may be generated from seismic well logs (as defined above) derived from the original and shifted seismic cubes).
Regarding dependent claim 21, the combination of Priezzhev and Imhof teaches all the limitations as set forth in the rejection of claim 1 that is incorporated. Priezzhev teaches further comprising:
training the multivariate model or the machine learning model using the at least one coincident seismic trace, the at least one core sample data ([0042] Data plots 308 a-c are examples of static data plots that may be generated by the data acquisition tools 302 a-d, respectively. Static data plot (308 a) is a seismic two-way response time and may be the same as the seismic trace (202) of FIG. 2A. Static plot (308 b) is core sample data measured from a core sample of the formation (304) similar to core sample (133) of FIG. 2B. Static data plot (308 c) is a logging trace, similar to the well log(204) of FIG. 2C; [0048] Each of the static models 402a-c is depicted as volumetric representations of an oilfield with one or more reservoirs, and their surrounding formation structures. These volumetric representations are a prediction of the geological structure of the subterranean formation at the specified location based upon available measurements).
Imhof teaches generating the at least one geophysical age trace ([0181] Aspects disclosed herein describe a method that creates and utilizes mapping volumes between the domains of geophysical depth and geologic age of deposition; [0182] By construction, each surface is assigned an age that enables the generation of mapping volumes from a depth domain to an age domain and from the age domain the depth domain. Each sample in the depth domain is assigned an age; [0191] FIG. 25 depicts a flowchart of a method 250 according to aspects disclosed herein. At block 252 seismic data is obtained. At block 254 the seismic data is subjected to the skeletonization processes described previously herein to extract a set of topologically consistent surfaces with sequential top-down labels; [0192] At block 255 an age is assigned to each surface; [0197] Using the age of each surface, at block 256 (FIG. 25) an age mapping volume is created. Once created, the age mapping volume may be used for interpretation in the depth domain, as represented by block 258. The age mapping volume maps samples from the depth domain to the age domain, and thus, is typically of the same size as the seismic dataset (as shown in FIG. 23)), and the lithology labels for training the multivariate model or the machine learning model ([0107] FIG. 11 shows the progression from a schematic multi-valued surface in map view (111) to lines by morphological thinning (112) and removal of line joints (113), from lines to points by morphological thinning (114), point labeling (115), and propagation of labels back onto the surface (116). The set of events with the same label define a patch. The result in FIG. 11 is a set of eight small patches in step 116, corresponding to the eight characteristic points in step 115).
Regarding independent claim 8, it is a medium claim that corresponding to the method of claim 1. Therefore, it is rejected for the same reason as claim 1 above. Priezzhev further teaches a non-transitory computer readable storage medium storing one or more instructions, that when executed by a processor, cause the processor to perform operations (Fig. 6; [0058]-[0059]).
Regarding independent claim 15, it is a system claim that corresponding to the method of claim 1. Therefore, it is rejected for the same reason as claim 1 above. Priezzhev further teaches An information handling system comprising: a memory; a processor coupled to the memory, wherein the memory comprises one or more instructions executable by the processor to operations (Fig. 6; [0058]-[0059]).
Regarding dependent claim 9, it is a medium claim that corresponding to the method of claim 2. Therefore, it is rejected for the same reason as claim 2 above.
Regarding dependent claim 16, it is a system claim that corresponding to the method of claim 2. Therefore, it is rejected for the same reason as claim 2 above.
Regarding dependent claim 10, it is a medium claim that corresponding to the method of claim 3. Therefore, it is rejected for the same reason as claim 3 above.
Regarding dependent claim 17, it is a system claim that corresponding to the method of claim 3. Therefore, it is rejected for the same reason as claim 3 above.
Regarding dependent claim 11, it is a medium claim that corresponding to the method of claim 4. Therefore, it is rejected for the same reason as claim 4 above.
Regarding dependent claim 18, it is a system claim that corresponding to the method of claim 4. Therefore, it is rejected for the same reason as claim 4 above.
Regarding dependent claim 12, it is a medium claim that corresponding to the method of claim 5. Therefore, it is rejected for the same reason as claim 5 above.
Regarding dependent claim 22, it is a medium claim that corresponding to the method of claim 21. Therefore, it is rejected for the same reason as claim 21 above.
Regarding dependent claim 23, it is a system claim that corresponding to the method of claim 21. Therefore, it is rejected for the same reason as claim 21 above.
Claims 7, 14 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Priezzhev, in view of Imhof as applied in claims 1, 8 and 15, further in view of Liu et al. (hereinafter Liu), US 11521122 B2.
Regarding dependent claim 7, the combination of Priezzhev and Imhof teaches all the limitations as set forth in the rejection of claim 1 that is incorporated. The combination of Priezzhev and Imhof does not explicitly disclose
determining a performance value of the machine learning model;
comparing the performance value to a threshold; and
retraining the multivariate model or the machine learning model based on the comparison of the performance value to the threshold.
However, in the same field of endeavor, Liu teaches
determining a performance value of the machine learning model (Col 10, lines 27-29 an interpreter identifies poor performance of the trained model(s) (e.g., either false negatives or false positives));
comparing the performance value to a threshold (Col 10, lines 27-29 identifies poor performance of the trained model(s)); and
retraining the multivariate model or the machine learning model based on the comparison of the performance value to the threshold (Col 10, lines 29-40 the interpreter may correct the results by re-labeling the data and/or retraining the model(s) with a re-labeled dataset. The trained models may be retrained with the user feedback (e.g., updated labeling) to either improve previously-learned interpretation tasks or learn new interpretation tasks. For example, method 100 may iteratively retrain the ML system, returning to block 120, until convergence of the feedback at block 160. The ML system may be retrained with additional model definitions (from block 111), additional training data (from block 112 and/or block 132), and/or feedback for existing models (from block 160)).
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of retraining the trained models with poor performance as suggested in Liu into Priezzhev and Imhof’s system because both of these systems are addressing generating subsurface models that reveal geologic structure. This modification would have been motivated by the desire for more efficient and/or more effective retraining procedures (Liu, [0022]).
Regarding dependent claim 14, it is a medium claim that corresponding to the method of claim 7. Therefore, it is rejected for the same reason as claim 7 above.
Regarding dependent claim 20, it is a system claim that corresponding to the method of claim 7. Therefore, it is rejected for the same reason as claim 7 above.
Response to Arguments
Applicant's arguments filed 09/18/2025 have been fully considered. Each of applicant’s remarks is set forth, followed by examiner’s response.
(1) Regarding to 35 U.S.C 101 rejection, Applicant argues it is noted that the Office repeatedly asserts, for almost every clause in the claims, that "This step for <claimed activity> is practically implementable in the human mind with the aid of a pen and paper and is understood to be a recitation of a mental process." In many instances, this assertion is incorrect and overly broad. Two examples include the claimed activities of generating a geophysical age model, and generating a predicted lithology volume. Neither of these actions can be performed entirely within the human mind, or with the use of a pencil and paper. The operations involved are far too complex, involving thousands, and even millions, of calculations.
As to point (1), Examiner respectfully disagrees. The claim does not place any limits and provide any details about how a geophysical age model and a predicted lithology volume are generated and the plain meaning of “generating” encompasses mental observations or evaluations based on judgment to generate a geophysical age model and a predicted lithology volume. The recited processor or system is recited at a high level of generality, i.e., as a generic computer performing generic computer functions.
(2) Applicant further argues in step 2A, prong 2, in the instant Application, it is noted that "Incorporating a geophysical age model for a post stack seismic reflection volume into the training of the machine learning algorithm improves the accuracy of the lithology prediction of the subterranean formation throughout a post-stack seismic reflection volume within the area of interest, reducing noise. Using a geophysical age model also generates realistic geological bodies, for example, parasequences and progradation trends. Such accuracy in lithology prediction provides a better understanding of subterranean formations which aids in the determination of where, if at all, to locate a wellsite, for example, for maximum production and storage within a formation of a hydrocarbon, water, or any other fluid (including a liquid or gas) or rock type." Application, para. [0018]. That is, the claimed incorporation of geophysical age trace information and lithology labels into the process of predicting lithology using seismic data and machine learning improves the overall accuracy of lithology prediction. Therefore, even if a judicial exception were recited in the claims (which the Applicant asserts is not the case), it is evident that the independent claims, as a whole, integrate the recited judicial exception into a practical application of that exception, enabling more accurate lithology prediction.
As to point (2), Examiner respectfully disagrees. In step 2A, prong 2, This part of the eligibility analysis evaluates whether the claim as a whole integrates the recited judicial exception into a practical application of the exception. This evaluation is performed by (1) identifying whether there are any additional elements recited in the claim beyond the judicial exception, and (2) evaluating those additional elements individually and in combination to determine whether the claim as a whole integrates the exception into a practical application. See MPEP 2106.04(d). As discussed above with respect to claim 1, “A non-transitory computer readable storage medium storing one or more instructions, that when executed by a processor, cause the processor to; An information handling system comprising: a memory; a processor coupled to the memory, wherein the memory comprises one or more instructions executable by the processor to” amount to components of a general purpose computer that applies a judicial exception, by use of conventional computer functions (see MPEP § 2106.05(b)). One way to determine integration into a practical application is when the claimed invention improves the functioning of a computer or improves another technology or technical field. To evaluate an improvement to a computer or technical field, the specification must set forth an improvement in technology and the claim itself must reflect the disclosed improvement. See MPEP 2106.04(d)(1) and 2106.05(a). The consideration of whether the claim as a whole includes an improvement to a computer or to a technological field requires an evaluation of the specification and the claim to ensure that a technical explanation of the asserted improvement is present in the specification, and that the claim reflects the asserted improvement. See MPEP 2106.04(d)(1) and 2106.05(a). The claim does not place any limits and provide any details about how incorporating a geophysical age model for a post stack seismic reflection volume into the training of the machine learning algorithm improves the accuracy of the lithology prediction of the subterranean formation throughout a post-stack seismic reflection volume within the area of interest, reducing noise. Thus, the claims are patent ineligible and are rejected under 35 U.S.C. 101 as detailed in the rejections set forth above.
(3) Applicant’s prior art arguments with respect to the pending claims have been considered but they are moot in view of the new ground(s) of rejections presented above.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AMY P HOANG whose telephone number is (469)295-9134. The examiner can normally be reached M-TH 8:30-5:00PM.
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, JENNIFER WELCH can be reached at 571-272-7212. 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.
/AMY P HOANG/ Examiner, Art Unit 2143
/JENNIFER N WELCH/ Supervisory Patent Examiner, Art Unit 2143
Prosecution Insights