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 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 thereof, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C 101 because the claimed invention is directed to a judicial exception without significantly more.
Claim 1.
STEP 1: Yes. The claim is directed to a “method” which is a process.
STEP 2A PRONE ONE:
The claim recites multiple mental processes and mathematical concepts.
determining a prediction model and one or more prediction model parameters associated with the optimization event;
This describes an observation, evaluation, judgment or opinion that can be done in the mind or with aid of pen and paper. In this case an evaluation to determine the prediction model and parameters associated with the optimization event.
determining a simulation model and one or more simulation model parameters associated with the optimization event;
This describes an observation, evaluation, judgment or opinion that can be done in the mind or with aid of pen and paper. In this case an evaluation to determine the simulation model and parameters associated with the optimization event.
generating a generalized optimization problem based on the optimization event and the one or more domain and user requirements;
This corresponds to a mathematical calculation when generating the generalized optimization problem.
determining an optimization model based on the generalized optimization problem;
This describes an observation, evaluation, judgment or opinion that can be done in the mind or with aid of pen and paper. In this case an evaluation to determine the optimization model.
generating an optimization output from the optimization model; and
This corresponds to a mathematical calculation when generating an optimization output.
STEP 2A PRONG TWO: The claim does not integrate the exception into a practical application.
receiving, from a user, a request for an optimization event;
MPEP 2106.05(g) – This is pre solution data gathering activity.
obtaining one or more domain and user requirements associated with the optimization event for a semantic domain model;
MPEP 2106.05(g) – This is pre solution data gathering activity.
providing the optimization output to the user.
MPEP 2106.05(g) – This is post-solution data display.
STEP 2B: The claim does not recite an inventive concept or significantly more than the exception.
Conclusion: Claim 1 is directed to mental processes and mathematical concepts, not integrated into a practical application and lacks an inventive concept. Therefore, it is ineligible under 35 U.S.C 101.
Regarding Claim 2, 4, 6, and 7:
These claims merely narrow the abstract idea by specifying how the recited determinations are performed modeling requirements with a generalized characteristics representation (claim 2), constructing and training a new prediction / simulation model via variable selection (claim 4, 6), and iteratively executing the prediction and simulation models with intermediate optimized solutions (claim 7). This does not integrate the judicial exception into a practical application. The claims do not resolve the issues from the claim they depend upon.
Regarding Claim 3, 5, and 8:
These claims merely add pre solution data gathering by, determining historical data (claim 3), determining simulation data (claim 5), MPEP 2106.05(g), or they narrow the input data type in the form of natural language (claim 8) and link the field of use, MPEP 2106.05(h). This does not integrate the judicial exception into a practical application. The claims do not resolve the issues from the claim they depend upon.
Claim 9.
STEP 1: Yes. The claim is directed to a “method” which is a process.
STEP 2A PRONE ONE:
The claim recites multiple mental processes and mathematical concepts.
determining a prediction model and one or more prediction model parameters based on the one or more domain and user requirements;
This describes an observation, evaluation, judgment or opinion that can be done in the mind or with aid of pen and paper. In this case an evaluation to determine the prediction model.
generating a generalized optimization problem based on the optimization event and the one or more domain and user requirements;
This corresponds to a mathematical calculation when generating an optimization problem.
determining an optimization model based on the generalized optimization problem;
This describes an observation, evaluation, judgment or opinion that can be done in the mind or with aid of pen and paper. In this case an evaluation to determine the optimization model.
generating an optimization output from the optimization model; and
This corresponds to a mathematical calculation when generating an optimization output.
STEP 2A PRONG TWO: The claim does not integrate the exception into a practical application.
receiving, from a user, a request for an optimization event;
MPEP 2106.05(g) – This is pre solution data gathering activity.
obtaining one or more domain and user requirements associated with the optimization event for a semantic domain model;
MPEP 2106.05(g) – This is pre solution data gathering activity.
providing the optimization output to the user.
MPEP 2106.05(g) – This is post-solution data display.
STEP 2B: The claim does not recite an inventive concept or significantly more than the exception.
Conclusion: Claim 9 is directed to mental processes and mathematical concepts, not integrated into a practical application and lacks an inventive concept. Therefore, it is ineligible under 35 U.S.C 101.
Regarding Claim 10, 11, and 13:
These claims merely narrow the abstract idea by specifying how the recited determinations are performed via modeling requirements with a generalized characteristics representation (claim 10), constructing and training a new prediction model via a variable selection service (claim 11), and iteratively executing the prediction model with intermediate optimized solutions (claim 13). Thus, the claims remain as mental processes and mathematical concepts, with any added data gathering being insignificant extra-solution activity, MPEP 2106.05(g). This does not integrate the judicial exception into a practical application. The claims do not resolve the issues from the claim they depend upon.
Regarding Claim 12:
This claim merely narrows the abstract idea by specifying how the variable selection is performed by determining variables and constraints, determining input variables based on a sematic relationship, and selecting the prediction model parameters. Thus, the claim remains as mental processes and mathematical concept. This does not integrate the judicial exception into a practical application. The claims do not resolve the issues from the claim they depend upon.
Claim 14.
STEP 1: Yes. The claim is directed to a “system” which is a machine.
STEP 2A PRONE ONE:
The claim recites multiple mental processes and mathematical concepts.
determine a prediction model and one or more prediction model parameters associated with the optimization event;
This describes an observation, evaluation, judgment or opinion that can be done in the mind or with aid of pen and paper. In this case an evaluation to determine the prediction model.
determine a simulation model and one or more simulation model parameters associated with the optimization event;
This describes an observation, evaluation, judgment or opinion that can be done in the mind or with aid of pen and paper. In this case an evaluation to determine the simulation model.
generate a generalized optimization problem based on the optimization event and the one or more domain and user requirements;
This corresponds to a mathematical calculation when generating an optimization problem.
determine an optimization model based on the generalized optimization problem;
This describes an observation, evaluation, judgment or opinion that can be done in the mind or with aid of pen and paper. In this case an evaluation to determine the optimization model.
generate an optimization output from the optimization model; and
This corresponds to a mathematical calculation when generating an optimization output.
STEP 2A PRONG TWO: The claim does not integrate the exception into a practical application.
a memory comprising computer-executable instructions; and a processor configured to execute the computer- executable instructions and cause the processing system to
MPEP 2106.05(f) – These are generic computer components used to implement the abstract idea.
receive, from a user, a request for an optimization event;
MPEP 2106.05(g) – This is pre solution data gathering activity.
obtain one or more domain and user requirements associated with the optimization event for a semantic domain model;
MPEP 2106.05(g) – This is pre solution data gathering activity.
provide the optimization output to the user.
MPEP 2106.05(g) – This is post-solution data display.
STEP 2B: The claim does not recite an inventive concept or significantly more than the exception.
Conclusion: Claim 14 is directed to mental processes and mathematical concepts, not integrated into a practical application and lacks an inventive concept. Therefore, it is ineligible under 35 U.S.C 101.
Regarding Claim 15, 17, 19, and 20:
These claims merely narrow the abstract idea by specifying how the recited determinations are performed by modeling requirements with a generalized characteristics representation (claim 15), constructing and training a new prediction / simulation model via a variable selection service (claims 17, 19), and iteratively executing the prediction and simulation models with intermediate optimized solutions (claim 20). This does not integrate the judicial exception into a practical application. The claims do not resolve the issues from the claim they depend upon.
Regarding Claim 16 and 18:
These claims merely add pre-solution data gathering by determining historical data (claim 16), determining simulation data (claim 18), and internal data transfer of the model optimization. MPEP 2106.05(g). This does not integrate the judicial exception into a practical application. The claims do not resolve the issues from the claim they depend upon.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 9-11 and 13 are rejected under 35 U.S.C 102 as being unpatentable over YUCE et al. “An ANN-GA Semantic Rule-Based System to Reduce the Gap Between Predicted and Actual Energy Consumption in Buildings” (2017).
Regarding Claim 9, YUCE teaches
A method for semantically-driven optimization, comprising:
receiving, from a user, a request for an optimization event;
“After the rule generation process, these rules are implemented in the pilot zone after conversion into SWRL and then inclusion in the OWL ontology. The rules are fired by an inference engine when the user request is received. The inference engine seeks for the rule which contains the desired objective and the desired reduction…”. (Pg. 1359 Section VII).
This shows a user submitting a request for a target optimization received by the system.
obtaining one or more domain and user requirements associated with the optimization event for a semantic domain model;
“This is delivered in the form of an energy management framework, illustrated in Fig. 2, consisting of: (a) an OWL knowledge base (ontology) providing a semantic description of the building and its properties, augmented with the proposed rules; (b) a fuzzy logic real-time controller (RTC), which fires proposed energy saving rules when triggering conditions are met; (c) a graphical user interface (GUI) at the disposal of the FM to negotiate energy saving plans, and thus interact with the solution; (d) a RDF (Triple/quad store)/SPARQL mapper…”. (Pg. 1353 Section III).
“The generated rules deliver optimized values to deal with multi-objective problems. In the building environment, these optimal values should be based on set points for control variables available in a given building. Hence, the theoretically generated rules will be able to respond to real world (multi-objective) requirements such as energy/ emission reduction, and thermal comfort enhancement.”. (Pg. 1352 Section I).
This shows using an OWL ontology (semantic domain model) holding the buildings domain data and the user’s energy / comfort requirements.
determining a prediction model and one or more prediction model parameters based on the one or more domain and user requirements;
“The learning stage of the proposed algorithm is based on a multilayer perceptron (MLP) structure ANN … consists of 17 inputs … The outputs of the ANN are the objectives of the considered scenario, i.e., heating (thermal) energy consumption (KhW) and predicted mean vote (PMV) …”. (Pg. 1356 Section V).
“… the best performing ANN was found with 30 process elements in the hidden layer. The following experiments will therefore use this number as the number of process elements. Finally, the different transfer function types in the hidden layer and output layer…”. (Pg. 1357 Section V).
The MLP ANN is a prediction model, determined for the scenario together with its parameters, the training learning function, layers, and transfer functions.
generating a generalized optimization problem based on the optimization event and the one or more domain and user requirements;
“The proposed optimization problem has four control variables, three date information and ten environmental variables which are given in (3)–(7). Moreover, ANN is utilized as a cost function predictor and embedded into GA. The overall process of the proposed GA is given in Fig. 10. where (3) (4) (5) (6) (7) is the objective function for the selected case, i.e., “Heating Energy Consumption…”. (Pg. 1357).
“The proposed rule generation is devised based on predetermined negotiation processes, designed for energy reduction levels of 5%, 10%, 15%, 20%, 25%, and 30%, while using thermal comfort as the constraint of the problem.”. (Pg. 1358).
This shows generating an optimization problem an energy consumption objective over control variables that are constrained by thermal comfort from the scenario’s energy and comfort requirements.
determining an optimization model based on the generalized optimization problem;
“A GA-based optimization solution is used. GA is a population-based stochastic optimization algorithm which utilizes a global search process to find the optimum solution for complex and non-linear type optimization problems.”. (Pg. 1357 Section VI).
“Moreover, ANN is utilized as a cost function predictor and embedded into GA.”. (Pg. 1357 Section VI).This shows determining a genetic algorithm optimization model, with the ANN embedded as its cost function in order to solve the formulated problem.
generating an optimization output from the optimization model; and
providing the optimization output to the user.
“The optimization process has found an optimum solution and recommends the user to set control variables as 17.53 C, off (0), off (0) and off (0) …”. (Pg. 1358).
This shows the GA optimization model producing an optimization output in this case the optimum control variables set points.
Regarding Claim 10, YUCE teaches
The method of Claim 9, further comprising: modelling the one or more domain and user requirements based on a generalized characteristics representation.
“Ontology is a computer and human readable conceptualization of a domain whereby knowledge is represented as sets of semantically related concepts through classes, their properties, and relationships [18].”. (Pg. 1352 Section 1).
“… an OWL knowledge base (ontology) providing a semantic description of the building and its properties…”. (Pg. 1353 Section III).
This shows modeling the domain and user requirements through the ontology’s class and property conceptualization the generalized characterizations representation.
Regarding Claim 11, YUCE teaches
The method of Claim 9, wherein determining the prediction model and the one or more prediction model parameters based on the one or more domain and user requirements, comprises:
determining no prediction model of a plurality of prediction models is associated with the optimization event and the one or more user and domain requirements,
“… energy gap problem can be addressed through:(i) a detailed physical model;(ii) a black-box model; or (iii) a gray-box model”. (Pg. 1351 Section I).
“Conversely, a black-box approach such as ANN does not require any prior information about the model, which makes it a preferred option to intelligently manage energy in buildings [7].”. (Pg. 1351 Section I).
This shows the reference finds the existing models unsuitable and instead builds a new block box ANN the “no suitable model” to construct a new branch.
constructing a new predictive model semantically based on historical data, comprising:
“… used to train an ANN to learn energy consumption patterns and behavior within the considered buildings.”. (Pg. 1351 Abstract).
“… whereby the simulated and metered data are utilized to provide a dynamic and system engineering characterization of the building energy dimension within the building.”. (Pg. 1354 Section III).
This shows constructing a new ANN through the semantic / ontology framework trained on the buildings metered (historical) data obtained for the scenario’s variables.
determining, via a variable selection service, the one or more prediction model parameters based on the one or more domain and user requirements; and
“A semantic mapping process is proposed using principle component analysis (PCA) and multi regression analysis (MRA) to determine the governing (i.e., most sensitive) variables…”. (Pg. 1351 Abstract).
This shows a variable selection service PCA plus MRA determining the variables that serve as the prediction models parameters.
training the new predictive model based on the historical data and simulated data; and
“The training of ANN has been carried out using the best combination of the topology with de fined inputs and outputs. To train ANN with this topology, the data set was divided into two parts as training and test data. The training data is 80% of the raw data, selected randomly.”. (Pg. 1357 Section V).
This shows training the new ANN on its defined inputs (selected parameters) and the data.
providing the new prediction model to the optimization model.
“Moreover, ANN is utilized as a cost function predictor and embedded into GA.”. (Pg. 1357 Section VI).
This shows providing the prediction model to the GA optimization model.
Regarding Claim 13, YUCE teaches
The method of Claim 9, wherein generating the optimized output based on the optimization model, comprises;
executing the prediction model with one or more intermediate optimized solutions generated by the optimization model and prediction data; and
“Moreover, ANN is utilized as a cost function predictor and embedded into GA.”. (Pg. 1357 Section VI).
“The fitness value of the heating energy consumption in each iteration.”. (Pg. 1358 Section VI).
This shows the prediction model being executed within the GA each iteration to evaluate candidate solutions.
obtaining the optimized output from the optimization model based on the executed prediction model.
“The optimization process has found an optimum solution and recommends the user to set control variables as 17.53…”. (Pg. 1358).
This shows the optimum output obtained from the GA based on the executed ANN.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or non-obviousness.
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 is advised of the obligation under 37 CFR 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 1-6 and 14-19 are rejected under 35 U.S.C 103 as being unpatentable over YUCE et al. “An ANN-GA Semantic Rule-Based System to Reduce the Gap Between Predicted and Actual Energy Consumption in Buildings” (2017) and LAURENT et al WO 2016130453 A1 (2016).
Regarding Claim 1, YUCE teaches
A method for semantically-driven optimization, comprising:
receiving, from a user, a request for an optimization event;
“After the rule generation process, these rules are implemented in the pilot zone after conversion into SWRL and then inclusion in the OWL ontology. The rules are fired by an inference engine when the user request is received. The inference engine seeks for the rule which contains the desired objective and the desired reduction…”. (Pg. 1359 Section VII).
“The test has been carried out on an Intel Pentium i-5 processor with 6 GB RAM desktop.”. (Pg. 1359 Section VIII).
This shows a user submitting a request for a target optimization received by the system.
obtaining one or more domain and user requirements associated with the optimization event for a semantic domain model;
“This is delivered in the form of an energy management framework, illustrated in Fig. 2, consisting of: (a) an OWL knowledge base (ontology) providing a semantic description of the building and its properties, augmented with the proposed rules; (b) a fuzzy logic real-time controller (RTC), which fires proposed energy saving rules when triggering conditions are met; (c) a graphical user interface (GUI) at the disposal of the FM to negotiate energy saving plans, and thus interact with the solution; (d) a RDF (Triple/quad store)/SPARQL mapper…”. (Pg. 1353 Section III).
“The generated rules deliver optimized values to deal with multi-objective problems. In the building environment, these optimal values should be based on set points for control variables available in a given building. Hence, the theoretically generated rules will be able to respond to real world (multi-objective) requirements such as energy/ emission reduction, and thermal comfort enhancement.”. (Pg. 1352 Section I).
This shows using an OWL ontology (semantic domain model) holding the buildings domain data and the user’s energy / comfort requirements.
determining a prediction model and one or more prediction model parameters associated with the optimization event;
“The learning stage of the proposed algorithm is based on a multilayer perceptron (MLP) structure ANN … consists of 17 inputs … The outputs of the ANN are the objectives of the considered scenario, i.e., heating (thermal) energy consumption (KhW) and predicted mean vote (PMV) …”. (Pg. 1356 Section V).
“… the best performing ANN was found with 30 process elements in the hidden layer. The following experiments will therefore use this number as the number of process elements. Finally, the different transfer function types in the hidden layer and output layer…”. (Pg. 1357 Section V).
The MLP ANN is a prediction model, determined for the scenario together with its parameters, the training learning function, layers, and transfer functions.
generating a generalized optimization problem based on the optimization event and the one or more domain and user requirements;
“The proposed optimization problem has four control variables, three date information and ten environmental variables which are given in (3)–(7). Moreover, ANN is utilized as a cost function predictor and embedded into GA. The overall process of the proposed GA is given in Fig. 10. where (3) (4) (5) (6) (7) is the objective function for the selected case, i.e., “Heating Energy Consumption…”. (Pg. 1357).
“The proposed rule generation is devised based on predetermined negotiation processes, designed for energy reduction levels of 5%, 10%, 15%, 20%, 25%, and 30%, while using thermal comfort as the constraint of the problem.”. (Pg. 1358).
This shows generating an optimization problem an energy consumption objective over control variables that are constrained by thermal comfort from the scenario’s energy and comfort requirements.
determining an optimization model based on the generalized optimization problem;
“A GA-based optimization solution is used. GA is a population-based stochastic optimization algorithm which utilizes a global search process to find the optimum solution for complex and non-linear type optimization problems.”. (Pg. 1357 Section VI).
“Moreover, ANN is utilized as a cost function predictor and embedded into GA.”. (Pg. 1357 Section VI).This shows determining a genetic algorithm optimization model, with the ANN embedded as its cost function in order to solve the formulated problem.
generating an optimization output from the optimization model; and
providing the optimization output to the user.
“The optimization process has found an optimum solution and recommends the user to set control variables as 17.53 C, off (0), off (0) and off (0) …”. (Pg. 1358).
This shows the GA optimization model producing an optimization output in this case the optimum control variables set points.
YUCE does not explicitly teach but LAURENT teaches
determining a simulation model and one or more simulation model parameters associated with the optimization event;
“The simulation module 105 shown in FIG. 1 may be used for determining airflow and temperature estimates based on room configurations and equipment set points. For example, according to some embodiments, the airflow and temperature simulation 105 may be used to predict the temperatures at each point of the room for a given control set point, and/or at a given IT load. Non-limiting examples of suitable simulation methods and systems include those based on computational fluid dynamics (CFD)…”. (Pg. 18).
“The optimization engine 115 uses the simulation module 105 and the energy model 110 in an iterative process that converges to an optimal set point.”. (Pg. 13).
This shows a simulation model, set by room and equipment parameters, run within in the optimization.
It would have been obvious before the effective filing date of the claimed invention to incorporate the teachings of LAURENT’s determination of an optimal simulation model and its parameters selection with YUCE’s semantic optimization system, in order to reduce the overall time to find the optimal set points, as stated by LAURENT’s “…and a regression model that is tuned by simulation that may be used by the optimization solver that functions to reduce the overall time to find the optimal set points”. (Pg. 3).
Regarding Claim 2, LAURENT does not explicitly teach but YUCE teaches
The method of Claim 1, further comprising modelling the one or more domain and user requirements associated with the optimization event based on a generalized characteristics representation.
“Ontology is a computer and human readable conceptualization of a domain whereby knowledge is represented as sets of semantically related concepts through classes, their properties, and relationships [18].”. (Pg. 1352 Section 1).
“… an OWL knowledge base (ontology) providing a semantic description of the building and its properties…”. (Pg. 1353 Section III).
This shows modeling the domain and user requirements through the ontology’s class and property conceptualization the generalized characterizations representation.
Regarding Claim 3, LAURENT does not explicitly teach but YUCE teaches
The method of Claim 1, wherein determining the prediction model and the one or more prediction model parameters based on the one or more domain and user requirements, comprises:
identifying the prediction model from a plurality of prediction models associated with the optimization event and the one or more domain and user requirements;
“… several ANN learning algorithms and topologies have been tested to determine the best performing ANN.”. (Pg. 1356 Section V).
This shows identifying the prediction model the best performing ANN from a plurality of tested models.
determining the one or more prediction model parameters based on the prediction model and the one or more domain and user requirements;
“… the best performing ANN topology was found using trainlm as the learning function, 30 process elements in the hidden layer, and the logarithmic sigmoid and tangent sigmoid function ([logsig tansig]) in the hidden layer and output layer, respectively.”. (Pg. 1357 Section V).
This shows determining the prediction models parameters.
determining historical data associated with the one or more domain and user requirements; and
“… simulated and metered data are utilized to provide a dynamic and system engineering characterization of the building energy dimension within the building.”. (Pg. 1353 Section III).
This shows determining the building’s historical / metered data for the model.
providing the prediction model and the prediction model parameters to the optimization model.
“Moreover, ANN is utilized as a cost function predictor and embedded into GA.”. (Pg. 1357 Section VI).
This shows providing the prediction model to the GA optimization model.
Regarding Claim 4, LAURENT does not explicitly teach but YUCE teaches
The method of Claim 1, wherein determining the prediction model and the one or more prediction model parameters based on the one or more domain and user requirements, comprises:
determining no prediction model of a plurality of prediction models is associated with the optimization event and the one or more user and domain requirements,
“… energy gap problem can be addressed through:(i) a detailed physical model;(ii) a black-box model; or (iii) a gray-box model”. (Pg. 1351 Section I).
“Conversely, a black-box approach such as ANN does not require any prior information about the model, which makes it a preferred option to intelligently manage energy in buildings [7].”. (Pg. 1351 Section I).
This shows the reference finds the existing models unsuitable and instead builds a new block box ANN the “no suitable model” to construct a new branch.
constructing a new predictive model semantically based on historical data, comprising:
obtaining the historical data associated with the one or more domain and user requirements associated with the optimization event and the optimization event;
“… used to train an ANN to learn energy consumption patterns and behavior within the considered buildings.”. (Pg. 1351 Abstract).
“… whereby the simulated and metered data are utilized to provide a dynamic and system engineering characterization of the building energy dimension within the building.”. (Pg. 1354 Section III).
This shows constructing a new ANN through the semantic / ontology framework trained on the buildings metered (historical) data obtained for the scenario’s variables.
determining, via a variable selection service the one or more prediction model parameters based on the one or more domain and user requirements; and
“A semantic mapping process is proposed using principle component analysis (PCA) and multi regression analysis (MRA) to determine the governing (i.e., most sensitive) variables…”. (Pg. 1351 Abstract).
This shows a variable selection service PCA plus MRA determining the variables that serve as the prediction models parameters.
training the new predictive model based on the one or more prediction model parameters and the historical data; and
“The training of ANN has been carried out using the best combination of the topology with de fined inputs and outputs. To train ANN with this topology, the data set was divided into two parts as training and test data. The training data is 80% of the raw data, selected randomly.”. (Pg. 1357 Section V).
This shows training the new ANN on its defined inputs (selected parameters) and the data.
providing the new prediction model and the one or more prediction model parameters to the optimization model.
“Moreover, ANN is utilized as a cost function predictor and embedded into GA.”. (Pg. 1357 Section VI).
This shows providing the prediction model to the GA optimization model.
Regarding Claim 5, YUCE does not explicitly teach but LAURENT teaches
The method of Claim 1, wherein determining the simulation model and the one or more simulation model parameters associated with the optimization event, comprises:
identifying the simulation model from a plurality of simulation models associated with the optimization event and the one or more domain and user requirements;
“Non-limiting examples of suitable simulation methods and systems include those based on computational fluid dynamics (CFD) analysis, such as potential flow or RANS (Reynolds- Averaged Navier Stokes) CFD, and alternatives to CFD, such as lumped models.”. (Pg. 18).
This shows identifying the simulation model from a plurality (CFD / potential flow / lumped models).
determining the one or more simulation model parameters based on the simulation model and the one or more domain and user requirements;
“Inputs to the model may include information about the predominant cooling architecture of the data center, measured temperatures, and parameters associated with the facility's chillers, coolers, and IT equipment racks, as well as a maximum inlet temperature.”. (Pg. 25).
This shows determining the simulations models parameters.
determining simulation data associated with the one or more domain and user requirements; and
“… the simulation module 105 that estimates airflow and temperature values 130 …”. (Pg. 13).
This shows the simulation determining the simulation data in this case the airflow and temperature values.
providing the simulation model and the simulation model parameters to the optimization model.
“The optimization engine 115 uses the simulation module 105 and the energy model 110 in an iterative process that converges to an optimal set point.”. (Pg. 13).
This shows providing the simulation model to the optimization module.
Regarding Claim 6, LAURENT does not explicitly teach but YUCE teaches
The method of Claim 1, wherein determining the simulation model and the one or more simulation model parameters based on the one or more domain and user requirements, comprises:
determining no simulation model of a plurality of simulation models is associated with the optimization event and the one or more user and domain requirements,
“… energy gap problem can be addressed through:(i) a detailed physical model;(ii) a black-box model; or (iii) a gray-box model”. (Pg. 1351 Section I).
“Conversely, a black-box approach such as ANN does not require any prior information about the model, which makes it a preferred option to intelligently manage energy in buildings [7].”. (Pg. 1351 Section I).
This shows determining that no existing model is available and in response constructing a new model.
determining, via a variable selection service the one or more simulation model parameters based on the one or more domain and user requirements; and
“A semantic mapping process is proposed using principle component analysis (PCA) and multi regression analysis (MRA) to determine the governing (i.e., most sensitive) variables…”. (Pg. 1351 Abstract).
This shows PCA and MRA acting as the variable selection service that picks the governing variables used as the model’s parameters.
YUCE does not explicitly teach but LAURENT teaches
constructing a new simulation model semantically based on simulation data, comprising:
obtaining the simulation data associated with the one or more domain and user requirements associated with the optimization event and the optimization event;
“… implementing the numerical simulation model includes generating a regression model, the regression model based at least in part on at least one operating parameter of the data center…”. (Pg. 5).
“… the regression model is based on at least one of simulation results and one or more measurements. The one or more measurements may be obtained from one or more sensors positioned in the data center.”. (Pg. 5).
This shows constructing a new regression simulation model from the simulation data the simulation results and sensor measurements obtained for the data center.
training the new simulation model based on the one or more simulation model parameters and the simulation data; and
“… the regression model is generated using a least square regression technique.”. (Pg. 5).
“The metamodel approach discussed above provides several advantages. For example, speed is enhanced, since the number of simulations needed to build the regression model may range from only 5 to 20.”. (Pg. 32).
This shows the new simulation model is being trained by fitting a regression to the 5 to 20 simulation runs via least squares.
providing the new simulation model and the one or more simulation model parameters to the optimization model.
“… a regression model that is tuned by simulation that may be used by the optimization solver that functions to reduce the overall time to find the optimal set points.”. (Pg. 3).
This shows the new regression simulation model being provided to the optimization solver to find the optimal set points.
Claim 14 recites sustainably the same limitations as claim 1 except this claim is directed to a “system”. Therefore this, claim is rejected for the same rationale as addressed above.
Claim 15 recites sustainably the same limitations as claim 2 except this claim is directed to a “system”. Therefore this, claim is rejected for the same rationale as addressed above.
Claim 16 recites sustainably the same limitations as claim 3 except this claim is directed to a “system”. Therefore this, claim is rejected for the same rationale as addressed above.
Claim 17 recites sustainably the same limitations as claim 4 except this claim is directed to a “system”. Therefore this, claim is rejected for the same rationale as addressed above.
Claim 18 recites sustainably the same limitations as claim 5 except this claim is directed to a “system”. Therefore this, claim is rejected for the same rationale as addressed above.
Claim 19 recites sustainably the same limitations as claim 6 except this claim is directed to a “system”. Therefore this, claim is rejected for the same rationale as addressed above.
Claims 7 and 20 are rejected under 35 U.S.C 103 as being unpatentable over YUCE et al. “An ANN-GA Semantic Rule-Based System to Reduce the Gap Between Predicted and Actual Energy Consumption in Buildings” (2017), LAURENT et al WO 2016130453 A1 (2016), and GENGEMBRE et al. “A Kriging constrained efficient global optimization approach applied to low-energy building design problems” (2012).
Regarding Claim 7, LAURENT does not explicitly teach but YUCE teaches
The method of Claim 1, wherein generating the optimized output based on the optimization model, comprises;
executing the prediction model with one or more intermediate optimized solutions generated by the optimization model and prediction data;
“Moreover, ANN is utilized as a cost function predictor and embedded into GA.”. (Pg. 1357 Section VI).
“The fitness value of the heating energy consumption in each iteration.”. (Pg. 1358 Section VI).
This shows the prediction model being executed within the GA each iteration to evaluate candidate solutions.
YUCE does not explicitly teach but LAURENT teaches
executing the simulation model with the one or more intermediate optimized solutions generated by the optimization model and simulation data; and
“… the optimization solver iteratively determines the at least one optimized cooling set point until a stopping condition is met by iteratively varying one or more inputs received by at least one of the energy model and the numerical simulation model.”. (Pg. 3-4).
This shows the simulation model is being executed on the optimizers iteratively valued candidate solutions to evaluate each alternative.
YUCE and LAURENT do not explicitly teach but GENGEMBRE teaches
obtaining the optimized output from the optimization model based on the executed prediction model and the executed simulation model.
“… optimization will update the Kriging surrogate model after each call to the expensive function in order to improve the accuracy of the surrogate model…”. (Pg. 5 Section 2.4).
“We will consider energy simulation expensive to evaluate, because one simulation can be fast as a need of a few seconds, but thousands of simulations will take too much time for a efficient use in building conception.”. (Pg. 5 Section 2.4).
This shows the optimizer executing both a prediction model and the building energy simulation each iteration, and obtaining the optimum from both.
It would have been obvious before the effective filing date of the claimed invention to incorporate the teachings of GENGEMBRE’s execution of both the predictive model and the simulation model within in the optimization loop with YUCE-LAURENT’s semantic optimization system, as stated by LAURENT’s “…optimization will update the Kriging surrogate model after each call to the expensive function in order to improve the accuracy of the surrogate model and to tend to the optimum.”. (Pg. 6).
Claim 20 recites sustainably the same limitations as claim 7 except this claim is directed to a “system”. Therefore this claim is rejected for the same rationale as addressed above.
Claim 8 is rejected under 35 U.S.C 103 as being unpatentable over YUCE et al. “An ANN-GA Semantic Rule-Based System to Reduce the Gap Between Predicted and Actual Energy Consumption in Buildings” (2017), LAURENT et al WO 2016130453 A1 (2016), and JETHWA et al. US20190121801A1 (2018).
Regarding Claim 8, YUCE and LAURENT does not explicitly teach but JETHWA teaches
The method of Claim 1, wherein the request for the optimization event comprises a structured natural language statement.
“The user can provide query input via the GUI to generate an updated graph corresponding to the query input. Recommendations can be provided to the user based on the query input and the contents of the updated graph.”. (Abstract).
“In some embodiments, the query input 240 provided in the search input 505 can originate from a knowledge or interactive agent (e.g., a chatbot program) that is configured to receive a user's inputs and provide those inputs as query inputs 240. As shown in FIG. 5B, the query input 240 provided in the search input 505 describes a query to identify which controller is most active (e.g., “Which controller is most active”). Upon entry of the query input 240 via the search query input 505, the graph 245 can be automatically generated or regenerated as described in relation to operation 430 of FIG. 4.”. (0071).
This shows the users request entered as a natural language statement through a GUI.
It would have been obvious before the effective filing date of the claimed invention to incorporate the teachings of JETHWA’s natural language input with YUCE-LAURENT’s semantic optimization system, in order improve interaction, as stated by JETHWA’s “The user can provide query input via the GUI to generate an updated graph corresponding to the query input.”. (Abstract).
Claim 12 is rejected under 35 U.S.C 103 as being unpatentable over YUCE et al. “An ANN-GA Semantic Rule-Based System to Reduce the Gap Between Predicted and Actual Energy Consumption in Buildings” (2017) and GONZALEZ et al. “Semantic prediction assistant approach applied to energy efficiency in Tertiary buildings” (2018).
Regarding Claim 12, YUCE teaches
The method of Claim 11, wherein determining, via the variable selection service, the one or more prediction model parameters based on the one or more domain and user requirements, comprises:
determining one or more variables and constraints based on the one or more domain and user requirements;
“The proposed optimization problem has four control variables, three date information and ten environmental variables…”. (Pg. 1357 Section VI).
“… while using thermal comfort as the constraint of the problem.”. (Pg. 1358 Section VI).
This shows determining the variables for example control, date, environmental and the constraint thermal comfort with upper and lower bounds.
selecting, the one or more prediction model parameters from the input variables via the variable selection service.
“Energy sensitive variables are then identified using PCA and MRA.”. (Pg. 1351 Abstract).
This shows the variable selection service selecting the sensitive variables which serve as model parameters.
YUCE does not explicitly teach but GONZALEZ teaches
determining input variables from the one or more variables and constraints based on a semantic relationship between the one or more variables and constraints and output variables for the prediction model; and
“…the object property eepsa: isAffectedBy relates spaces to climatic variables that affect their environmental conditions.”. (Section 3.1).
“Relevant datasets and subsets of variables that will form the data input for machine learning algorithms are selected.”. (Section 3.3).
“Summarizing, the EEPSA process uses OWL inferences to assist the data analyst in classifying the space at hand and suggesting variables affecting it.”. (Section 3.3).
This shows the models input variables being determined by an ontology relationship.
It would have been obvious before the effective filing date of the claimed invention to incorporate the teachings of GONZALEZ’s determination based on a semantic relationship with YUCE’s semantic optimization system, in order improve predictions, as stated by GONZALEZ’s “…results show that the proposed solution improves the accuracy of predictions.”. (Abstract).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US-8055358-B2 teaches a system and method for controlling a process includes simulating the process and producing a simulated output of the process.
US20170211837A1 teaches a collaborative energy management system, method and program product for a multi-zone space.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to NARCISO EDUARDO MONTES whose telephone number is (571)272-5773. The examiner can normally be reached Mon-Fri 8-5.
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, REHANA PERVEEN, can be reached at (571) 272-3676. 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.
/N.E.M./Examiner, Art Unit 2189
/REHANA PERVEEN/Supervisory Patent Examiner, Art Unit 2189
Prosecution Insights