DETAILED ACTION
This office action is in response to applicant’s communication filed 09/21/2023.
Claim(s) 1-20 have been considered.
- Claim(s) 1-20 are pending.
- Claim(s) 1-20 have been rejected as described below.
- This action is NON-FINAL.
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 .
Information Disclosure Statement
Examiner acknowledges the entry of following Information Disclosure Statement (IDS) document(s) from applicant:
The information disclosure statement(s) filed 09/27/2023 has/have been considered by examiner.
Priority
Applicant’s claim for the benefit of a prior-filed application under 35 U.S.C. 119(e) or under 35 U.S.C. 120, 121, 365(c), or 386(c) is acknowledged. The provisional application 63/411,864 was filed on 09/30/2022.
Specification
The disclosure filed 09/21/2023 are acknowledged and accepted by examiner for examination.
Drawings
The drawings filed 09/21/2023 are acknowledged and accepted by examiner for examination.
Claim Objections
Claim(s) 6 and 9 is/are objected to due to having minor informalities:
Claim 6 in L4 ends with “..”, which should be ending with a period “.” instead.
Claim 9 in L1 recites: “wherein the occupancy predication comprises …”, which should be “wherein the occupancy prediction comprises …”.
Correction is required.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claim(s) 6 and 11 is/are rejected under 35 U.S.C. 101 because the claimed invention is/are directed to an abstract idea without significantly more.
Claim 6 recites a method (apparatus), which is a statutory category of invention.
However, claim 6 recites, “using a first value of the occupancy prediction to generate an infection risk estimate for the building; and using the infection risk estimate to generate a second value of the occupancy prediction.”. This/these limitation(s) fall(s) into the “mental process” group of abstract ideas, because the recited step(s) of generating the data, appear to be an observation/evaluation/calculation and judgement that can be performed in the human mind (and/or written with a pen on a paper), under broadest reasonable interpretation. These/This limitation(s) therefore recite(s) concept(s) performed in the human mind. Also note, all of these steps, can be written down with a pen on a paper. Note, the courts do not distinguish between mental processes that are performed entirely in the human mind and mental processes that require a human to use a physical aid (e.g., pen and paper or a slide rule) to perform the claim limitation. Nor do the courts distinguish between claims that recite mental processes performed by humans and claims that recite mental processes performed on a computer. As the Federal Circuit has explained, "[c]ourts have examined claims that required the use of a computer and still found that the underlying, patent-ineligible invention could be performed via pen and paper or in a person’s mind. (See MPEP 2106.04(a)(2)) The mere nominal recitation of a generic processor/computer devices to perform this determination does not take the claim limitation out of the mental processes grouping. Thus, the claim recites a mental process. Thus, this/these limitation(s) fall(s) into the “mental processes” grouping of abstract ideas in 2019 PEG Section I, 84 Fed. Reg. at 52.
This judicial exception is not integrated into a practical application. Besides the abstract ideas, claim recites additional element(s) based on its dependency from claim 1, such as, “providing an occupancy prediction for a building using an occupancy prediction model that uses both historical values and forecast values of an environmental condition as inputs; and controlling the building equipment based on the occupancy prediction.” Note, these are recited in a high level of generality. Using an occupancy prediction model to provide the data are thus merely invoking computer components as a tool. This/these element(s) is/are general purpose computer/computer component or other machinery that are used in its ordinary capacity for economic or other tasks (e.g., to receive, store, or transmit data) or being considered as simply adding a general purpose computer or computer components after the fact to an abstract idea (e.g., a fundamental economic practice or mathematical equation) and thus does not integrate a judicial exception into a practical application or provide significantly more (MPEP 2106.05(f)).
From above, “and controlling the building equipment based on the occupancy prediction.”, which is/are described at a high level of generality and without improvements to computer functionality and also appears to have simply attempted to limit the use of the abstract idea to a particular technological environment (i.e., a particular technological environment or field of use) (See MPEP 2106.05(a), and MPEP 2106.05(h)). Limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not amount to significantly more than the exception itself, and cannot integrate a judicial exception into a practical application (MPEP 2106.05(h)).
Accordingly, even when viewed in combination, these additional elements do not integrate the recited judicial exception into a practical application and the claim is directed to the judicial exception.
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception due to the same reasons as stated above. For example, “providing an occupancy prediction for a building using an occupancy prediction model that uses both historical values and forecast values of an environmental condition as inputs; and controlling the building equipment based on the occupancy prediction.” Note, these are recited in a high level of generality. Using an occupancy prediction model to provide the data are thus merely invoking computer components as a tool. This/these element(s) is/are general purpose computer/computer component or other machinery that are used in its ordinary capacity for economic or other tasks (e.g., to receive, store, or transmit data) or being considered as simply adding a general purpose computer or computer components after the fact to an abstract idea (e.g., a fundamental economic practice or mathematical equation) and thus does not integrate a judicial exception into a practical application or provide significantly more (MPEP 2106.05(f)).
From above, “and controlling the building equipment based on the occupancy prediction.”, which is/are described at a high level of generality and without improvements to computer functionality and also appears to have simply attempted to limit the use of the abstract idea to a particular technological environment (i.e., a particular technological environment or field of use) (See MPEP 2106.05(a), and MPEP 2106.05(h)). Limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not amount to significantly more than the exception itself, and cannot integrate a judicial exception into a practical application (MPEP 2106.05(h)).
Accordingly, in combination, these additional elements do not amount to significantly more than the judicial exception.
Therefore, claim 6 is not patent eligible.
Claim 11 recites a method (apparatus), which is a statutory category of invention.
However, claim 11 recites, “and generating a setpoint for the building equipment by performing an optimization using the predictive building model.”. This/these limitation(s) fall(s) into the “mental process” group of abstract ideas, because the recited step(s) of generating the setpoint, appear to be an observation/evaluation/calculation and judgement that can be performed in the human mind (and/or written with a pen on a paper), under broadest reasonable interpretation. These/This limitation(s) therefore recite(s) concept(s) performed in the human mind. Also note, all of these steps, can be written down with a pen on a paper. Note, the courts do not distinguish between mental processes that are performed entirely in the human mind and mental processes that require a human to use a physical aid (e.g., pen and paper or a slide rule) to perform the claim limitation. Nor do the courts distinguish between claims that recite mental processes performed by humans and claims that recite mental processes performed on a computer. As the Federal Circuit has explained, "[c]ourts have examined claims that required the use of a computer and still found that the underlying, patent-ineligible invention could be performed via pen and paper or in a person’s mind. (See MPEP 2106.04(a)(2)) The mere nominal recitation of a generic processor/computer devices to perform this determination does not take the claim limitation out of the mental processes grouping. Thus, the claim recites a mental process. Thus, this/these limitation(s) fall(s) into the “mental processes” grouping of abstract ideas in 2019 PEG Section I, 84 Fed. Reg. at 52.
This judicial exception is not integrated into a practical application. Besides the abstract ideas, claim recites additional element(s) based on its dependency from claim 1, such as, “providing an occupancy prediction for a building using an occupancy prediction model that uses both historical values and forecast values of an environmental condition as inputs; and controlling the building equipment based on the occupancy prediction.” Note, these are recited in a high level of generality. Using an occupancy prediction model to provide the data are thus merely invoking computer components as a tool. This/these element(s) is/are general purpose computer/computer component or other machinery that are used in its ordinary capacity for economic or other tasks (e.g., to receive, store, or transmit data) or being considered as simply adding a general purpose computer or computer components after the fact to an abstract idea (e.g., a fundamental economic practice or mathematical equation) and thus does not integrate a judicial exception into a practical application or provide significantly more (MPEP 2106.05(f)). Same analysis is applicable for “using the predictive building model.” and “using the occupancy prediction as an input to a predictive building model” of claim 11 as well.
From above, “and controlling the building equipment based on the occupancy prediction.”, which is/are described at a high level of generality and without improvements to computer functionality and also appears to have simply attempted to limit the use of the abstract idea to a particular technological environment (i.e., a particular technological environment or field of use) (See MPEP 2106.05(a), and MPEP 2106.05(h)). Limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not amount to significantly more than the exception itself, and cannot integrate a judicial exception into a practical application (MPEP 2106.05(h)).
Accordingly, even when viewed in combination, these additional elements do not integrate the recited judicial exception into a practical application and the claim is directed to the judicial exception.
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception due to the same reasons as stated above. For example, “providing an occupancy prediction for a building using an occupancy prediction model that uses both historical values and forecast values of an environmental condition as inputs; and controlling the building equipment based on the occupancy prediction.” Note, these are recited in a high level of generality. Using an occupancy prediction model to provide the data are thus merely invoking computer components as a tool. This/these element(s) is/are general purpose computer/computer component or other machinery that are used in its ordinary capacity for economic or other tasks (e.g., to receive, store, or transmit data) or being considered as simply adding a general purpose computer or computer components after the fact to an abstract idea (e.g., a fundamental economic practice or mathematical equation) and thus does not integrate a judicial exception into a practical application or provide significantly more (MPEP 2106.05(f)). Same analysis is applicable for “using the predictive building model.” and “using the occupancy prediction as an input to a predictive building model” of claim 11 as well.
From above, “and controlling the building equipment based on the occupancy prediction.”, which is/are described at a high level of generality and without improvements to computer functionality and also appears to have simply attempted to limit the use of the abstract idea to a particular technological environment (i.e., a particular technological environment or field of use) (See MPEP 2106.05(a), and MPEP 2106.05(h)). Limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not amount to significantly more than the exception itself, and cannot integrate a judicial exception into a practical application (MPEP 2106.05(h)).
Accordingly, in combination, these additional elements do not amount to significantly more than the judicial exception.
Therefore, claim 11 is not patent eligible.
Accordingly, claim(s) 6 and 11 are not patent eligible.
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.
Claim(s) 1, 6-7, 9, 11-13, 16-17, and 19 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Risbeck (US 20200348038 A1).
Regarding claim 1, Risbeck teaches:
A method for controlling building equipment, comprising: (Fig. 5-6, 0158, 0207-09 etc. teach computer/processor including machine-readable media executing the functions.)
providing an occupancy prediction for a building using an occupancy prediction model that uses both historical values and forecast values of an environmental condition as inputs; (See Fig. 6, 602-608 for the prediction; 0004 teaches, “The controller is configured to obtain a dynamic temperature model and a dynamic infectious quanta model for the one or more building zones, determine an infection probability, and generate control decisions for the airside HVAC equipment using the dynamic temperature model, the dynamic infectious quanta model, and the infection probability. … Obtaining the dynamic temperature model and the dynamic infectious quanta model can include receiving one or both of the models as inputs, generating one or both of the models, retrieving one or both of the models from a database or from a user device, or otherwise obtaining one or both of the models in any other manner.” Fig. 6-7 and 0167 teach, “optimization manager 412 may be configured to re-optimize during a middle of the day if ambient sensor data from ambient sensors 314 (e.g., ambient temperature, outdoor temperature, outdoor humidity, etc.) and/or weather forecasts and/or occupancy forecasts indicate that the optimization should be re-performed (e.g., if the weather forecasts are incorrect or change)” For historical values, see 0029-30, 0096, 0110 etc. teach that the data points can be historical values of outdoor air temperature, humidity, air quality, etc., energy usage of a campus or building, etc.)
and controlling the building equipment based on the occupancy prediction. (See Fig. 6, 612-616 for the control action(s); As above, 0004 teaches, “The controller is configured to obtain a dynamic temperature model and a dynamic infectious quanta model for the one or more building zones, determine an infection probability, and generate control decisions for the airside HVAC equipment using the dynamic temperature model, the dynamic infectious quanta model, and the infection probability. In some embodiments, the control decisions provide a desired level of disinfection. In some embodiments, the control decisions indicate an amount of the clean air to be provided to the one or more building zones by the airside HVAC equipment.)
Regarding claim 6, Risbeck discloses the system as recited in claim 1.
Risbeck further discloses wherein providing the occupancy prediction comprises: using a first value of the occupancy prediction to generate an infection risk estimate for the building; and using the infection risk estimate to generate a second value of the occupancy prediction. (0004 teaches, “The controller is configured to obtain a dynamic temperature model and a dynamic infectious quanta model for the one or more building zones, determine an infection probability, and generate control decisions for the airside HVAC equipment using the dynamic temperature model, the dynamic infectious quanta model, and the infection probability.” For the second value of occupancy prediction, see step 716 of Fig. 7 that estimates cost using the aggregated model data of steps 704-710, which includes the data from infectious quanta model.).
Regarding claim 7, Risbeck discloses the system as recited in claim 1.
Risbeck further discloses wherein the environmental condition is a particulate matter concentration or air quality index. (0163 teaches, “n some embodiments, zone-by-zone temperature measurements are obtained by controller 310 from zone sensors 312 (e.g., a collection of temperature, humidity, CO2, air quality, etc., sensors that are positioned at each of the multiple zones 206). Also, 0092 teaches, “carbon dioxide (CO2) is a readily-measureable parameter that can be a proxy species, measured by zone sensors 312. In some embodiments, a concentration of CO2 in the zones 206 may be directly related to a concentration of the infectious quanta.”).
Regarding claim 9, Risbeck discloses the system as recited in claim 1.
Risbeck further discloses wherein the occupancy predication comprises a timeseries of predicted occupancy values for a plurality of time steps of an upcoming time period. (0097, 0099 and 0177 teach various occupancy prediction data integrated over all time steps of a given time period).
Regarding claim 11, Risbeck discloses the system as recited in claim 1.
Risbeck further discloses wherein controlling the building equipment based on the occupancy prediction comprises using the occupancy prediction as an input to a predictive building model and generating a setpoint for the building equipment by performing an optimization using the predictive building model. (Fig. 7 and 0184 teach step 708 (aggregated models) being used for step 714 to 718 for building equipment control, more specifically towards estimation of operating cost, for example. For the setpoint of equipment being part of control decisions, see 0016 teaches, “In some embodiments, the control decisions indicate an amount of clean air to be provided to the one or more building zones and using the control decisions to operate the VAV unit includes generating both a temperature setpoint and a minimum airflow constraint for the VAV unit. The minimum airflow constraint may be the amount of clean air to be provided to the one or more building zones. Using the control decisions to operate the VAV unit may further include operating the VAV unit to control a temperature of the one or more building zones based on the temperature setpoint, subject to the minimum airflow constraint.”.)
Regarding claim 12, Risbeck teaches:
One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising: (Fig. 5-6, 0158, 0207-09 etc. teach computer/processor including machine-readable media executing the functions.)
predicting a future occupancy of a space by using forecasted values relating to infection risk and weather as inputs to an occupancy model; (See Fig. 6, 602-608 for the prediction; 0004 teaches, “The controller is configured to obtain a dynamic temperature model and a dynamic infectious quanta model for the one or more building zones, determine an infection probability, and generate control decisions for the airside HVAC equipment using the dynamic temperature model, the dynamic infectious quanta model, and the infection probability. … Obtaining the dynamic temperature model and the dynamic infectious quanta model can include receiving one or both of the models as inputs, generating one or both of the models, retrieving one or both of the models from a database or from a user device, or otherwise obtaining one or both of the models in any other manner.” Fig. 6-7 and 0167 teach, “optimization manager 412 may be configured to re-optimize during a middle of the day if ambient sensor data from ambient sensors 314 (e.g., ambient temperature, outdoor temperature, outdoor humidity, etc.) and/or weather forecasts and/or occupancy forecasts indicate that the optimization should be re-performed (e.g., if the weather forecasts are incorrect or change)”)
and controlling building equipment to affect heating, ventilation, or cooling of the space based on the future occupancy of the space. (See Fig. 6, 612-616 for the control action(s); As above, 0004 teaches, “The controller is configured to obtain a dynamic temperature model and a dynamic infectious quanta model for the one or more building zones, determine an infection probability, and generate control decisions for the airside HVAC equipment using the dynamic temperature model, the dynamic infectious quanta model, and the infection probability. In some embodiments, the control decisions provide a desired level of disinfection. In some embodiments, the control decisions indicate an amount of the clean air to be provided to the one or more building zones by the airside HVAC equipment.)
Regarding claim 13, Risbeck discloses the system as recited in claim 12.
Risbeck further discloses wherein the occupancy model comprises a plurality of artificial neural networks. (0148 teaches, “In some embodiments, optimization manager 412 is configured to solve a number of one-step optimization problems (e.g., formulate different optimization problems for different sets of the control variables and solve the optimization problem over a single timestep) in a training period, and then train a function approximator (e.g., a neural network) to recreate a mapping. This can improve an efficiency of the optimization.”. 0168 teaches, “controller 310 uses neural-network suggestions”.).
Regarding claim 16, Risbeck discloses the system as recited in claim 12.
Risbeck further discloses wherein predicting the future occupancy of the space further comprises using information indicative of an event occurring external to the space. (0155 teaches, “In some embodiments, optimization manager 412 requires various simulation data in order to perform the off-line simulation (e.g., to determine the design parameters). … The simulation data … can include … external temperature, humidity, and solar data, filtration efficiency, pressure drop, …”. 0060 also teaches, “an external weather service may provide an outside air temperature forecast for each hour of the next 24 hours.”.).
Regarding claim 17, Risbeck discloses the system as recited in claim 12.
Risbeck further discloses the operations further comprising training the occupancy model on historical occupancy data, infection risk history, and weather measurements. (0029-30, 0096, 0110 etc. teach that the data points can be historical values of outdoor air temperature, humidity, air quality, etc., energy usage of a campus or building, etc. 0063 teaches the dynamic aspect of the models including infectious quanta being a quantity along with other variables (changing over time).)
Regarding claim 19, Risbeck discloses the system as recited in claim 12.
Risbeck further discloses wherein controlling the building equipment based on the future occupancy of the space comprises applying the future occupancy as an input to a building model and using the building model for model predictive control. (Fig. 7 and 0184 teach step 708 (aggregated models) being used for step 714 to 718 for building equipment control, more specifically towards estimation of operating cost, for example. Also see 0016 teaches, “In some embodiments, the control decisions indicate an amount of clean air to be provided to the one or more building zones and using the control decisions to operate the VAV unit includes generating both a temperature setpoint and a minimum airflow constraint for the VAV unit. The minimum airflow constraint may be the amount of clean air to be provided to the one or more building zones. Using the control decisions to operate the VAV unit may further include operating the VAV unit to control a temperature of the one or more building zones based on the temperature setpoint, subject to the minimum airflow constraint.”.)
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.
Claim(s) 2 is/are rejected under 35 U.S.C. 103 as being unpatentable over Risbeck (US 20200348038 A1) in view of Joy Dutta (OccupancySense: Context-based indoor occupancy detection & prediction using CatBoost model. Article. [online]. 2022) hereinafter Dutta.
Regarding claim 2, Risbeck discloses the system as recited in claim 1.
Risbeck does not explicitly disclose:
wherein providing the occupancy prediction comprises: generating, by at least one first neural network, an encoder state based on historical timeseries data of occupancy and the environmental condition as inputs; generating, by a second neural network, the occupancy prediction based on the encoder state and a forecast timeseries for the environmental condition.
Dutta further discloses wherein providing the occupancy prediction comprises: generating, by at least one first neural network, an encoder state based on historical timeseries data of occupancy and the environmental condition as inputs; (Fig. 1 & section 3.1-3.2 in pages 3-4 teach encoding data via a neural network based on historical weather context data and occupancy headcount data.)
generating, by a second neural network, the occupancy prediction based on the encoder state and a forecast timeseries for the environmental condition. (Fig. 1 & section 3.1-3.3 in pages 3-4 teach in the model ready dataset, 33 features are being considered in total by including all IAQ, context and time stamp extracted features. See CatBoost in Fig. 1 for the second neural network used.)
Accordingly, as Risbeck and Dutta are directed to building/HVAC system and control technology using prediction modeling, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have specifically added the feature of utilizing the well-known technology of utilizing an LSTM neural network and encoder-decoder architecture, as taught by Dutta to the building/HVAC control system including prediction modeling that uses neural networks for optimization as taught by Risbeck. One would have been motivated to combine these features because such a combined system/method would have enabled the usage of a specific type of neural networks which are well-known in the art to be used together as this data fusion helps us to achieve higher forecasting accuracy along with the integration of state of the art gradient boosting based categorical features supported CatBoost algorithm, as evident in Dutta, abstract, section 3.1-3.3, etc.
Claim(s) 3-5 is/are rejected under 35 U.S.C. 103 as being unpatentable over Risbeck (US 20200348038 A1) in view of Joy Dutta (OccupancySense: Context-based indoor occupancy detection & prediction using CatBoost model. Article. [online]. 2022) hereinafter Dutta in further view of Murugesan (US 20210056386 A1).
Regarding claim 3, Risbeck and Dutta disclose the system as recited in claim 2.
Risbeck and Dutta do not explicitly disclose the additional limitations of claim 3.
Murugesan further discloses wherein the at least one first neural network comprises a long- short-term-memory network receiving a plurality of values of the occupancy and a plurality of values of the environmental condition from the historical timeseries data as inputs. (Fig. 6, 0094-96, 0099-0100 and 0146 teach LSTM layers and encoder-decoder architecture that receive these values. More specifically, 0146 teaches, “Inference model 926 may provide the generated probability distributions to building controller 932 and/or to user presentation system 930 to control building equipment 934 and/or to be displayed at a user device. Inference model 926 may be a neural network, an LSTM S2S neural network (e.g., LSTM S2S neural network 400), Random Forest, a support vector machine, etc.”. 0100 teaches, “Referring now to FIGS. 7 and 8, an LSTM S2S neural network 700 for energy forecasting is shown during a training phase and an inference phase, according to an exemplary embodiment. The LSTM S2S 700 may be the same as or similar to the LSTM S2S 400 described with reference to FIG. 4. More particularly, the LSTM S2S neural network 700 includes an encoder 708, a decoder 710, an input sequence 702 to the encoder 708, an output sequence 704 of the decoder 710, and a feedback sequence to the decoder 710. The output of decoder 710 at each time-step can be a point-forecast of energy.”)
Accordingly, as Risbeck, Dutta and Murugesan are directed to building/HVAC system and control technology using prediction modeling, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have specifically added the feature of utilizing the well-known technology of utilizing an LSTM neural network and encoder-decoder architecture receiving various values, as taught by Murugesan to the building/HVAC control system including prediction modeling that uses neural networks for optimization as taught by Risbeck and Dutta. One would have been motivated to combine these features because such a combined system/method would have enabled the usage of a specific type of neural network such as LSTM with encoder-decoder architecture which are well-known in the art to be used together to manage complex, time-dependent building dynamics such as receiving past sequence data and generating future sequence data, as evident in Murugesan, 0094-96, 0099-0100, 0146, etc.
Regarding claim 4, Risbeck, and Dutta disclose the system as recited in claim 2.
Risbeck and Dutta do not explicitly disclose the additional limitations of claim 4.
Murugesan further discloses wherein the at least one second neural network comprises a long- short-term-memory network receiving the encoder state and a plurality of values of the environmental condition from the forecast timeseries as inputs. (Fig. 6, 0094-96, 0099-0100 and 0146 teach LSTM layers and encoder-decoder architecture that receive these values. More specifically, 0146 teaches, “Inference model 926 may provide the generated probability distributions to building controller 932 and/or to user presentation system 930 to control building equipment 934 and/or to be displayed at a user device. Inference model 926 may be a neural network, an LSTM S2S neural network (e.g., LSTM S2S neural network 400), Random Forest, a support vector machine, etc.”. 0100 teaches, “Referring now to FIGS. 7 and 8, an LSTM S2S neural network 700 for energy forecasting is shown during a training phase and an inference phase, according to an exemplary embodiment. The LSTM S2S 700 may be the same as or similar to the LSTM S2S 400 described with reference to FIG. 4. More particularly, the LSTM S2S neural network 700 includes an encoder 708, a decoder 710, an input sequence 702 to the encoder 708, an output sequence 704 of the decoder 710, and a feedback sequence to the decoder 710. The output of decoder 710 at each time-step can be a point-forecast of energy.”)
Accordingly, as Risbeck, Dutta and Murugesan are directed to building/HVAC system and control technology using prediction modeling, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have specifically added the feature of utilizing the well-known technology of utilizing an LSTM neural network and encoder-decoder architecture receiving various values, as taught by Murugesan to the building/HVAC control system including prediction modeling that uses neural networks for optimization as taught by Risbeck and Dutta. One would have been motivated to combine these features because such a combined system/method would have enabled the usage of a specific type of neural network such as LSTM with encoder-decoder architecture which are well-known in the art to be used together to manage complex, time-dependent building dynamics such as receiving past sequence data and generating future sequence data, as evident in Murugesan, 0094-96, 0099-0100, 0146, etc.
Regarding claim 5, Risbeck, and Dutta disclose the system as recited in claim 2.
Risbeck and Dutta do not explicitly disclose the additional limitations of claim 5.
Murugesan further discloses wherein the forecast timeseries for the environmental condition comprises weather values associated with a plurality of time steps and the occupancy prediction comprises a plurality of occupancy values associated with the plurality of time steps. (Fig. 6, 0094-96, 0099-0100 and 0146 teach LSTM layers and encoder-decoder architecture that receive these values. More specifically, 0146 teaches, “Inference model 926 may provide the generated probability distributions to building controller 932 and/or to user presentation system 930 to control building equipment 934 and/or to be displayed at a user device. Inference model 926 may be a neural network, an LSTM S2S neural network (e.g., LSTM S2S neural network 400), Random Forest, a support vector machine, etc.”. 0100 teaches, “Referring now to FIGS. 7 and 8, an LSTM S2S neural network 700 for energy forecasting is shown during a training phase and an inference phase, according to an exemplary embodiment. The LSTM S2S 700 may be the same as or similar to the LSTM S2S 400 described with reference to FIG. 4. More particularly, the LSTM S2S neural network 700 includes an encoder 708, a decoder 710, an input sequence 702 to the encoder 708, an output sequence 704 of the decoder 710, and a feedback sequence to the decoder 710. The output of decoder 710 at each time-step can be a point-forecast of energy.” Regarding plurality time steps, see 0100 as above.)
Accordingly, as Risbeck, Dutta and Murugesan are directed to building/HVAC system and control technology using prediction modeling, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have specifically added the feature of utilizing the well-known technology of utilizing an LSTM neural network and encoder-decoder architecture receiving various values, as taught by Murugesan to the building/HVAC control system including prediction modeling that uses neural networks for optimization as taught by Risbeck and Dutta. One would have been motivated to combine these features because such a combined system/method would have enabled the usage of a specific type of neural network such as LSTM with encoder-decoder architecture which are well-known in the art to be used together to manage complex, time-dependent building dynamics such as receiving past sequence data and generating future sequence data, as evident in Murugesan, 0094-96, 0099-0100, 0146, etc.
Claim(s) 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Risbeck (US 20200348038 A1) in view of Fadell (US 20130173064 A1).
Regarding claim 8, Risbeck discloses the system as recited in claim 1.
Risbeck does not explicitly disclose:
wherein the environmental condition is precipitation.
Fadell further discloses wherein the environmental condition is precipitation. (0116 teaches, “the weather forecast data includes predictions more than 24 hours in the future, and can include predictions such as temperature, humidity and/or dew point, solar output, precipitation, wind and natural disasters. According to some embodiments the model for the enclosure is updated based also on historical weather data such as temperature, humidity, wind, solar output and precipitation. According to some embodiments, the model for the enclosure is updated based in part on the occupancy data, such as predicted and/or detected occupancy data.”)
Accordingly, as Risbeck and Fadell are directed to building/HVAC system and control technology using prediction modeling, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have specifically added the feature of utilizing the well-known technology of utilizing precipitation data as an environmental condition, as taught by Fadell to the building/HVAC control system including prediction modeling that uses neural networks for optimization as taught by Risbeck. One would have been motivated to combine these features because such a combined system/method would have enabled the usage of a specific type of data among other forecast and historical data as a known way of updating models with various inputs, as evident in Fadell, 0116, etc.
Claim(s) 14-15, 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Risbeck (US 20200348038 A1) in view of Murugesan (US 20210056386 A1).
Regarding claim 14, Risbeck discloses the system as recited in claim 12.
Risbeck does not explicitly disclose:
wherein the occupancy model comprises a long short-term memory network and has an encoder-decoder architecture.
Murugesan further discloses wherein the occupancy model comprises a long short-term memory network and has an encoder-decoder architecture. (Fig. 6, 0094-96, 0099-0100 and 0146 teach LSTM layers and encoder-decoder architecture. More specifically, 0146 teaches, “Inference model 926 may provide the generated probability distributions to building controller 932 and/or to user presentation system 930 to control building equipment 934 and/or to be displayed at a user device. Inference model 926 may be a neural network, an LSTM S2S neural network (e.g., LSTM S2S neural network 400), Random Forest, a support vector machine, etc.”. 0100 teaches, “Referring now to FIGS. 7 and 8, an LSTM S2S neural network 700 for energy forecasting is shown during a training phase and an inference phase, according to an exemplary embodiment. The LSTM S2S 700 may be the same as or similar to the LSTM S2S 400 described with reference to FIG. 4. More particularly, the LSTM S2S neural network 700 includes an encoder 708, a decoder 710, an input sequence 702 to the encoder 708, an output sequence 704 of the decoder 710, and a feedback sequence to the decoder 710. The output of decoder 710 at each time-step can be a point-forecast of energy.”)
Accordingly, as Risbeck and Murugesan are directed to building/HVAC system and control technology using prediction modeling, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have specifically added the feature of utilizing the well-known technology of utilizing an LSTM neural network and encoder-decoder architecture, as taught by Murugesan to the building/HVAC control system including prediction modeling that uses neural networks for optimization as taught by Risbeck. One would have been motivated to combine these features because such a combined system/method would have enabled the usage of a specific type of neural network such as LSTM with encoder-decoder architecture which are well-known in the art to be used together to manage complex, time-dependent building dynamics such as receiving past sequence data and generating future sequence data, as evident in Murugesan, 0094-96, 0099-0100, 0146, etc.
Regarding claim 15, Risbeck discloses the system as recited in claim 12.
Risbeck does not explicitly disclose:
the operations further comprising using historical occupancy measurements as inputs to the occupancy model.
Murugesan further discloses the operations further comprising using historical occupancy measurements as inputs to the occupancy model. (Among many exemplary paras, see 0012 teaches, “the instructions cause the one or more processors to generate input data that indicates index values of the updated prediction set of measurements that are associated with the predetermined value; and provide the input data to the predictive model.” and 0159 teaches, “The prediction set of measurements (e.g., the historical prediction set of measurements) may include previous predictions that the data source provider made as to future values of the data point at the various time-steps. The actual set of measurements (e.g., the historical actual set of measurements) may include the actual values of the data point at the same time-steps.”)
Accordingly, as Risbeck and Murugesan are directed to building/HVAC system and control technology using prediction modeling, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have specifically added the feature of utilizing the well-known technology of utilizing historical data as inputs to the prediction model, as taught by Murugesan to the building/HVAC control system including prediction modeling that uses neural networks for optimization as taught by Risbeck. One would have been motivated to combine these features because such a combined system/method would have enabled selecting specific types of data forecasts to use as inputs into prediction models, for example, which also would have enabled checking if these are outside of tolerance of corresponding historical actual measurements, etc. as evident in Murugesan, 0001, 0003, 0012, 0159, etc.
Regarding claim 20, Risbeck discloses the system as recited in claim 12.
Risbeck does not explicitly disclose:
wherein the forecasted values relating to weather are indicative of precipitation or air quality index.
Murugesan further discloses wherein the forecasted values relating to weather are indicative of precipitation or air quality index. (0096 teaches, “The sequences 408, 410, and 412 can represent historical values of a data point (the sequence 410), predicted values of the data point for one or multiple times in the future (the sequence 408), and the predicted values of the data point fed back into the decoder 404 (the sequence 412). … The data point can be a control point, an ambient condition data point (e.g., outdoor air temperature, humidity, air quality, etc.), energy usage of a campus or building, etc.”)
Accordingly, as Risbeck and Murugesan are directed to building/HVAC system and control technology using prediction modeling, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have specifically added the feature of utilizing the well-known technology of utilizing various types of past and forecast data including air quality data in building control, as taught by Murugesan to the building/HVAC control system including prediction modeling that uses neural networks for optimization as taught by Risbeck. One would have been motivated to combine these features because such a combined system/method would have enabled the usage of a specific type of neural network such as LSTM with encoder-decoder architecture which are well-known in the art to be used together to manage complex, time-dependent building dynamics such as receiving past sequence data and generating future sequence data, as evident in Murugesan, 0094-96, 0099-0100, 0146, etc.
Claim(s) 10 and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Risbeck (US 20200348038 A1) in view of Brahme (US 20230288092 A1).
Regarding claim 10, Risbeck discloses the system as recited in claim 1.
Risbeck does not explicitly disclose:
wherein controlling building equipment based on the occupancy prediction comprises classifying a time period into a classification based on the occupancy prediction, selecting control settings based on the classification, and controlling the building equipment using the control settings.
Brahme further discloses wherein controlling building equipment based on the occupancy prediction comprises classifying a time period into a classification based on the occupancy prediction, selecting control settings based on the classification, and controlling the building equipment using the control settings. (0031 teaches, “Occupancies 156, 162 may be “occupied” if one or more people are in the space (or predicted to be in the space) or “unoccupied” if no one is in the space (or no one is predicted to be in the space). … the predicted occupancy 162, which may indicate that a space is likely to be occupied during certain portions of the day and unoccupied during other portions of the day. If the space serviced by the HVAC system 100 becomes unoccupied during the demand response time or is predicted to be unoccupied during the demand response time, the operation schedule 164 may be adjusted to cause compressor 106 to shut off at least when the serviced space is unoccupied.”)
Accordingly, as Risbeck and Brahme are directed to building/HVAC system and control technology using prediction modeling, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have specifically added the feature of utilizing the well-known technology of utilizing classification of predicted occupancy to control building equipment accordingly, as taught by Brahme to the building/HVAC control system including prediction modeling that uses neural networks for optimization as taught by Risbeck. One would have been motivated to combine these features because such a combined system/method would have enabled varying operation schedules in future based on occupancy prediction which would improve occupant comfort while also saving energy (e.g., by meeting comfort and/or energy-saving criteria), as evident in Brahme, 0004, 0031, etc.
Regarding claim 18, Risbeck discloses the system as recited in claim 12.
Risbeck does not explicitly disclose:
wherein controlling building equipment based on the future occupancy of the space comprises: determining a classification of a time period as occupied or unoccupied based on the future occupancy; and selecting a setting for the building equipment based on the classification.
Brahme further discloses wherein controlling building equipment based on the future occupancy of the space comprises: determining a classification of a time period as occupied or unoccupied based on the future occupancy; and selecting a setting for the building equipment based on the classification. (0031 teaches, “Occupancies 156, 162 may be “occupied” if one or more people are in the space (or predicted to be in the space) or “unoccupied” if no one is in the space (or no one is predicted to be in the space). … the predicted occupancy 162, which may indicate that a space is likely to be occupied during certain portions of the day and unoccupied during other portions of the day. If the space serviced by the HVAC system 100 becomes unoccupied during the demand response time or is predicted to be unoccupied during the demand response time, the operation schedule 164 may be adjusted to cause compressor 106 to shut off at least when the serviced space is unoccupied.”)
Accordingly, as Risbeck and Brahme are directed to building/HVAC system and control technology using prediction modeling, it would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have specifically added the feature of utilizing the well-known technology of utilizing classification of predicted occupancy to control building equipment accordingly, as taught by Brahme to the building/HVAC control system including prediction modeling that uses neural networks for optimization as taught by Risbeck. One would have been motivated to combine these features because such a combined system/method would have enabled varying operation schedules in future based on occupancy prediction which would improve occupant comfort while also saving energy (e.g., by meeting comfort and/or energy-saving criteria), as evident in Brahme, 0004, 0031, etc.
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. “The use of patents as references is not limited to what the patentees describe as their own inventions or to the problems with which they are concerned. They are part of the literature of the art, relevant for all they contain.” 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)). Further, a reference may be relied upon for all that it would have reasonably suggested to one having ordinary skill the art, including nonpreferred embodiments. Merck & Co. v. Biocraft Laboratories, 874 F.2d 804, 10 USPQ2d 1843 (Fed. Cir.), cert, denied, 493 U.S. 975 (1989). See also Upsher-Smith Labs. v. Pamlab, LLC, 412 F.3d 1319, 1323, 75 USPQ2d 1213, 1215 (Fed. Cir. 2005) (reference disclosing optional inclusion of a particular component teaches compositions that both do and do not contain that component); Celeritas Technologies Ltd. v. Rockwell International Corp., 150 F.3d 1354, 1361, 47 USPQ2d 1516, 1522-23 (Fed. Cir. 1998).
Pertinent Art(s)
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Ba et al. (US 20220146136 A1) is related to an approach for monitoring, detecting and localizing anomalies of HVAC system by using the combination of thermodynamics models, the energy balance of a zone in steady state, and data analytics. The approach determines, via machine learning, the ideal thermodynamic model for an area serviced by an HVAC system. The approach retrieves reading from various sensors and insert the current sensor reading into the ideal model. In the presence of anomalies, the parameters of the model will deviate from their nominal values and an appropriate action can be taken based on the severity of the detected and localized anomalies.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MARZIA T MONTY whose telephone number is (571)272-5441. The examiner can normally be reached on T-F: 11am -5pm (approximately). 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, Robert Fennema can be reached on 571-272-2748. The fax phone number for the organization where this application or proceeding is assigned is 571-273-5441.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR.
Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/MARZIA T MONTY/Examiner, Art Unit 2117
/ROBERT E FENNEMA/Supervisory Patent Examiner, Art Unit 2117
Prosecution Insights