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 therefor, 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. A subject matter eligibility analysis is set forth below. See MPEP 2106.
Specifically, representative Claim 1 recites:
A system for identifying and classifying airflow system types, the system comprising:
an airflow system configured to receive air via a return air pathway and supply air via a supply air pathway;
a comfort sensor disposed within the supply air pathway or proximate to an opening of the supply air pathway of the airflow system and configured to collect supply airflow data including at least one of a supply air temperature or a supply air pressure of supply air supplied from the airflow system via the supply air pathway;
a filter sensor disposed within the return air pathway or proximate to an opening of the return air pathway of the airflow system and configured to collect return airflow data including at least one of a return air temperature or a return air pressure of return air received at the airflow system via the return air pathway; and
one or more processors communicatively coupled to a memory storing one or more instructions that, when executed, cause the one or more processors to:
receive the supply airflow data including the at least one of the supply air temperature or the supply air pressure from the comfort sensor;
receive the return airflow data including the at least one of the return air
temperature or the return air pressure from the filter sensor;
analyze the supply airflow data and the return airflow data to generate one or more cycle variables associated with the airflow system; and
analyze the one or more cycle variables associated with the airflow system using a machine learning model, wherein the analyzing includes:
generating, using the machine learning model, a class prediction metric based on the one or more cycle variables associated with the airflow system, and
classifying, based on the class prediction metric, an airflow system type for the airflow system.
Similar limitations are recited in method claim 11, which mirrors the steps of claim 1 by applying the same abstract idea using a generic computer processor.
Under Step 1 of the analysis, claim 1 belongs to a statutory category, namely it is a system claim. Likewise, claim 11 is a method claim.
Under Step 2A, prong 1: This part of the eligibility analysis evaluates whether the claim recites a judicial exception. As explained in MPEP 2106.04, subsection II, a claim “recites” a judicial exception when the judicial exception is “set forth” or “described” in the claim.
In the instant case, claim 1 is found to recite at least one judicial exception (i.e. abstract idea), that being a Mental Process and a Mathematical Concept. This can be seen in the claim limitations of “analyzing” airflow data, which amounts to evaluating information, “generating” a class prediction metric which requires a mathematical calculation, and “classifying” an airflow system type, which amounts to information based on a calculated prediction metric. The limitations are the judicial exception of a mental process because these limitations are merely data observations, evaluation, and/or judgement in order to evaluate a user performance and is capable of being performed mentally and/or with the aid of pen and paper. Additionally, the aforementioned limitations recite mathematical calculations such these sections in the specifications that recite using formulas such as a mean probability estimator used for determining airflow systems based off data generated.
Similar limitations comprise the abstract ideas of Claim 11.
Step 2A, prong 2 of the eligibility analysis evaluates whether the claim as a whole integrates the recited judicial exception(s) into a practical application of the exception. This evaluation is performed by (a) identifying whether there are any additional elements recited in the claim beyond the judicial exception, and (b) evaluating those additional elements individually and in combination to determine whether the claim as a whole integrates the exception into a practical application.
The claim includes additional elements recited in claim 1 in addition to the abstract ideas that are recited in a high level and used in a conventional manner. The claimed system recited “an airflow system configured to receive air via a return air pathway and supply air via a supply air pathway”, “a comfort sensor disposed within the supply air pathway or proximate to an opening of the supply air pathway of the airflow system and configured to collect supply airflow data including at least one of a supply air temperature or a supply air pressure of supply air supplied from the airflow system via the supply air pathway”, “a filter sensor disposed within the return air pathway or proximate to an opening of the return air pathway of the airflow system and configured to collect return airflow data including at least one of a return air temperature or a return air pressure of return air received at the airflow system via the return air pathway”, “receive the supply airflow data including the at least one of the supply air temperature or the supply air pressure from the comfort sensor”, and “receive the return airflow data including the at least one of the return air temperature or the return air pressure from the filter sensor”. However, these elements are found to be data gathering and output steps, which are recited at a high level of generality, and thus merely amount to “insignificant extra-solution” activity(ies). See MPEP 2106.05(g) “Insignificant Extra-Solution Activity,”. The use of an air pathway that is generic to a HVAC system does not elevate the claim to a practical implementation. Also, the use of a machine learning model to generate and classify information on an airflow system is nothing more than mere instructions to implement the abstract idea on a generic computer. See MPEP 2106.05(f). The claim also does not describe any improvement to the operation of the sensors, processors, or HVAC components themselves, nor do they set forth any specific technological advancement on how the data is collected or analyzed. Instead, the claim simply apply a mathematical model to airflow data collected and used to classify system types, which is equivalent to applying the abstract idea of evaluating and categorizing data on a general purpose computer or can be carried out as a mental process with the aid of pen and paper. See MPEP 2106.05(h): “For instance, a data gathering step that is limited to a particular data source (such as the Internet) or a particular type of data (such as power grid data or XML tags) could be considered to be both insignificant extra-solution activity and a field of use limitation.” The steps of “analyzing airflow data”, “generating a class prediction metric”, and “classifying an airflow system type” are recited in the claim are performed “by one or more processors communicatively coupled to a memory storing one or more instructions that, when executed, cause the one or more processors…” however this is found to be equivalent to adding the words “apply it” and mere instructions to apply a judicial exception on a general-purpose computer does not integrate the abstract idea into a practical application. See MPEP 2106.05(f).
Method claim 11 recites similar additional elements as claim 1, namely the use of a generic general purpose computer processor to carry out the abstract idea. In claim 11, it highlights the use of a processor in each step such as “receiving, by the one or more processors”, and “analyzing, by the one or more processors”.
The generic data gathering, processing, and output steps, are recited at such a high level of generality (e.g. using “sensors and “processors”) that it represents no more than mere instructions to apply the judicial exceptions on a computer. It can also be viewed as nothing more than an attempt to generally link the use of the judicial exceptions to the technological environment of a computer. Noting MPEP 2106.04(d)(I): “It is notable that mere physicality or tangibility of an additional element or elements is not a relevant consideration in Step 2A Prong Two. As the Supreme Court explained in Alice Corp., mere physical or tangible implementation of an exception does not guarantee eligibility. Alice Corp. Pty. Ltd. v. CLS Bank Int’l, 573 U.S. 208, 224, 110 USPQ2d 1976, 1983-84 (2014) ("The fact that a computer ‘necessarily exist[s] in the physical, rather than purely conceptual, realm,’ is beside the point")”.
Thus, under Step 2A, prong 2 of the analysis, 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. No specific practical application is associated with the claimed system. For instance, nothing is done with the results of classifying the airflow system type, such as adjusting or controlling the HVAC equipment, modifying the operation, or improving the HVAC technology within the system, instead the claims merely generate and classify data without applying it in a meaningful way.
Under Step 2B, the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements, as described above with respect to Step 2A Prong 2, merely amount to a general purpose computer system that attempts to apply the abstract idea in a technological environment, limiting the abstract idea to a particular field of use, and/or merely performs insignificant extra-solution activit(ies) (claims 1 and 11). Such insignificant extra-solution activity, e.g. data gathering and output, when re-evaluated under Step 2B is further found to be well-understood, routine, and conventional as evidenced by MPEP 2106.05(d)(II) (describing conventional activities that include transmitting and receiving data over a network, electronic recordkeeping, storing and retrieving information from memory, and electronically scanning or extracting data from a physical document).
Therefore, similarly the combination and arrangement of the above identified additional elements when analyzed under Step 2B also fails to necessitate a conclusion that claim 1, as well as claim 11, amount to significantly more than the abstract idea.
With regards to the dependent claims, claims 4-10 and 14-20, merely further expand upon the algorithm/abstract idea and do not set forth further additional elements that integrate the recited abstract idea into a practical application or amount to significantly more. Therefore, these claims are found ineligible for the reasons described for parent claims 1 and 11. Specifically:
With respect to dependent claims 10, and 20 specifically, the claims further recite collecting airflow data such as temperature, pressure, or ambient sensor data. However, these recitations merely specify the type of data that is being gathered, which amounts to data collection. In addition, the data collection can be performed mentally or with the aid of pen and paper. Therefore, these claims fail to integrate the recited abstract idea into a practical application or amount to significantly more. See MPEP 2106.05(g).
With respect to dependent claims 4-6 and 14-16 specifically, the claims further recite airflow classifications, functionalities, or speed with the HVAC system. However, these limitations simply identify and restricts the abstract idea to certain categories of data but does not improve the function of the airflow system itself. These limitations amount to classification or organization of information, which is also a form of a mental process that can be performed without a computer. See MPEP 2106.05(h): “For instance, a data gathering step that is limited to a particular data source (such as the Internet) or a particular type of data (such as power grid data or XML tags) could be considered to be both insignificant extra-solution activity and a field of use limitation.”
With respect to dependent claims 7-9, and 17-19 specifically, the claims further recite generating class prediction metrics, and training a machine learning model using store preprocessed data. However, these recitations are described broadly without specifically any technical details of the machine learning model or how it will improve the operation of the HVAC system. Instead, they merely amount to a mathematical operation and data manipulation which is also considered an abstract idea. Therefore, these claims fail to integrate the recited abstract idea into a practical application or amount to significantly more. See MPEP 2106.05(f).
Accordingly, for the reasons above and those discussed in relation to the independent claims 1 and 11, and the dependent claims are insufficient to integrate the recited abstract idea into a practical application or amount to significantly more.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-6, 10-16, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over US 20200149764 A1, Sinha et al. (hereinafter Sinha) in view of US 20220018566 A1, Kurganskii et al. (hereinafter Kurganskii).
Regarding Claim 1 and 11, Sinha teaches a system for identifying and classifying airflow system types (Sinha, [0032] an HVAC unit is provided. The HVAC unit may include one or more components to control an ambient condition of an area of a building, a memory configured to store a set of instructions, and a processor coupled with the memory. The processor may be configured to receive sensor information from a wireless sensor located in the area, the sensor information indicating the ambient condition of the area), the system comprising:
an airflow system (Sinha, Fig. 3 (300) airside system) configured to receive air via a return air (Sinha, Fig. 3 (304) return air) pathway and supply air via a supply air (Sinha, Fig. 3 (310) supply air) pathway (Sinha, Fig. 1, [0078] Airside system (130) can deliver the airflow supplied by AHU (106) (i.e., the supply airflow) to building (10) via air supply ducts (112) and can provide return air from building (10) to AHU (106) via air return ducts (114));
a comfort sensor (Sinha, Fig. 3 (362) sensor) disposed within the supply air pathway or proximate to an opening of the supply air pathway of the airflow system and configured to collect supply airflow data including at least one of a supply air temperature or a supply air pressure of supply air supplied from the airflow system via the supply air pathway (Sinha, [0093] AHU controller 330 receives a measurement of the supply air temperature from a temperature sensor 362 positioned in supply air duct 312 (e.g., downstream of cooling coil 334 and/or heating coil 336));
a filter sensor (Sinha, Fig. 3 (364) sensor) disposed within the return air pathway or proximate to an opening of the return air pathway (Sinha, Fig. 3, [0093] AHU controller 330 can also receive a measurement of the temperature of building zone 306 from a temperature sensor 364 located in building zone 306) of the airflow system (Sinha, Fig. 3, [0078] AHU 106 can include various sensors (e.g., temperature sensors, pressure sensors, etc.) configured to measure attributes of the supply airflow. AHU 106 can receive input from sensors located within AHU 106 and/or within the building zone and can adjust the flow rate, temperature, or other attributes of the supply airflow through AHU 106 to achieve set-point conditions for the building zone) and configured to collect return airflow data associated with including at least one of a return air temperature or a return air pressure of return air received at the airflow system via the return air pathway (Sinha, [0078] Airside system 130 can deliver the airflow supplied by AHU 106 (i.e., the supply airflow) to building 10 via air supply ducts 112 and can provide return air from building 10 to AHU 106 via air return ducts 114); and
one or more processors (Sinha, [0163] The processor 1804 may be configured to execute computer code and/or instructions stored in the memory 1806 or received from other computer readable media) communicatively coupled to a memory storing one or more instructions that, when executed, cause the one or more processors (Sinha, [0164] the memory 1806 can include one or more devices (e.g., memory units, memory devices, storage devices, etc.) for storing data and/or computer code for completing and/or facilitating the various processes) to:
receive the supply airflow data including the at least one of the supply air temperature or the supply air pressure from the comfort sensor (Sinha, Fig. 3 (362), [0093] AHU controller 330 receives a measurement of the supply air temperature from a temperature sensor 362 positioned in supply air duct 312 (e.g., downstream of cooling coil 334 and/or heating coil 336). AHU controller 330 can also receive a measurement of the temperature of building zone 306 from a temperature sensor 364 located in building zone 306 [0239] The HVAC system 2900 may also include the sensors 2950 located within one or more rooms of the building 2990 and/or within or near the supply vents 2922. One or more sensors 2950 may be configured to detect an ambient condition such as a temperature or a humidity level of the room where the sensor 2950 is located. Each of the sensors 2950 may provide sensor information 2980 to the HVAC unit 2910. Examples of a sensor 2950 may include a temperature sensor, a humidity sensor, or any sensor configured to detect an ambient condition of one or more rooms of the building 2990);
receive the return airflow data including the at least one of the return air temperature or the return air pressure from the filter sensor (Sinha, Fig. 3 (364), [0093] AHU controller 330 receives a measurement of the supply air temperature from a temperature sensor 362 positioned in supply air duct 312 (e.g., downstream of cooling coil 334 and/or heating coil 336). AHU controller 330 can also receive a measurement of the temperature of building zone 306 from a temperature sensor 364 located in building zone 306, [0132] The removable sensor 1304 can be any kind of environmental sensor configured to sense environmental conditions of an area associated with the headless thermostat 700. The removable sensor 1304 can be a temperature sensor, a humidity sensor, an air quality sensor, and/or any other kind of sensor, [0246] method 3000 may include receiving sensor information from a wireless sensor located in the area, the sensor information indicating the ambient condition of the area. For example, one or more components (e.g., processor 3110, memory 3120, operation control component 2942, monitoring component 2970, or information receiver 2972) of the HVAC unit 2910 may receive the sensor information 2980 from the one or more sensors 2950, the sensor information 2980 may indicate an ambient condition (e.g., current temperature or humidity level of one or more rooms of building 2990) of an area (e.g., one or more rooms of building 2990) corresponding to a location of each sensor 2950);
analyze the supply airflow data and the return airflow data to generate one or more cycle variables associated with the airflow system (Sinha, [0094] may correlate with the amount of energy consumed to achieve a desired supply air temperature. AHU controller 330 can control the temperature of supply air 310 and/or building zone 306 by activating or deactivating coils 334-336, adjusting a speed of fan 338, or a combination of both);
Sinha does not disclose analyze the one or more cycle variables associated with the airflow system using a machine learning model, wherein the analyzing includes:
generating, using the machine learning model, a class prediction metric based on the one or more cycle variables associated with the airflow system, and
classifying, based on the class prediction metric, an airflow system type for the airflow system.
However, Kurganskii teaches analyze the one or more cycle variables associated with the airflow system using a machine learning model, wherein the analyzing (Kurganskii, [0007] The proposed technical solution can be used to generate optimal historical training data consisting of setpoints (equipment control values) and readings of sensors (parameters) as response to setpoints during operation of HVAC equipment. The historical data are used to train machine learning models used to develop HVAC equipment control systems) includes:
generating, using the machine learning model, a class prediction metric based on the one or more cycle variables associated with the airflow system (Kurganskii, [0015] the data to train the heating, ventilation and air conditioning equipment control system are generated using predictive model (Model Predictive Control), where the predictive model implementing machine learning using classifier or decision trees or regression equations is learning on the data from parameters and setpoints database), and
classifying, based on the class prediction metric (Kurganskii, [0015] the data to train the heating, ventilation and air conditioning equipment control system are generated using predictive model (Model Predictive Control), where the predictive model implementing machine learning using classifier or decision trees or regression equations is learning on the data from parameters and setpoints database or is made in the form of system of equations describing operation of each operation unit), an airflow system type for the airflow system (Kurganskii, [0006] The proposed technical solution is aimed to increase the accuracy of controlling HVAC equipment of the building based on machine learning methods and to optimize the control, by, at least, one criterion (e.g., reduction of electric energy consumption, improvement of comfort, reduction of the cost of electric consumption, including selection of the electric energy source at different electric rates), including satisfaction of restrictions, more particularly, indoor microclimate conditions (e.g. temperate range indoors, delivery air pressure, CO2 level, etc.)).
Before the effective filling date of the claimed invention, it would have been
obvious to one of ordinary skill in the art to combine Sinha and Kurganskii’s teaching by incorporating the machine learning analysis techniques of Kurganskii to analyze airflow data collected from sensors of the HVAC system, including supply air temperature or pressure and return air temperature or pressure, in order to classify airflow system types. Sinha discloses sensors configured to measure airflow characteristics within supply and return air pathways, while Kurganskii teaches applying machine learning techniques to analyze system data to predictive and classification purposes. It would have been obvious to apply Kurganskii’s machine learning techniques to the airflow data collected by Sinha’s sensors to classify airflow system types based on operating conditions. A person of ordinary skill in the art would have been motivated to combine these references because both Sinha and Kurganskii are directed to HVAC systems that utilize sensor data and data processing to improve system performance. Integrating Kurganskii’s machine learning techniques with Sinha’s system would have predictably enhanced the ability to classify airflow system types and improve system control and efficiency.
Regarding Claim 4 and 14, Sinha in view of Kurganskii teaches the system of claim 1.
Sinha teaches wherein the one or more cycle variables include at least one of: (i) an air conditioning cycle type, (ii) a heating cycle type (Sinha, Fig. 29, [0241] the controller 2940 may include logic to operate the A/C unit 2912, the furnace 2914, the blower 2916, and the humidifier/dehumidifier 2918, based on the sensor information 2980 and the setpoint information 2964), (iii) a cycle run time, or (iv) an airflow system (Sinha, Fig. 1 (100) HVAC system) heating performance (Sinha, Fig. 29, [0241] the operation of the components of the HVAC unit (2910) may include one or more of an initiation time, a stop time, a run time, a power state, speed level, a heating/cooling level, and/or any other operational state of one or more of these components of the HVAC unit (2910)).
Regarding Claim 5 and 15, Sinha in view of Kurganskii teaches the system of claim 1.
Sinha teaches wherein the airflow system (Sinha, Fig. 1 (100) HVAC system) type is associated with at least an airflow system (Sinha, Fig. 1 (100) HVAC system) functionality, and the airflow system (Sinha, Fig. 1 (100) HVAC system) functionality includes at least one of (i) air conditioner functionality or (ii) heat pump functionality (Sinha, [0232] the sensor may be configured to communicate with an HVAC unit, which is located exterior (e.g., A/C unit, heat pump) or interior (e.g., furnace, air handler) to a building, current ambient condition information (e.g., indoor temperature or humidity)).
Regarding Claim 6 and 16, Sinha in view of Kurganskii teaches the system of claim 1.
Sinha teaches wherein the airflow system (Sinha, Fig. 1 (100) HVAC system) type is associated with at least an airflow system (Sinha, Fig. 1 (100) HVAC system) speed, and the airflow system (Sinha, Fig. 1 (100) HVAC system) speed includes at least one of (i) dual speed, (ii) constant speed, or (iii) variable speed (Sinha, Fig. 6, [0107] the compressor 612 may be driven by the variable speed drive 608 and the motor 610. For example, the outdoor unit controller 606 can generate control signals for the variable speed drive 608. The variable speed drive 608 (e.g., an inverter, a variable frequency drive, etc.) may be an AC-AC inverter, a DC-AC inverter, and/or any other type of inverter).
Regarding Claim 10 and 20, Sinha in view of Kurganskii teaches the system of claim 1.
Sinha teaches wherein the memory further stores instructions that, when executed, cause the one or more processors (Sinha, [0163] The processor 1804 may be configured to execute computer code and/or instructions stored in the memory 1806 or received from other computer readable media) to:
receive ambient airflow data from a water sensor (Sinha, [0132] sensor 1304 can be a temperature sensor, a humidity sensor, an air quality sensor, and/or any other kind of sensor) disposed proximate to the airflow system (Sinha, Fig. 1 (100) HVAC system);
wherein analyzing the supply airflow data and the return airflow data to generate the one or more cycle variables associated with the airflow system includes (Sinha, Fig. 1, [0078] Airside system (130) can deliver the airflow supplied by AHU (106) (i.e., the supply airflow) to building (10) via air supply ducts (112) and can provide return air from building (10) to AHU (106) via air return ducts (114)):
analyzing the supply airflow data, the return airflow data, and the ambient airflow data (Sinha, Fig. 1, [0078] AHU (106) can include various sensors (e.g., temperature sensors, pressure sensors, etc.) configured to measure attributes of the supply airflow. AHU (106) can receive input from sensors located within AHU (106) and/or within the building zone and can adjust the flow rate, temperature, or other attributes of the supply airflow through AHU (106) to achieve set-point conditions for the building zone) to generate the one or more cycle variables (Sinha, [0155] The headless thermostat (700) can utilize a sensed temperature, sensed by the headless thermostat (700) or by another sensor, e.g., sensor data received wirelessly from the remote sensors (1714), and generate a control decision for the HVAC unit (1712). The decision may be to turn on one or multiple heating or cooling stages, turn on or off a fan, etc. The adapter unit (1702) can be configured to receive the commands and operate the HVAC unit (1712)).
Claims 7-9, and 17-19 are rejected under 35 U.S.C. 103 as being unpatentable over US 20200149764 A1, Sinha et al. (hereinafter Sinha) in view of US 20220018566 A1, Kurganskii et al. (hereinafter Kurganskii), in further view of US 20190020670 A1, Brabec et al. (hereinafter Brabec).
Regarding Claim 7 and 17, Sinha in view of Kurganskii teaches the system of claim 1 and 11.
Sinha does not disclose wherein generating the class prediction metric includes:
receiving, at the machine learning model, the one or more cycle variables as one or more inputs;
calculating, by one or more trees of the machine learning model, a mean probability estimate for each airflow system type class; and
determining the class prediction metric based on a highest mean probability estimate.
However, Kurganskii teaches wherein generating the class prediction metric includes:
Receiving (Kurganskii, [0016] receiving of current equipment parameters, generation of set of setpoint versions in the preset neighborhood of setpoint values forming the setpoints combinations grid to further predictively check the optimality), at the machine learning model, the one or more cycle variables as one or more inputs (Kurganskii, [0117] the data to train the heating, ventilation and air conditioning control system are generated using the control method with predictive model (Model Predictive Control), where the predictive model implementing machine learning);
Before the effective filling date of the claimed invention, it would have been
obvious to one of ordinary skill in the art to combine Sinha and Kurganskii’s teaching because both references are directed to predictive models using machine learning. Sinha provides the overall framework for generating prediction metrics, while Kurganskii teaches receiving system parameters and generating predictive setpoint combinations. One of ordinary skill in the art would put these together to improve functionality and performance of Sinha’s system.
Brabec however teaches calculating (Brabec, Fig. 6, [0054-0071] computing performed, [0054] In one aspect of the techniques herein, the conditional probability may be computed of the true label y given the predictions of the individual decision trees 404) by one or more trees (Brabec, Fig. 6, [0075] step 610, where, as described in greater detail above, the computing device may provide a feature vector as input to a random decision forest. In various embodiments, the decision forest may comprise a plurality of decision trees trained using a training dataset. Each decision tree in the forest may generally be configured to output a classification label prediction for the input feature vector) of the machine learning model, a mean probability estimate (Brabec, Fig. 6, [0077] the predictions from the different decision trees can be weighted according to their estimated posterior prediction probabilities determined from their OOB datasets) for each airflow system type class (Brabec, [0025] the evolution of the Internet is the ability to connect more than just computers and communications devices, but rather the ability to connect “objects” in general, such as lights, appliances, vehicles, heating, ventilating, and air-conditioning (HVAC))
determining the class prediction metric (Brabec, [0077] at step 620, the computing device may generate weightings for the classification label predictions from the decision trees based on the determined conditional probabilities, as described in greater detail above. In particular, rather than employing an equal weighting, such as in the case of majority voting, the predictions from the different decision trees can be weighted according to their estimated posterior prediction probabilities determined from their OOB datasets) based on a highest mean probability estimate (Brabec, an example calculation using decision trees [0063-0066], [0066] applying the estimated probabilities P(1|1), P(1|2), P(1|3) to Equation 5, it can be seen that the class with the highest weight is the class number 3).
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art to combine Sinha in view of Kurganskii and Brabec’s teaching because Brabec discloses calculating a mean probability estimate and determining a prediction based off the highest mean probability estimate using decision trees. Incorporating Brabec’s method into the combined system of Sinha and Kurganskii would have been an obvious design to further refine the prediction metrics, and improving the classification accuracy and system performance.
Regarding Claim 8 and 18, Sinha in view of Kurganskii teaches the system of claim 1 and 11.
Sinha does not disclose wherein the memory further stores instructions that, when executed, cause the one or more processors to:
train the machine learning model using stored airflow data associated with one or more airflow system types, wherein the training includes:
receiving, at the machine learning model, the stored airflow data as one or more inputs;
calculating, by one or more trees of the machine learning model, a mean probability estimate for each airflow system type class;
determining the class prediction metric based on a highest mean probability estimate for the stored airflow data; and
validating the class prediction metric.
However, Kurganskii teaches wherein the memory further stores instructions that, when executed, cause the one or more processors to:
train the machine learning model using stored airflow data associated with one or more airflow system types, wherein the training includes (Kurganskii, Fig. 1, [0040] metrics of computing (evaluating) accuracy of controlling HVAC equipment control system (101) is selected. In different embodiments the metrics can be defined as integral time of violation of control restrictions (such as temperature and CO level in the room, flow rate, air pressure) or as mean time of violations of control restrictions per hour/day/week, or any similar method, each metrics, as a rule, depends, at this, at least, on the building (and its parameters, equipment, etc.)):
receiving (Kurganskii, [0007] The proposed technical solution can be used to generate optimal historical training data consisting of setpoints (equipment control values) and readings of sensors (parameters) as response to setpoints during operation of HVAC equipment), at the machine learning model, the stored airflow data as one or more inputs (Kurganskii, [0007] the historical data are used to train machine learning models used to develop HVAC equipment control systems);
Before the effective filling date of the claimed invention, it would have been
obvious to one of ordinary skill in the art to combine Sinha and Kurganskii’s teaching because Sinha discloses a system for predicting airflow system but does not address training a model and validating the prediction results. Kurganskii teaches training the machine learning model using stored airflow data and historical airflow data. One of ordinary skill in the art would have recognized that incorporating Kurganskii’s training into Sinha’s predictive system would enhance the HVAC system.
Brabec however teaches calculating (Brabec, Fig. 6, [0054-0071] computing performed, [0054] In one aspect of the techniques herein, the conditional probability may be computed of the true label y given the predictions of the individual decision trees 404), by one or more trees (Brabec, Fig. 6, [0075] step 610, where, as described in greater detail above, the computing device may provide a feature vector as input to a random decision forest. In various embodiments, the decision forest may comprise a plurality of decision trees trained using a training dataset. Each decision tree in the forest may generally be configured to output a classification label prediction for the input feature vector) of the machine learning model, a mean probability estimate (Brabec, Fig. 6, [0077] the predictions from the different decision trees can be weighted according to their estimated posterior prediction probabilities determined from their OOB datasets) for each airflow system type class (Brabec, [0025] the evolution of the Internet is the ability to connect more than just computers and communications devices, but rather the ability to connect “objects” in general, such as lights, appliances, vehicles, heating, ventilating, and air-conditioning (HVAC));
determining the class prediction metric (Brabec, [0077] at step 620, the computing device may generate weightings for the classification label predictions from the decision trees based on the determined conditional probabilities, as described in greater detail above. In particular, rather than employing an equal weighting, such as in the case of majority voting, the predictions from the different decision trees can be weighted according to their estimated posterior prediction probabilities determined from their OOB datasets) based on a highest mean probability estimate (Brabec, an example calculation using decision trees [0063-0066], [0066] applying the estimated probabilities P(1|1), P(1|2), P(1|3) to Equation 5, it can be seen that the class with the highest weight is the class number 3).
for the stored (Brabec, [0030] It will be apparent to those skilled in the art that other processor and memory types, including various computer-readable media, may be used to store and execute program instructions pertaining to the techniques described herein) airflow data (Brabec, [0025] the evolution of the Internet is the ability to connect more than just computers and communications devices, but rather the ability to connect “objects” in general, such as lights, appliances, vehicles, heating, ventilating, and air-conditioning (HVAC)) and
validating the class prediction metric (Brabec, Fig. 6, [0078] At step 625, as detailed above, the computing device may apply a final classification label to the feature vector based on the weightings for the classification label predictions from the decision trees).
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art to combine Sinha in view of Kurganskii and Brabec’s teaching because while Sinha and Kurganskii disclose training a model using airflow system data and evaluating its performance, but they do not disclose determining a prediction based off the mean probability estimate calculations and verifying the prediction. Brabec teaches the use of machine learning models to process, predict, and classify systems. One of ordinary skill in the art would have been motivated to apply Brabec’s teaching to combine with Sinha and Kurganskii’s system to improve reliability and robustness of the predictions made within the system.
Regarding Claim 9 and 19, Sinha in view of Kurganskii in further view of Brabec teaches the system of claim 8 and 18.
Sinha does not disclose wherein the memory further stores instructions that, when executed, cause the one or more processors to:
preprocess the stored airflow data prior to training the machine learning model, wherein the preprocessing includes:
identifying a subset of stored airflow data, wherein the subset includes one or more predetermined cycle variables associated with the stored airflow data; and
resample the subset of stored airflow data.
However, Kurganskii teaches wherein the memory further stores instructions that, when executed, cause the one or more processors to:
preprocess the stored airflow data prior to training the machine learning model (Kurganskii, [0031] The input data 131, in particular, available historical data on parameters (particularly, the sensor readings) and setpoints (particularly, the control values) of HVAC equipment 121 prior to putting into operation of the HVAC equipment control system 101), wherein the preprocessing includes (Kurganskii, [0108] At step 717 data of equipment parameters and setpoints are received from the building management system and stored in the database of equipment parameters and setpoints, which also stores sets of data from the data generation controller generating optimal training data for the HVAC control system after their generation):
identifying a subset of stored airflow data, wherein the subset includes one or more predetermined cycle variables associated with the stored airflow data (Kurganskii, Fig. 1, [0031] the input data (131), in particular, available historical data on parameters (particularly, the sensor readings) and setpoints (particularly, the control values) of HVAC equipment (121) ... The mentioned sensors may be sensors of temperature, air flow, water flow, humidity, CO2. In a particular case, a part of sensors monitors correct operation of equipment, the other part—observation of microclimate conditions indoors); and
resample the subset of stored airflow data (Kurganskii, [0059] to generate optimal historical training data tables of PS historical data are set by the number of lines (an example of a table is described below, including sixty readings of temperature sensors, fifty-six readings of pressure sensors, and so on).
Before the effective filling date of the claimed invention, it would have been
obvious to one of ordinary skill in the art to combine Sinha and Kurganskii’s teaching to preprocess stored airflow data from Sinha’s HVAC system before training Kurganskii’s machine learning model by identifying data and resampling that data as needed. This will allow Kurganskii’s machine learning model to have certain variables continuously identifying new information for data from Sinha’s system to help make accurate predictions. Since both references relate to HVAC systems that utilize airflow-related data, it would have been obvious to one of ordinary skill in the art to use the data from Sinha’s HVAC system as inputs to the Kurganskii’s machine learning model to identify airflow systems but before they are used as inputs they are identified as subsets from the stored airflow data in Sinha and resampled as needed.
Response to Arguments
35 USC§ 101
Applicant’s arguments with respect to claims 1-20 of the 35 USC§ 101 rejection have been fully considered but are not persuasive. Applicant contends that the amended claims improve HVAC system classification through the use of specific sensors and a machine learning model. However, the claims recite receiving airflow data, analyzing the data to generate cycle variables, and using a machine learning model to generate a class prediction metric and classify an airflow system type, which constitute an abstract idea in the form of mental processes and mathematical concepts. The additional elements, including the recited comfort sensor, filter sensor, processor, and memory, merely perform data gathering and generic computer functions and do not integrate the abstract idea into a practical application. The sensors are broadly recited and only collect conventional data such as temperature or pressure, which amounts to insignificant extra solution activity. Furthermore, the claims do not recite any specific improvement to the functioning of the HVAC system or the machine learning model, but instead apply the abstract idea to a particular field of use. Accordingly, the claims do not amount to significantly more than the abstract idea, and the rejection under 35 USC§ 101 is maintained.
35 USC§ 103
Applicant’s arguments with respect to claims 1-20 under 35 USC§ 103 have been fully considered but are not persuasive and/or are moot in view of the findings set forth above. Applicant contends that Sinha does not disclose a filter sensor disposed within or proximate to a return air pathway and that Kurganskii does not teach classifying an airflow system type. However, Sinha teaches sensors configured to measure airflow-related parameters such as temperature and pressure within an HVAC system, including sensors located within airflow pathways and system components, which reasonably correspond to the claimed sensor placement. The exact positioning of the sensor within or proximate to an opening of the return air pathway is considered an obvious matter of design choice. Further, Kurganskii teaches the use of machine learning models, including classifiers, to analyze system data and generate predictive outputs. Such teachings reasonably suggest generating a class prediction metric and classifying system operation. Accordingly, the rejection under 35 USC§ 103 is maintained.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to IBRAHIM NAGI SHOHATEE whose telephone number is (571)272-6612. The examiner can normally be reached 8am-5pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Shelby Turner can be reached at (571) 272-6334. 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.
/IBRAHIM NAGI SHOHATEE/Examiner, Art Unit 2857
/SHELBY A TURNER/Supervisory Patent Examiner, Art Unit 2857
Prosecution Insights