DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . This action is responsive to the Application filed on 01/26/2024. Claims 1-20 are pending in the case. Claims 1, 9, and 16 are independent claims.
Claim Rejections - 35 U.S.C. § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. §§ 102 and 103 (or as subject to pre-AIA 35 U.S.C. §§ 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. § 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1, 2, 9, and 10 are rejected under 35 U.S.C. § 102(a)(1) as being anticipated by Lee et al. (U.S. Pat. App. Pub. No. 2021/0190364, hereinafter Lee).
As to independent claim 1, Lee discloses:
A computer system for improving automated surrogate training performance by incorporating simulator information, the computer system comprising:
a memory, and a processor, the processor configured for (Paragraph 93, "a processor 406 and memory 408"):
performing a simulation of a system being modeled (Paragraph 62, "Simulated experience data is generated using a dynamic model of the HVAC system);
identifying, based on the simulation of the system being modeled, information about the system being modeled (Paragraph 64, "The simulated experience data may be data generated by a prediction model of the particular HVAC system to predict future states and rewards of the system." Paragraph 63, "experience data can generally include, but is not limited to, the current state of a system at a given time, one or more actions performed by the controller in response to the current state of the system, a future or resultant state of the system caused by the performed action, and/or a determined reward responsive to performing the action in the current state. Experience data may also include other values, such as other valuation metrics or error measurements." Paragraph 163, "Time series data may allow modeling systems or analytic systems to correlate data in time and identify data trends over time for either model training or execution.");
modifying an architecture of a surrogate of the system being modeled, wherein the architecture of the surrogate is modified to incorporate the identified information about the system being modeled (Paragraph 146, "The overall architecture of the DNN model
may mathematically partition the overall state X of the system into substates XC for the controller and xp for the physics, each with
corresponding outputs yc and yp." Paragraph 177, "RL model 606 may be configured in some embodiments with quantized states or actions. Quantized states may reduce the complexity of the input space (i.e., number of states, number of potential actions, etc.). Quantization may be defined by the structure of RL model 606."); and
training the surrogate with the information about the system being modeled to generate a final surrogate (Paragraph 168, "Surrogate models are generally designed to simulate how a particular system may react to a given input. The surrogate model can include a DNN of any configuration." Paragraph 168, "Surrogate models can be retrained over time to produce more accurate results").
As to dependent claim 2, Lee discloses updating the identified information about the system being modeled during a training process for the surrogate as more information is learned through a sampling process (Paragraph 48, "the one or more processors are further caused to sample the second simulated experience data according to a sampling function to retrain the DRL model").
As to independent claim 9, Lee discloses:
A method for improving automated surrogate training performance by incorporating simulator information, the method comprising:
performing a simulation of a system being modeled (Paragraph 62, "Simulated experience data is generated using a dynamic model of the HVAC system);
identifying, based on the simulation of the system being modeled, information about the system being modeled (Paragraph 64, "The simulated experience data may be data generated by a prediction model of the particular HVAC system to predict future states and rewards of the system." Paragraph 63, "experience data can generally include, but is not limited to, the current state of a system at a given time, one or more actions performed by the controller in response to the current state of the system, a future or resultant state of the system caused by the performed action, and/or a determined reward responsive to performing the action in the current state. Experience data may also include other values, such as other valuation metrics or error measurements." Paragraph 163, "Time series data may allow modeling systems or analytic systems to correlate data in time and identify data trends over time for either model training or execution.');
modifying an architecture of a surrogate of the system being modeled, wherein the architecture of the surrogate is modified to incorporate the identified information about the system being modeled (Paragraph 146, "The overall architecture of the DNN model may mathematically partition the overall state X of the system into substates XC for the controller and xp for the physics, each with corresponding outputs yc and yp." Paragraph 177, "RL model 606 may be configured in some embodiments with quantized states or actions. Quantized states may reduce the complexity of the input space (i.e., number of states, number of potential actions, etc.). Quantization may be defined by the structure of RL model 606."); and
training the surrogate with the information about the system being modeled to generate a final surrogate (Paragraph 168, "Surrogate models are generally designed to simulate how a particular system may react to a given input. The surrogate model can include a DNN of any configuration." Paragraph168, "Surrogate models can be retrained over time to produce more accurate results").
As to dependent claim 10, Lee discloses updating the identified information about the system being modeled during a training process for the surrogate as more information is learned through a sampling process (Paragraph 48, "the one or more processors are further caused to sample the second simulated experience data according to a sampling function to retrain the DRL model").
Claim Rejections - 35 U.S.C. § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. §§ 102 and 103 (or as subject to pre-AIA 35 U.S.C. §§ 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. § 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102 of this title, 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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant are advised of the obligation under 37 C.F.R. § 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. § 102(b)(2)(C) for any potential 35 U.S.C. § 102(a)(2) prior art against the later invention.
Claims 3 and 11 are rejected under 35 U.S.C. § 103 as being unpatentable over Lee in view of Ozturk et al. (Ozturk, Mustafa C., Dongming Xu, and Jose C. Principe. "Analysis and design of echo state networks." Neural computation 19, no. 1 (2007): 111-138, hereinafter Ozturk).
As to dependent claim 3, the rejection of claim 1 is incorporated.
Lee does not appear to expressly teach the identified information about the system being modeled includes average Jacobian norms, Jacobian eigenvalues, a maximum value of at least one state over time, or a minimum value of at least one state over time.
Ozturk teaches the identified information about the system being modeled includes average Jacobian norms, Jacobian eigenvalues, a maximum value of at least one state over time, or a minimum value of at least one state over time (Page 120, paragraph 2, "Then the Jacobian matrix and the eigenvalues are calculated using equation 2.5.").
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the modeling of Lee to include the Jacobian norms of Ozturk to improve the surrogate architecture design (see Ozturk page 120, paragraph 2).
As to dependent claim 11, the rejection of claim 9 is incorporated.
Lee does not appear to expressly teach the identified information about the system being modeled includes average Jacobian norms, Jacobian eigenvalues, a maximum value of at least one state over time, or a minimum value of at least one state over time.
Ozturk teaches the identified information about the system being modeled includes average Jacobian norms, Jacobian eigenvalues, a maximum value of at least one state over time, or a minimum value of at least one state over time (Page 120, paragraph 2, "Then the Jacobian matrix and the eigenvalues are calculated using equation 2.5").
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the modeling of Lee to include the Jacobian norms of Ozturk to improve the surrogate architecture design (see Ozturk page 120, paragraph 2).
Claims 4-8 and 12-15 are rejected under 35 U.S.C. § 103 as being unpatentable over Lee in view of Anantharaman et al. (Anantharaman, Ranjan, Yingbo Ma, Shashi Gowda, Chris Laughman, Viral Shah, Alan Edelman, and Chris Rackauckas. "Accelerating simulation of stiff nonlinear systems using continuous-time echo state networks." arXiv preprint arXiv:2010.04004 (2020), hereinafter Anantharaman).
As to dependent claim 4, the rejection of claim 1 is incorporated.
Lee does not appear to expressly teach the surrogate includes a reservoir that is constructed by exciting a fixed neural network layer with a chosen input, wherein a response of the fixed neural network evolves over time.
Anantharaman teaches the surrogate includes a reservoir that is constructed by exciting a fixed neural network layer with a chosen input, wherein a response of the fixed neural network evolves over time (Page 3, column 1, paragraph 3, "Echo State Networks (ESNs) are a reservoir computing framework which projects signals from higher dimensional spaces defined by the dynamics of a fixed non-linear system called a "reservoir").
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the modeling of Lee to include the reservoir computing of Anantharaman to improve the surrogate accuracy and efficiency (see Anantharaman page 3, column 1, paragraph 3).
As to dependent claim 5, Lee does not appear to expressly teach dynamics of the reservoir of the surrogate are scaled by a factor that represents a time scale associated with dynamics of the system being modeled such that the surrogate uses the time scale associated with dynamics of the system being modeled, or the dynamics of the reservoir of the surrogate are adjusted to introduce periodicity in the surrogate.
Anantharaman teaches dynamics of the reservoir of the surrogate are scaled by a factor that represents a time scale associated with dynamics of the system being modeled such that the surrogate uses the time scale associated with dynamics of the system being modeled, or the dynamics of the reservoir of the surrogate are adjusted to introduce periodicity in the surrogate (Page 3, column 2, paragraph 4, "The CTESN of with reservoir dimension NR is defined as r 0 = f(Ar + Whybx(p t)), (3) x(t) = g(Woutr(t)), (4) where A is a fixed sparse random matrix of dimension NR X NR and Whyb is a fixed random dense matrix of dimensions NR X N." Page 4, column 1, paragraph 4, "Another advantage is the ability to use time stepping information from the solver during training. As noted before, not only are step sizes chosen adaptively based on minimizing a local error estimate to a specified tolerance (Shampine and Gear 1979), but they also adapt to concentrate around the most stiff and numerically difficult time points of the model by incorporating the Newton convergence into the rejection framework. These timestamps thus provide heuristic snapshots of the most important points for training the least squares fit, whereas snapshots from uniform time steps may skip over many crucial aspects of the dynamics.").
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the modeling of Lee to include the reservoir computing of Anantharaman to improve the surrogate accuracy and efficiency (see Anantharaman page 3, column 1, paragraph 3).
As to dependent claim 6, the rejection of claim 1 is incorporated.
Lee does not appear to expressly teach the surrogate is a continuous-time echo-state network, a neural network, or a physics-informed neural network.
Anantharaman teaches the surrogate is a continuous-time echo-state network, a neural network, or a physics-informed neural network (Page 3, column 2, paragraph 4, "we introduce a new variant of ESNs, which we call continuous-time echo state networks (CTESNs)").
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the modeling of Lee to include the reservoir computing of Anantharaman to improve the surrogate accuracy and efficiency (see Anantharaman page 3, column 1, paragraph 3).
As to dependent claim 7, Lee does not appear to expressly teach when the surrogate is a physics-informed neural network, the physics-informed neural network is constrained by using a sigmoid activation function.
Anantharaman teaches when the surrogate is a physics-informed neural network, the physics-informed neural network is constrained by using a sigmoid activation function (Page 3, column 2, paragraph 4. Page 4 column 1, paragraph 1, "The CTESN of with reservoir dimension NR is defined as r 0 = f(Ar + Whybx(p t)), (3) x(t) = g(Woutr(t)), (4) where A is a fixed sparse random matrix of dimension NR X NR and Whyb is a fixed random dense matrix of dimensions NR xN. The term Whybx(p t) represents a "hybrid" term that incorporates physics information into the reservoir." Page 3, column 1, paragraph 3, "For a NRdimensional reservoir, the reservoir equation is given by: m+1 = f(Arn + Wf bxn), (1) where f is a chosen activation function (like tanh or sigmoid)." Page 4, column 1, paragraph 1, "in this study we choose = tanh").
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the modeling of Lee to include the reservoir computing of Anantharaman to improve the surrogate accuracy and efficiency (see Anantharaman page 3, column 1, paragraph 3).
As to dependent claim 8, Lee does not appear to expressly teach the constrained physics-informed neural network is scaled by a scale factor of s.
Anantharaman teaches the constrained physics-informed neural network is scaled by a scale factor of s (Page 3, column 1, paragraph 3, "where f is a chosen activation function (like tanh or sigmoid)." According to this authority and as is obvious to one skilled in the art, the activation function can be scaled and padded to restrict its output to the requisite rang).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the modeling of Lee to include the reservoir computing of Anantharaman to improve the surrogate accuracy and efficiency (see Anantharaman page 3, column 1, paragraph 3).
As to dependent claim 12, the rejection of claim 9 is incorporated.
Lee does not appear to expressly teach the surrogate includes a reservoir that is constructed by exciting a fixed neural network layer with a chosen input, with a response of the fixed neural network evolves over time.
Anantharaman teaches the surrogate includes a reservoir that is constructed by exciting a fixed neural network layer with a chosen input, with a response of the fixed neural network evolves over time (Page 3, column 1, paragraph 3, "Echo State Networks (ESNs) are a reservoir computing framework which projects signals from higher dimensional spaces defined by the dynamics of a fixed non-linear system called a "reservoir").
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the modeling of Lee to include the reservoir computing of Anantharaman to improve the surrogate accuracy and efficiency (see Anantharaman page 3, column 1, paragraph 3).
As to dependent claim 13, Lee does not appear to expressly teach dynamics of the reservoir of the surrogate are scaled by a factor that represents a time scale associated with dynamics of the system being modeled such that the surrogate uses the time scale associated with dynamics of the system being modeled, or the dynamics of the reservoir of the surrogate are adjusted to introduce periodicity in the surrogate.
Anantharaman teaches dynamics of the reservoir of the surrogate are scaled by a factor that represents a time scale associated with dynamics of the system being modeled such that the surrogate uses the time scale associated with dynamics of the system being modeled, or the dynamics of the reservoir of the surrogate are adjusted to introduce periodicity in the surrogate (Page 3, column 2, paragraph 4 "The CTESN of with reservoir dimension NR is defined as r 0 = f(Ar + Whybx(p t)), (3) x(t) = g(Woutr(t)), (4) where A is a fixed sparse random matrix of dimension NR X NR and Whyb is a fixed random dense matrix of dimensions NR X N. " Page 4, column 1, paragraph 4, "Another advantage is the ability to use time stepping information from the solver during training. As noted before, not only are step sizes chosen adaptively based on minimizing a local error estimate to a specified tolerance (Shampine and Gear 1979), but they also adapt to concentrate around the most stiff and numerically difficult time points of the model by incorporating the Newton convergence into the rejection framework. These timestamps thus provide heuristic snapshots of the most important points for training the least squares fit, whereas snapshots from uniform time steps may skip over many crucial aspects of the dynamics.”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the modeling of Lee to include the reservoir computing of Anantharaman to improve the surrogate accuracy and efficiency (see Anantharaman page 3, column 1, paragraph 3).
As to dependent claim 14, the rejection of claim 9 is incorporated.
Lee does not appear to expressly teach the surrogate is a continuous-time echo-state network, a neural network, or a physics-informed neural network.
Anantharaman teaches the surrogate is a continuous-time echo-state network, a neural network, or a physics-informed neural network (Page 3, column 2, paragraph 4, "we introduce a new variant of ESNs, which we call continuous-time echo state networks (CTESNs)").
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the modeling of Lee to include the reservoir computing of Anantharaman to improve the surrogate accuracy and efficiency (see Anantharaman page 3, column 1, paragraph 3).
As to dependent claim 15, Lee does not appear to expressly teach when the surrogate is a physics-informed neural network, the physics-informed neural network is constrained by using a sigmoid activation function.
Anantharaman teaches when the surrogate is a physics-informed neural network, the physics-informed neural network is constrained by using a sigmoid activation function (Page 3, column 1, paragraph 3, "For a NRdimensional reservoir, the reservoir equation is given by: rn+1 = f(Arn + Wf bxn), (1) where f is a chosen activation function (like tanh or sigmoid)." Page 4, column 1, paragraph 1, "in this study we choose f = tanh").
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the modeling of Lee to include the reservoir computing of Anantharaman to improve the surrogate accuracy and efficiency (see Anantharaman page 3, column 1, paragraph 3).
Claims 16-20 are rejected under 35 U.S.C. § 103 as being unpatentable over Lee in view of Oztruk and Anantharaman.
As to independent claim 16, Lee teaches:
A system for improving automated surrogate training performance by incorporating simulator information, the computer system comprising:
a memory, and a processor, the processor configured for (Paragraph 93, "a processor 406 and memory 408"):
creating a model of a system being modeled (Paragraph 62, "Simulated experience data is generated using a
dynamic model of the HVAC system");
defining a surrogate having a surrogate architecture for the model of the system being modeled… (Paragraph 23, "the dynamics model is a surrogate model or a simulation model, the surrogate model including a deep neural network." Paragraph 4, "wherein the surrogate model can include a deep neural network");
performing one or more simulations of the model to identify information about the system being modeled (Paragraph 64, "The simulated experience data may be data generated by a prediction model of the particular HVAC system to predict future states and rewards of the system");
identifying, based on the one or more simulations of the model, information about the system being modeled… (Paragraph 64, "The simulated experience data may be data generated by a prediction model of the particular HVAC system to predict future states and rewards of the system." Paragraph 63, "experience data can generally include, but is not limited to, the current state of a system at a given time, one or more actions performed by the controller in response to the current state of the system, a future or resultant state of the system caused by the performed action, and/or a determined reward responsive to performing the action in the current state. Experience data may also include other values, such as other valuation metrics or error measurements." Paragraph 163, "Time series data may allow modeling systems or analytic systems to correlate data in time and identify data trends over time for either model training or execution.", para [0185] "specific samples are chosen based on knowledge of the domain, such as, for example, the maximum, minimum, mean, or standard deviation of one or more values of the experience data.");
generating an improved surrogate by modifying the surrogate architecture using the identified information about the system being modeled from the one or more simulations (Paragraph 146, "The overall architecture of the DNN model may mathematically partition the overall state X of the system into substates XC for the controller and xp for the physics, each with corresponding outputs yc and yp." Paragraph 177, "RL model 606 may be configured in some embodiments with quantized states or actions. Quantized states may reduce the complexity of the input space (i.e., number of states, number of potential actions, etc.). Quantization may be defined by the structure of RL model 606"); and
generating a final surrogate by training the improved surrogate (Paragraph 168, "Surrogate models are generally designed to simulate how a particular system may react to a given input. The surrogate model can include a DNN of any configuration." Paragraph 168, "Surrogate models can be retrained over time to produce more accurate results").
Lee does not appear to expressly teach wherein the identified information about the system includes average Jacobian norms, Jacobian eigenvalues, maximum or minimum values of states of the model over time, mean values of states of the model over time, length of time to run the simulation, maximum of a time series of the model, natural bounds of the model, or periodicity of the model.
Oztruk teaches wherein the identified information about the system includes average Jacobian norms, Jacobian eigenvalues, maximum or minimum values of states of the model over time, mean values of states of the model over time, length of time to run the simulation, maximum of a time series of the model, natural bounds of the model, or periodicity of the model (Page 120, paragraph 2, "Then the Jacobian matrix and the eigenvalues are calculated using equation 2.5").
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the modeling of Lee to include the Jacobian norms of Ozturk to improve the surrogate architecture design (see Ozturk page 120, paragraph 2).
Lee does not appear to expressly teach wherein the surrogate architecture is a CTESN, a neural network, a PINN, or a neural ODE.
Anantharaman teaches wherein the surrogate architecture is a CTESN, a neural network, a PINN, or a neural ODE ((Page 3, column 2, paragraph 4, "we introduce a new variant of ESNs, which we call continuous-time echo state networks (CTESNs)." Page 3, column 2, paragraph 4. Page 4, column 1, paragraph 1, "The CTESN of with reservoir dimension NR is defined as r 0 = f(Ar + Whybx(p t)). (3) x(t) = g(Woutr(t)), (4) where A is a fixed sparse random matrix of dimension NR X NR and Whyb is a fixed random dense matrix of dimensions NR xN. The term Whybx(p t) represents a "hybrid" term that incorporates physics information into the reservoir").
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the modeling of Lee to include the reservoir computing of Anantharaman to improve the surrogate accuracy and efficiency (see Anantharaman page 3, column 1, paragraph 3).
As to dependent claim 17, Lee further teaches updating the identified information about the system being modeled during a training process for the improved surrogate as additional information is learned about the system being modeled through a sampling process (Paragraph 48, "the one or more processors are further caused to sample the second simulated experience data according to a sampling function to retrain the DRL model").
As to dependent claim 18, Anantharaman further teaches the surrogate architecture includes a reservoir constructed by exciting a fixed neural network layer with a chosen input, wherein a response of the fixed neural network evolves over time (Page 3, column 1, paragraph 3, "Echo State Networks (ESNs) are a reservoir computing framework which projects signals from higher dimensional spaces defined by the dynamics of a fixed non-linear system called a "reservoir").
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the modeling of Lee to include the reservoir computing of Anantharaman to improve the surrogate accuracy and efficiency (see Anantharaman page 3, column 1, paragraph 3).
As to dependent claim 19, Anantharaman further teaches dynamics of the reservoir of the surrogate architecture are scaled by a factor that represents a time scale associated with dynamics of the system being modeled such that the surrogate uses the time scale associated with dynamics of the system being modeled (Page 3, column 2, paragraph 4, "The CTESN of with reservoir dimension NR is defined as r 0 = f(Ar + Whybx(p t)), (3) x(t) = g(Woutr(t)), (4) where A is a fixed sparse random matrix of dimension NR X NR and Whyb is a fixed random dense matrix of dimensions NR X N." Page 4, column, 1 paragraph 4, "Another advantage is the ability to use time stepping information from the solver during training. As noted before, not only are step sizes chosen adaptively based on minimizing a local error estimate to a specified tolerance (Shampine and Gear 1979), but they also adapt to concentrate around the most stiff and numerically difficult time points of the model by incorporating the Newton convergence into the rejection framework. These timestamps thus provide heuristic snapshots of the most important points for training the least squares fit, whereas snapshots from uniform time steps may skip over many crucial aspects of the dynamics.).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the modeling of Lee to include the reservoir computing of Anantharaman to improve the surrogate accuracy and efficiency (see Anantharaman page 3, column 1, paragraph 3).
As to dependent claim 20, Anantharaman further teaches the dynamics of the reservoir of the surrogate architecture are modified to introduce periodicity in the surrogate (Page 4, column 1, paragraph 4, "Another advantage is the ability to use time stepping information from the solver during training. As noted before, not only are step sizes chosen adaptively based on minimizing a local error estimate to a specified tolerance (Shampine and Gear 1979), but they also adapt to concentrate around the most stiff and numerically difficult time points of the model by incorporating the Newton convergence into the rejection framework. These timestamps thus provide heuristic snapshots of the most important points for training the least squares fit, whereas snapshots from uniform time steps may skip over many crucial aspects of the dynamics).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the modeling of Lee to include the reservoir computing of Anantharaman to improve the surrogate accuracy and efficiency (see Anantharaman page 3, column 1, paragraph 3).
Citation of Pertinent Prior Art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Van Gils et al. (U.S. Pat. App. Pub. No. 2022/0122207) teaches license-free surrogate model generation. A method, node, and computer-readable medium are provided to convert a proprietary model to a tool-agnostic surrogate model using a functional mockup interface (FMI) standard. A proprietary model is received as a functional-mockup unit (FMU) An automated dataset generation is performed on the FMU to create input/output datasets based on design of experiments and input requirements. Steady-state operational-points are determined. The tool-agnostic surrogate model is generated based on the input/output datasets and the steady-state operational-points. The tool-agnostic surrogate model is output as an output FMU model that is free of licensing requirements of a license for the proprietary model. The tool-agnostic surrogate model may be a steady-state surrogate model, a dynamic surrogate model, or a combination thereof.
Conclusion
The prior art made of record and not relied upon is considered pertinent to Applicant's disclosure. Applicant is required under 37 C.F.R. § 1.111(c) to consider these references fully when responding to this action.
It is noted that any citation to specific pages, columns, lines, or figures in the prior art references and any interpretation of the references should not be considered to be limiting in any way. A reference is relevant for all it contains and may be relied upon for all that it would have reasonably suggested to one having ordinary skill in the art. In re Heck, 699 F.2d 1331, 1332-33, 216 U.S.P.Q. 1038, 1039 (Fed. Cir. 1983) (quoting In re Lemelson, 397 F.2d 1006, 1009, 158 U.S.P.Q. 275, 277 (C.C.P.A. 1968)).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Casey R. Garner whose telephone number is 571-272-2467. The examiner can normally be reached Monday to Friday, 8am to 5pm, Eastern Time.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Alexey Shmatov can be reached on 571-270-3428. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from Patent Center and the Private Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from Patent Center or Private PAIR. Status information for unpublished applications is available through Patent Center and Private PAIR to authorized users only. Should you have questions about access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
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) Form at https://www.uspto.gov/patents/uspto-automated- interview-request-air-form.
/Casey R. Garner/Primary Examiner, Art Unit 2123
Prosecution Insights