DETAILED ACTION
A. This action is in response to the following communications: Amendment filed: 08/26/2026. This action is made Final.
B. Claims 1-20 remain pending.
Claim Rejections - 35 USC § 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 (i.e., changing from AIA to pre-AIA ) 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, 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.
Claim(s) 1-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Pasour, Ernest et al. (US Pub. 2022/0138606 A1), herein referred to as “Pasour” in view of ELBSAT, Mohammad N. et al. (US Pub. 2020/0356087 A1), herein referred to as “ELBSAT” in further view of Risbeck, Michael J. et al. (US Pub. 2020/0125045 A1), herein referred to as “Risbeck”.
As for claims 1, 8 and 15, Pasour teaches. A method and corresponding system of claim 8 and computer-readable storage medium of claim 15 comprising:
Specific to claim 8 a processor; and memory or storage comprising an algorithm or computer instructions, which when executed by the processor, performs an operation comprising (par. 47 hardware environment; processors):
Specific to claim 15 having a computer-readable program code embodied therewith, the computer-readable program code executable by one or more computer processors to perform an operation comprising (par. 47 hardware environment; machine-readable storage medium):
Performing a production process configured to produce a product (par. 47 and 65 give examples for handling data relating to production/manufacturing of products: For example, network-attached data stores 110 may hold unstructured (e.g., raw) data, such as manufacturing data (e.g., a database containing records identifying products being manufactured with parameter data for each product, such as colors and models) or product sales databases (e.g., a database containing individual data records identifying details of individual product sales. Thus, computing environment 214 can retrieve data of interest, such as client information (e.g., product information, client rules, etc.), technical product details, news, current or predicted weather, and so on. The “performing a production process” is ambiguous and arbitrary as is the result of this being configured to produce a product; the citation of data gathering can be related to performing a production process and the configured to produce a product can be outputting a report to a user, or the mere mention that the data gathered is related to a manufacturing process of a product also reads on this limitation. Prior art goes on to state that data gathered is interacted with for making predictions; thus the understanding if the data is related to products and manufacturing then the predictions and models used are based upon manufacturing of products).
determining, via a process model, a variable state of the process model, wherein the variable state includes a first input state variable, a first output state variable, and a first control parameter (fig. 16 user interface for selecting a model to use on a data set wherein the data can be variable and upon running the model on the data set updating data based upon found predictions; first, second to the nth amount of predictions can be made on the dataset; par. 178);
generating, via a short-term prediction module, a first prediction of a first update of the variable state (par. 178 predictor to the model outcome);
generating, via a terminal value prediction module, a second prediction of a second update to the variable state (par. 179 other predictors based upon more than one update to variable state (e.g. between 0 and 1);
generating, via a control optimization module, a second control parameter based on the first prediction and the second prediction (par. 181 allowing the user to select a validation method for validating the model which is based upon first and second prediction value updates from the dataset);
and controlling, via a processor, a production process of the process model based on the second control parameter (par. 181-182 user interface give controlling function over the model to the user to select a production process ‘validation AIC, BIC etc..’ which will process the model based upon second control parameters as shown in figure 16).
Pasour teaches instructions to cause a computing system to generate an updated model for a set of regression models; but does not discuss using a mixed-integer linear program (MILP); also Pasour does not teach wherein the first prediction represents an optimized prediction of multiple updates on a short-term future time horizon; however in the same field endeavor ELBSAT teaches:
Performing a production process configured to produce a product (par. 315 For example, neural network trainer 1210 can receive a set of training data including the estimated degradation states {circumflex over (δ)}k at each time step k from degradation estimator 1116 along with data indicating the amounts of input resources consumed and output resources produced at each time step k. The amounts of resources consumed and produced at each time step k may be indicated by the performance variables yk. ELBSAT produces a product in terms of software by outputting dynamic generated maintenance schedule; the system also creates workflow events (software objects) to deliver to end user (e.g. schedule coil cleaning when efficiency has declined (par. 231-232); the maintenance action plan referred to as “rate of change manager” is essentially a digital job planner to dynamically schedule jobs that include step-by-step procedures, required tools to complete the job, estimated time, dependences and safety checks – par. 341-342; thus we have the production of a software product delivered to end user);
generating, via a short-term prediction module, a first prediction of a first update applied to the variable state at a present time, wherein the first prediction represents an optimized prediction of multiple updates on a short-term future time horizon (par. 206 Objective function generator 935 can be configured to generate the objective function J by summing the operational cost term, the maintenance cost term, and the capital cost term formulated by cost predictors 910, 920, and 930. Par., 208 Objective function generator 935 can be configured to impose constraints on one or more variables or parameters in the objective function J; par. 212 Objective function optimizer 940 can be configured to optimize the objective function J periodically (e.g., once per day, once per week, once per month, etc.) to dynamically update the predicted cost and/or the net present value NPV.sub.cost based on the closed-loop feedback from connected equipment 610);
generating, via a terminal value prediction module, a second prediction of a second update to the variable state, wherein the second prediction represents optimized predictions of variable states on a long-term future time horizon at a time after the short-term future time horizon wherein the second prediction represents optimized predictions of variable states resulting form the first update applied to the variable state of the present time (par. 212 years are implied but none the less monthly is long term in view of daily as mentioned the optimizer can predict futures across multiple times);
generating, via a control optimization module, a second control parameter based on the first prediction and the second prediction to achieve a target output state variable of the process model, wherein the control optimization module is a mixed- integer linear programming (MILP) model that combines the first prediction and the second prediction into a single objective function and resolves the single objective function to generate the second control parameter configured to control the production process (Paragraph 209 states that the objective function optimizer 940 can optimize objective functional to determine the optimal values of binary decision variables over a duration of optimized period and can use any of a variety of optimization techniques to formulate and optimize the objective function J, this includes Mixed integer Linear Programming, mixed integer stochastic optimization, convex programming etc… further into the disclosure makes mention of using mixed integer stochastic optimization, this would be interchangeable with the techniques listed in paragraph 209 since it was mentioned that “These and other optimization techniques are known in the art and will not be described in detail here.”
par. 206 the predictors are combined to determine future predictions in the calculations; par. 212-216 as discussed above one or variable/ parameters in the objective function J can be updated dynamically to updated the reliability efficiency of connected equipment the objective function optimizer 940 can be configured to optimize function J periodically in various time lengths that can be contrasted as short and long time. The objective function optimizer 940 generates optimization results. The optimization results may include the optimal values of the decision variables in the objective function J for each time step i in the optimization period. MPM system 602 uses the optimization results to generate equipment purchase and maintenance recommendations. The equipment purchase and maintenance recommendations may be based on the optimal values for the binary decision variables Bmain,i and Bcap,i determined by optimizing the objective function J. For example, a value of Bmain,25=1 for a particular device of connected equipment 610 may indicate that maintenance should be performed on that device at the 25th time step of the optimization period, whereas a value of Bmain,25=0 may indicate that the maintenance should not be performed at that time step.) par. 218 Process 1000 is shown to include estimating an efficiency and reliability of the building equipment as a function of the equipment performance information (step 1006) par. 220 step 1006 can include predicting the efficiency ηi of the building equipment at each time step i of the optimization period. Par. 221-222 discusses degradation of equipment and formulating a prediction over the optimization period time steps. “. Step 1006 can include examining the time series of initial efficiency values η0 to determine the rate at which the efficiency degrades.” Par. 224 combines this intake of information to make predictions “step 1006 includes using the equipment performance information to identify a current operating state of the building equipment. The current operating state can be examined to expose when the building equipment begin to degrade in performance and/or to predict when faults will occur. “
and controlling, via a processor, the production process of the process model based on the second control parameter such that the production process produces the product according to the target output state variable (par. 206-213 objective function optimizer 940 generates optimization results. The optimization results may include the optimal values of the decision variables in the objective function J for each time step i in the optimization period. The optimization results include operating decisions, equipment maintenance decisions, and/or equipment purchase decisions for each device of connected equipment 610).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine ELBSAT into Pasour because ELBSAT suggests the use of a model predictive maintenance system for building equipment for performing maintenance too frequently may result in a low operating cost but a high maintenance cost, whereas performing maintenance too infrequently may result in a low maintenance cost but a higher operating cost. It can be difficult to determine an appropriate maintenance strategy for building equipment in the interest of reducing total life cycle cost (par.3-4).
The rationale to modify or combine the prior art does not have to be expressly stated in the prior art; the rationale may be expressly or impliedly contained in the prior art or it may be reasoned from knowledge generally available to one of ordinary skill in the art, established scientific principles, or legal precedent established by prior case law. In re Fine, 837 F.2d 1071, 5 USPQ2d 1596 (Fed. Cir. 1988); In re Jones, 958 F.2d 347, 21 USPQ2d 1941 (Fed. Cir. 1992); see also In re Kotzab, 217 F.3d 1365, 1370, 55 USPQ2d 1313, 1317 (Fed. Cir. 2000) (setting forth test for implicit teachings); In re Eli Lilly & Co., 902 F.2d 943, 14 USPQ2d 1741 (Fed. Cir. 1990) (discussion of reliance on legal precedent); In re Nilssen, 851 F.2d 1401, 1403, 7 USPQ2d 1500, 1502 (Fed. Cir. 1988) (references do not have to explicitly suggest combining teachings); Ex parte Clapp, 227 USPQ 972 (Bd. Pat. App. & Inter. 1985) (examiner must present convincing line of reasoning supporting rejection); and Ex parte Levengood, 28 USPQ2d 1300 (Bd. Pat. App. & Inter. 1993) (reliance on logic and sound scientific reasoning).
Even if it is found that the teachings in par. 212-222 of ELBSAT do not imply predicting with long-term future time horizons and short-term future time horizons; then it is also found in an alternative that Risbeck teaches long-term future time horizons and short-term future time horizons (par. 48, 72, 91, 134 and 159-160; these paragraphs arrive at supporting ELBSAT since they are describing the same invention from the same assignee “Johnson Controls Technology”, the disclosure of Risbeck will be used as an obvious extension to ELBSAT disclosure to teach the limitations ELBSAT is used for.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Risbeck into ELBSAT, because Risbeck suggests heating, ventilation, or air conditioning (HVAC) system and more particularly to an HVAC system that that uses optimizations to operate (par. 2-3).
As for claims 2, 9 and 16, Pasour teaches. The method of claim 1, wherein the process model is a machine learning model trained to learn underlying relationships and dynamics of inputs and outputs of the production process; wherein the first input state variable represents a controllable input of the production process; and wherein the first output state variable represents a determined output or a measured output of the production process (par. 170-171 example of finding relationship between one or more target values and determining output based upon predictions identified in the dataset of information).
As for claims 3, 10 and 17, Pasour teaches. The method of claim 1, wherein the first input state variable further represents an input of the process model; wherein the first output state variable further represents an output of one or more processing stages of the process model; and wherein the first control parameter represents an adjustment to an input state variable (par. 190-191 term settings presented in the user interface fig. 16 allows the user to adjust the model for desired variable state information related to machine log dataset).
As for claims 4, 11 and 18, Pasour teaches. The method of claim 1, wherein the short-term prediction module is a machine learning model or a statistical regression model configured to: receive the variable state; generate the first update of the variable state based on the variable state; and generate the first prediction based on the first update (par. 193 example of first predictions based upon first update is generating candidate predictors which allows for updating model; fig. 17 par. 197-198 goes into more detail upon fine tuning the term predictors and how they updated and affect the model chosen in fig. 16).
As for claims 5, 12 and 19, Pasour teaches. The method of claim 4, wherein the first prediction represents a minimum or maximum of updated variable states across a first time period, and wherein the first time period ranges from a present time to a first future time period (par. 66 The data received and collected by computing environment 214, no matter what the source or method or timing of receipt, may be processed over a period of time for a client to determine results data based on the client's needs and rules).
As for claims 6, 13 and 20, Pasour teaches. The method of claim 1, wherein the terminal value prediction module is a machine learning model or a statistical regression model configured to: receive the variable state; generate the second update of the variable state based on historical data of input state variables and output state variables of the production process to determine future input state variables and future output state variables; and generate the second prediction based on the second update (par. 241-243 user interface displays histogram for user interface this histogram is built upon model running and making predictions on datasets trained on the model).
As for claims 7, 14 and 20, Pasour teaches. The method of claim 6, wherein the second prediction represents a minimum or a maximum of updated variable states across a second time period, wherein the second time period ranges from a first future time period to a second future time period (par. 241-243 user interface displays histogram for user interface this histogram is built upon model running and making predictions on datasets trained on the model; the histogram shows more than one time entry for user selection thereby allowing the user to view predictions related to documents across different selected times).
(Note :) 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 USPQ 1038, 1039 (Fed. Cir. 1983) (quoting In re Lemelson, 397 F.2d 1006,1009, 158 USPQ 275, 277 (CCPA 1968)).
Response to Arguments
Applicant's arguments filed 08/26/2026 have been fully considered but they are not persuasive.
A1. Applicant argues that prior arts do not teach "generating, via a short-term
prediction module, a first prediction of a first update of the variable state, wherein the first prediction represents an optimized prediction of multiple updates on a short-term future time horizon; generating, via a terminal value prediction module, a second prediction of a second update to the variable state, wherein the second prediction represents optimized predictions of variable states on a long-term future time horizon at a time after the short-term future time horizon".
R1. Examiner does not agree, the claim limitation given broadest reasonable interpretation requires a module with an arbitrary name that is used in the generation of a prediction on information that is variable and this prediction has been optimized on a short term future time horizon but does not define a length of time; next generating with the use of a second module with arbitrary name a second prediction from an update of the variable information and this represents optimized prediction for a long-time future time horizon but does not give a time but suggests its after the short term future horizon so in a broadest sense we have generated two predictions along a time one near into the future and one far into the future but the time length is not suggested.
Paragraph 209 states that the objective function optimizer 940 can optimize objective functional to determine the optimal values of binary decision variables over a duration of optimized period and can use any of a variety of optimization techniques to formulate and optimize the objective function J, this includes Mixed integer Linear Programming, mixed integer stochastic optimization, convex programming etc… further into the disclosure makes mention of using mixed integer stochastic optimization, this would be interchangeable with the techniques listed in paragraph 209 since it was mentioned that “These and other optimization techniques are known in the art and will not be described in detail here.” Paragraph 206 the predictors are combined to determine future predictions in the calculations, these predictions are taken across time (short and long is inferred). Paragraphs 212-216 as discussed above one or variable/ parameters in the objective function J can be updated dynamically to updated the reliability efficiency of connected equipment the objective function optimizer 940 can be configured to optimize function J periodically in various time lengths that can be contrasted as short and long time. The objective function optimizer 940 generates optimization results. The optimization results may include the optimal values of the decision variables in the objective function J for each time step i in the optimization period. MPM system 602 uses the optimization results to generate equipment purchase and maintenance recommendations. The equipment purchase and maintenance recommendations may be based on the optimal values for the binary decision variables Bmain,i and Bcap,i determined by optimizing the objective function J. For example, a value of Bmain,25=1 for a particular device of connected equipment 610 may indicate that maintenance should be performed on that device at the 25th time step of the optimization period, whereas a value of Bmain,25=0 may indicate that the maintenance should not be performed at that time step.)
Paragraph 212-213 shows short and long term future horizons. In paragraph 213 the optimization results optimize the economic value of operating, maintaining, and purchasing connected equipment 610 over the duration of the optimization period. The optimization results optimize the net present value of one or more devices of connected equipment 610 at a particular point in time. The optimization results may cause BMS 606 to activate, deactivate, or adjust a setpoint for connected equipment 610 in order to achieve the optimal values of the decision variables specified in the optimization results.
Paragraph 214 states recommendations to buy equipment; this is another example of a product, software product that recommends based upon prediction.
Paragraph 218 teaches of the process 1000 is shown to include estimating an efficiency and reliability of the building equipment as a function of the equipment performance information (step 1006)
Paragraph 220 teaches that step 1006 can include predicting the efficiency ηi of the building equipment at each time step i of the optimization period.
Paragraphs 221-222 discusses degradation of equipment and formulating a prediction over the optimization period time steps. “. Step 1006 can include examining the time series of initial efficiency values η0 to determine the rate at which the efficiency degrades.”
Paragraph 224 combines this intake of information to make predictions “step 1006 includes using the equipment performance information to identify a current operating state of the building equipment. The current operating state can be examined to expose when the building equipment begin to degrade in performance and/or to predict when faults will occur.
EXAMINER NOTES: These examples discuss short and long timer predictions of the monitoring equipment in an HVAC to dynamically schedule maintenance, order parts and make repairs to prevent future failures across different time optimization periods that suggests short and long time future time horizons. None the less the alternative prior art Risbeck introduced to aid in the use of short and long term future time horizons for making predictions; Risbeck is describing an HVAC from the same assignee as ELBSAT and therefore makes an obvious case of inclusion to support that ELBSAT is concerned with short and long term prediction of equipment health.
Examiner recommends clarification amendment in the areas of what product is being produced; user interaction added into the claim limitations and displaying results to an end user.
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Inquires
Any inquiry concerning this communication should be directed to NICHOLAS AUGUSTINE at telephone number (571)270-1056.
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.
PNG
media_image1.png
213
559
media_image1.png
Greyscale
/NICHOLAS AUGUSTINE/Primary Examiner, Art Unit 2178 September 30, 2026
