Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
The claim limitations being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, are within claims 1-7. These claims specifically state, “a data collection unit”, “a preprocessing unit”, “a derivation unit”, and “a training unit”. These limitations are generic placeholder, both are followed by "configured to" (i.e. functional language), and both lack sufficient structure, material, or acts for performing the claimed function.
Because these claim limitations are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, they are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitations interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitations to avoid them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitations recite sufficient structure to perform the claimed function so as to avoid them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Claim Rejections - 35 USC § 112
112(A):
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1-7 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claims contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention. Paragraph 0028 denotes that the various units can be program modules in the form of operating systems, application program modules, and other program modules stored in the memory modules, which may include routines, subroutines, programs, objects, components, and data structures for performing specific tasks or executing specific abstract data types. This shows the structure related to the units, but not the algorithm needed to perform the various steps within the claims. There is no clear link between the units and the algorithm. Therefore, the claims are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ) for lack of written description.
112(B):
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-7 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being incomplete for omitting essential structural cooperative relationships of elements, such omission amounting to a gap between the necessary structural connections. See MPEP § 2172.01. The omitted structural cooperative relationships are: Specialized computer functions and an algorithm.
For claims 1-7, the claim limitations use specialized computer functions such as “ a data collection unit”, “a preprocessing unit”, “a derivation unit”, and “a training unit”. These units can be program modules in the form of operating systems, application program modules, and other program modules stored in the memory modules, and may include routines, subroutines, programs, objects, components, and data structures for performing specific tasks or executing specific abstract data type. The specialized computer functions would require more than just structure, they would need an algorithm for performing the steps, in which there is not a clear link between the function and an algorithm in the spec. Therefore, the claims are indefinite and is rejected under 35 U.S.C. 112(b) or pre-AIA 35 U.S.C. 112, second paragraph.
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, 4, 8, 11, and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Brebner et al, U.S. Patent (US 11726822 B1), filed on March 13th, 2020 in view of Kapteyn et al, NPL (From Physics-Based Models to Predictive Digital Twins via Interpretable Machine Learning), published April 28th, 2020.
With regard to independent claim 1,
Brebner teaches, “An apparatus configured to drive a digital twin model, comprising:” (Col. 13, Lines 60-62 and Col. 178, Lines 31-38; EN: This denotes a system or apparatus that provides digital twin enabled applications). “a data collection unit configured to collect sensing data from a plurality of sensors mapped to a plurality of digital twin models for a target area to be managed;” (Col.78 Lines 33-43, Col. 93 Lines 59-67, Col. 94 Lines 1-8, Col. 99 Lines 4-39, and Col. 134 Lines 17-43; EN: This denotes that the generative content system can get samples from a data collection device, in which the data can come from various sensors at particular locations. The application system in combination with a server kit and/or generative content system can use data to generate or enhance digital twins with representations of real-world systems, in which multiple digital twins can be embedded in a larger digital twin).
“a preprocessing unit configured to generate a hierarchical data set assigned with a weight by performing a preprocessing process on the collected sensing data;” (Col. 81, Lines 8-23 and Col. 82, Lines 9-26; EN: This denotes the creation of sparse data sets based on partitioning a hierarchical graph in which the data set has edge nodes that are marked to be used for different computations based on the partition scheme. The data set may have arbitrary or predefined weighted elements associated with the graph node hierarchy, classes, and node properties due to class dependent algorithms).
“… corresponding to the hierarchical data set …” (Col. 81, Lines 8-23 and Col. 82, Lines 9-26; EN: This denotes the creation of sparse data sets based on partitioning a hierarchical graph in which the data set has edge nodes that are marked to be used for different computations based on the partition scheme. The data set may have arbitrary or predefined weighted elements associated with the graph node hierarchy, classes, and node properties due to class dependent algorithms)
However, Brebner fails to disclose “and a derivation unit configured to derive information about at least one digital twin model … among the plurality of digital twin models by using a pre-trained classification model”
Kapteyn teaches, “and a derivation unit configured to derive information about at least one digital twin model … by using a pre-trained classification model” (Pg. 6, Section: 4, Subsection A; EN: This denotes training an offline optimal decision tree with training data generated from a physics-based model library. This physics-based model library can use models to simulate sensor responses to various assets states, such as rare real-world events and historical events. Once the optimal decision tree is trained offline it is then used as a classification tree that acts as a data-driven model selector, which looks at observed data and chooses which physics-based model best matches the physical asset to make or update a digital twin).
Brebner and Kapteyn are considered to be analogous to the claimed invention due to the fact that they both are generally related to development and use of digital twins. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to modify the use of sensors to generate both hierarchical data sets and digital twins of Brebner with the offline training and retrieval of information from digital twins of Kapteyn. One would be motivated to do so to improve the generation and use of digital twins. By combining these modifications, one would be able to not only generate and use multiple connected digital twins at the same time but would also be able to train these digital twins on the same data and retrieve information regarding one of the digital twins.
With regard to dependent claim 4,
Brebner teaches, “The apparatus of Claim 1, further comprising: a training unit configured to generate a training data set by …” (Col. 97, Lines: 58-67 and Col. 98, Lines: 1-20; EN: This denotes that the generative content system can generate training data for various machine learning models used by various types of systems). “corresponding to the hierarchical data set among the plurality of digital twin models with the hierarchical data set,” (Col.78 Lines 33-43, Col. 81 Lines 8-23, Col. 82 Lines 9-26, and Col. 134 Lines17-43; EN: This denotes the creation of sparse data sets based on partitioning a hierarchical graph in which the data set has edge nodes that are marked to be used for different computations based on the partition scheme. The data set may have arbitrary or predefined weighted elements associated with the graph node hierarchy, classes, and node properties due to class dependent algorithms. It also denotes the generation of multiple digital twins, which can be embedded into larger digital twins). “and train the classification model based on the generated training data set” (Col. 97, Lines: 58-67 and Col. 98, Lines: 1-20; EN: This denotes that the generative content system can train various models using the collected and generated data).
Brebner fails to disclose “… combining class information of a digital twin model” and “… the plurality of digital twin models …”.
Kapteyn teaches, ““… combining class information of a digital twin model” (: Pg. 6, Section: 4, Subsection A; EN: This denotes training an offline optimal decision tree with training data generated from a physics-based model library. This physics-based model library can use models to simulate sensor responses to various assets states, such as rare real-world events and historical events. Once the optimal decision tree is trained offline it is then used as a classification tree that acts as a data-driven model selector, which looks at observed data and chooses which physics-based model best matches the physical asset to make or update a digital twin).
With regard to independent claim 8,
This claim is similar in scope to claim 1 and is rejected under a similar rationale.
With regard to dependent claim 11,
This claim is similar in scope to claim 4 and is rejected under a similar rationale.
With regard to independent claim 15,
Brebner teaches “A non-transitory computer-readable medium storing computer program including a sequence of instructions to derive a digital twin model, which when executed by a computing device, causes the computing device to:” (Col. 178, Lines 61-66; EN: This denotes non-transitory storage medium that provides instructions to execute and derive digital twin enabled applications). The rest of this claim is similar in scope to claim 1 and is rejected under a similar rationale.
Claims 2 and 9 are rejected under 35 U.S.C. 103 as being unpatentable over Brebner et al, U.S. Patent (US 11726822 B1), filed on March 13th, 2020 in view of Kapteyn et al, NPL (From Physics-Based Models to Predictive Digital Twins via Interpretable Machine Learning), published April 28th, 2020 as applied to claims 1 and 8 above, and further in view of Kim et al, NPL (A weight-adjusted voting algorithm for ensembles of classifiers), published on March 27th, 2011.
With regard to dependent claim 2,
As discussed above, Brebner in view of and Kapteyn, teaches the apparatus of claim 1. Brebner teaches, “The apparatus of Claim 1, wherein the preprocessing unit assigns the generated hierarchical data set… corresponding to the plurality of digital twin models,” (Col.78 Lines 33-43, Col. 81 Lines 8-23, Col. 82 Lines 9-26, and Col. 134 Lines 17-43; EN: This denotes the creation of sparse data sets based on partitioning a hierarchical graph in which the data set has edge nodes that are marked to be used for different computations based on the partition scheme. The data set may have arbitrary or predefined weighted elements associated with the graph node hierarchy, classes, and node properties due to class dependent algorithms. It also denotes the generation of multiple digital twins, which can be embedded into larger digital twins). “…the hierarchical data set…” (Col. 81, Lines 8-23 and Col. 82, Lines 9-26; EN: This denotes the creation of sparse data sets based on partitioning a hierarchical graph in which the data set has edge nodes that are marked to be used for different computations based on the partition scheme. The data set may have arbitrary or predefined weighted elements associated with the graph node hierarchy, classes, and node properties due to class dependent algorithms).
Brebner fails to disclose “…with a plurality of optimum weight sets…” and “and the derivation unit inputs … assigned with the optimum weight sets into the classification model”.
Kapteyn teaches, “and the derivation unit inputs…” (Pg. 6, Section: 4, Subsection A; EN: This denotes training an offline optimal decision tree with training data generated from a physics-based model library. This physics-based model library can use models to simulate sensor responses to various assets states, such as rare real-world events and historical events. Once the optimal decision tree is trained offline it is then used as a classification tree that acts as a data-driven model selector, which looks at observed data and chooses which physics-based model best matches the physical asset to make or update a digital twin).
However, Brebner and Kapteyn fail to disclose “…with a plurality of optimum weight sets…” and “… assigned with the optimum weight sets into the classification model”.
Kim teaches, “…with a plurality of optimum weight sets…” (Pg.438, Section: 2.1, paragraph 2; EN: This denotes finding the optimal weights for both classifiers and instances). “…assigned with the optimum weight sets into the classification model” (Pg.438, Section: 2.1, paragraph 2; EN: This denotes finding the optimal weights for both classifiers and instances).
Brebner, Kapteyn, and Kim are considered to be analogous to the claimed invention due to the fact that they are all generally related to development and use of various neural networks. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to modify the use of sensors to generate both hierarchical data sets and digital twins of Brebner and the offline training and retrieval of information from digital twins of Kapteyn with the weight vectors used for classifiers and instances of Kim. One would be motivated to do so to improve the generation and use of digital twins and classification models. By combining these modifications, one would be able to not only generate and use multiple connected digital twins at the same time but would also be able to train these digital twins on the same classified observation data and retrieve information regarding one of the digital twins.
With regard to dependent claim 9,
This claim is similar in scope to claim 2 and is rejected under a similar rationale.
Claims 3 and 10 are rejected under 35 U.S.C. 103 as being unpatentable over Brebner et al, U.S. Patent (US 11726822 B1), filed on March 13th, 2020 in view of Kapteyn et al, NPL (From Physics-Based Models to Predictive Digital Twins via Interpretable Machine Learning), published April 28th, 2020, and Kim et al, NPL (A weight-adjusted voting algorithm for ensembles of classifiers), published on March 27th, 2011 as applied to claims 1, 2, 8, and 9 above, and further in view of Ritto et al, NPL (Digital twin, physics-based model, and machine learning applied to damage detection in structures), published on June 14th, 2020.
With regard to dependent claim 3,
As discussed above, Brebner in view of Kapteyn teaches the apparatus of claim 1. Brebner teaches, “…to the hierarchical data set” (Col. 81, Lines 8-23 and Col. 82, Lines 9-26; EN: This denotes the creation of sparse data sets based on partitioning a hierarchical graph in which the data set has edge nodes that are marked to be used for different computations based on the partition scheme. The data set may have arbitrary or predefined weighted elements associated with the graph node hierarchy, classes, and node properties due to class dependent algorithms). “…the plurality of digital twin models…” (Col.78 Lines 33-43 and Col. 134 Lines 17-43; EN: This denotes that the application system in combination with a server kit and/or generative content system can use data to generate or enhance digital twins with representations of real-world systems, in which multiple digital twins can be embedded in a larger digital twin).
However, Brebner fails to disclose “The apparatus of Claim 2, wherein the derivation unit derives class information of a digital twin model corresponding…”, “assigned with the optimum weight sets … by using the classification model”, and “and a probability value for the digital twin model”.
Kapteyn teaches, “The apparatus of Claim 2, wherein the derivation unit derives class information of a digital twin model corresponding…” (Pg. 6, Section: 4, Subsection A; EN: This denotes training an offline optimal decision tree with training data generated from a physics-based model library. This physics-based model library can use models to simulate sensor responses to various assets states, such as rare real-world events and historical events. Once the optimal decision tree is trained offline it is then used as a classification tree that acts as a data-driven model selector, which looks at observed data and chooses which physics-based model best matches the physical asset to make or update a digital twin).
However, Brebner and Kapteyn fail to disclose “assigned with the optimum weight sets … by using the classification model” and “and a probability value for the digital twin model”.
Kim teaches, “assigned with the optimum weight sets among … by using the classification model” (Pg.438, Section: 2.1, paragraph 2; EN: This denotes finding the optimal weights for both classifiers and instances).
However, Brebner, Kapteyn, and Kim fail to disclose “and a probability value for the digital twin model”.
However, Brebner, Kapteyn, and Kim fail to disclose “and a probability value for the digital twin model”.
Ritto teaches, “and a probability value for the digital twin model” (Pg. 14-16, Section 4.6; EN: This denotes the probability of a class or situation occurring that displays the damage or chance of failure at specific location).
Brebner, Kapteyn, Kim, and Ritto are considered to be analogous to the claimed invention due to the fact that they are all generally related to development and use of various neural networks. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to modify the use of sensors to generate both hierarchical data sets and digital twins of Brebner, the offline training and retrieval of information from digital twins of Kapteyn, and the weight vectors used for classifiers and instances of Kim with the discrete physics-based computational model being employed to investigate several damage scenarios. One would be motivated to do so to improve the generation and use of digital twins and classification models. By combining these modifications, one would be able to generate and use multiple connected digital twins at the same time, train digital twins on the same classified observation data, retrieve information regarding one of the digital twins, and disclose the probability of a situation occurring that ends with damage at specific locations or something failing.
With regard to dependent claim 10,
This claim is similar in scope to claim 3 and is rejected under a similar rationale.
Claims 5 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Brebner et al, U.S. Patent (US 11726822 B1), filed on March 13th, 2020 in view of Kapteyn et al, NPL (From Physics-Based Models to Predictive Digital Twins via Interpretable Machine Learning), published April 28th, 2020 as applied to claims 1, 4, 8, and 11 above, and further in view of Kirkpatrick et al, NPL (Overcoming catastrophic forgetting in neural networks), published on January 25th, 2017.
With regard to dependent claim 5,
As discussed above, Brebner in view of Kapteyn teaches the apparatus of claim 1. Brebner teaches, “The apparatus of Claim 4, wherein the preprocessing unit assigns the training data set with…” (Col. 97, Lines: 58-67 and Col. 98, Lines: 1-20; EN: This denotes that the generative content system can both generate and use training data to train various models using the collected and generated data). “and the training unit … into the classification model,” (Col. 97, Lines: 58-67 and Col. 98, Lines: 1-20; EN: This denotes that the generative content system can both generate and use training data to train various models using the collected and generated data). “and trains the classification model…” (Col. 97, Lines: 58-67 and Col. 98, Lines: 1-20; EN: This denotes that the generative content system can train various models using the collected and generated data).
However, Brebner fails to disclose “…a plurality of test weight sets”, “… inputs a plurality of training data sets assigned with the plurality of test weight sets …,”, and “…to derive an optimum coefficient value”.
Kirkpatrick teaches, “…a plurality of test weight sets” (Pg. 3-4, Section 2.1; EN: This denotes that through the use of elastic weight consolidation (EWC) a deep neural network could be trained for various tasks, where each task could have its own dataset and weight. The weight for each task can either be similar or different). “… inputs a plurality of training data sets assigned with the plurality of test weight sets …,” (Pg. 3-4, Section 2.1; EN: This denotes that through the use of elastic weight consolidation (EWC) a deep neural network could be trained for various tasks, where each task could have its own dataset and weight. The weight for each task can either be similar or different). “…to derive an optimum coefficient value” (Pg. 2-3, Section 2; EN: This denotes calculating the minimum loss for task B).
Brebner, Kapteyn, and Kirkpatrick are considered to be analogous to the claimed invention due to the fact that they are all generally related to development and use of neural networks. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to modify the use of sensors to generate both hierarchical data sets and digital twins of Brebner and the offline training and retrieval of information from digital twins of Kapteyn with neural networks learning tasks in a sequential fashion of Kirkpatrick. One would be motivated to do so to improve the generation and use of digital twins. By combining these modifications, one would be able to not only generate and use multiple connected digital twins at the same time but would also be able to train these digital twins on the same data, retrieve information regarding one of the digital twins, and allow digital twins to learn various weights from previous task that are similar or different to current task.
With regard to dependent claim 12,
This claim is similar in scope to claim 5 and is rejected under a similar rationale.
Claims 6, 7, 13, and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Brebner et al, U.S. Patent (US 11726822 B1), filed on March 13th, 2020 in view of Kapteyn et al, NPL (From Physics-Based Models to Predictive Digital Twins via Interpretable Machine Learning), published April 28th, 2020, Kim et al, NPL (A weight-adjusted voting algorithm for ensembles of classifiers), published on March 27th, 2011, and Kirkpatrick et al, NPL (Overcoming catastrophic forgetting in neural networks), published on January 25th, 2017 as applied to claims 1, 4, 5, 8, 11, and 12) above, and further in view of Brena et al, NPL (Choosing the Best Sensor Fusion Method: A Machine-Learning Approach), published on April 20th, 2020).
With regard to dependent claim 6,
As discussed above, Brebner in view of Kapteyn teaches the apparatus of claim 1. Brebner teaches, “The apparatus of Claim 5, wherein the preprocessing unit…” (Col. 81, Lines 8-23 and Col. 82, Lines 9-26; EN: This denotes the use of the generative content system which can be classified as a preprocessing unit).
However, Brebner fails to disclose “…derives a training data set corresponding to the optimum coefficient value among the plurality of training data sets assigned with the plurality of test weight sets,” and “and sets a test weight set assigned to the derived training data set as an optimum weight set for a digital twin model corresponding to class information included in the derived training data set”.
Kirkpatrick teaches, “…corresponding to the optimum coefficient value among the plurality of training data sets assigned with the plurality of test weight sets,” (Pg. 2-4, Section: 2 and 2.1; EN: This denotes calculating the minimum loss for task B and that through the use of elastic weight consolidation (EWC) a deep neural network could be trained for various tasks, where each task could have its own dataset and weight. The weight for each task can either be similar or different). “and sets a test weight set…” (Pg. 3-4, Section 2.1; EN: This denotes that through the use of elastic weight consolidation (EWC) a deep neural network could be trained for various tasks, where each task could have its own dataset and weight. The weight for each task can either be similar or different).
However, Brebner and Kim fail to disclose “…derives a training data set…” and “…assigned to the derived training data set as an optimum weight set for a digital twin model corresponding to class information included in the derived training data set”.
Kim teaches, “…an optimum weight set…” (Pg.438, Section: 2.1, paragraph 2; EN: This denotes finding the optimal weights for both classifiers and instances).
However, Brebner, Kirkpatrick, and Kim fail to disclose “…derives a training data set…” and “…for a digital twin model corresponding to class information included in the derived training data set”.
Kapteyn teaches, “…for a digital twin model corresponding to class information…” (Pg. 6, Section: 4, Subsection A; EN: This denotes training an offline optimal decision tree with training data generated from a physics-based model library. This physics-based model library can use models to simulate sensor responses to various assets states, such as rare real-world events and historical events. Once the optimal decision tree is trained offline it is then used as a classification tree that acts as a data-driven model selector, which looks at observed data and chooses which physics-based model best matches the physical asset to make or update a digital twin).
However, Brebner, Kirkpatrick, Kim, and Kapteyn fail to teach “…derives a training data set…” and “…assigned to the derived training data set as … included in the derived training data set”.
Brena teaches, “…derives a training data set…” (Pg. 9, Section: 4.1.2; EN: This denotes the use of 36 derived data sets in the gas domain that were extracted from the Gas Sensor Array Drift (GSAD) data set, which is a reference data set often used in gas classification). “…assigned to the derived training data set as … included in the derived training data set” (Pg. 9, Section: 4.1.2; EN: This denotes the use of 36 derived data sets in the gas domain that were extracted from the Gas Sensor Array Drift (GSAD) data set, which is a reference data set often used in gas classification).
Brebner, Kapteyn, Kirkpatrick, Kim, and Brena are considered to be analogous to the claimed invention due to the fact that they are all generally related to development and use of neural networks. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to modify the use of sensors to generate both hierarchical data sets and digital twins of Brebner, the offline training and retrieval of information from digital twins of Kapteyn, the neural networks learning tasks in a sequential fashion of Kirkpatrick, and the weight vectors used for classifiers and instances of Kim with the multi-sensor fusion method of Brena. One would be motivated to do so to improve the generation and use of digital twins. By combining these modifications, one would be able to generate and use multiple connected digital twins at the same time, train digital twins on the same classified observation data, retrieve information regarding one of the digital twins, allow digital twins to learn various weights from previous task that are similar or different to current task, and allow digital twins to improve the overall accuracy in regards to classifying various damage and failures related to specific areas by utilizing multi-sensor fusion when once sensor isn’t enough to classify the damage or failures.
With regard to dependent claim 7,
As discussed above, Brebner in view of Kapteyn teaches the apparatus of claim 1. Brebner teaches, “The apparatus of Claim 6, wherein the preprocessing unit sets“…for each of the plurality of digital twin models” (Col.78 Lines 33-43, Col. 81, Lines 8-23 and Col. 82, Lines 9-26 and Col. 134 Lines 17-43; EN: This denotes that the application system in combination with a server kit and/or generative content system, which can be classified as a preprocessing unit, can use data to generate or enhance digital twins with representations of real-world systems, in which multiple digital twins can be embedded in a larger digital twin).
However, Brebner fails to disclose “…an optimum weight set for each of the plurality of digital twin models”.
Kim teaches, “…an optimum weight set…” (Pg.438, Section: 2.1, paragraph 2; EN: This denotes finding the optimal weights for both classifiers and instances).
With regard to dependent claim 13,
This claim is similar in scope to claim 6 and is rejected under a similar rationale.
With regard to dependent claim 14,
This claim is similar in scope to claim 7 and is rejected under a similar rationale.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SETH CAPRIANO-UMARI SHELTON whose telephone number is (571)270-0213. The examiner can normally be reached 8am-5pm.
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, Matthew Ell can be reached at (571) 270-3264. 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.
/SETH CAPRIANO-UMARI SHELTON/Examiner, Art Unit 2141
/MATTHEW ELL/Supervisory Patent Examiner, Art Unit 2141