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 .
Response to Arguments
In response to applicant's argument that the machine learning algorithm of Pourmohammad cannot be included with the RTU computer of Majewski, the test for obviousness is not whether the features of a secondary reference may be bodily incorporated into the structure of the primary reference; nor is it that the claimed invention must be expressly suggested in any one or all of the references. Rather, the test is what the combined teachings of the references would have suggested to those of ordinary skill in the art. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981). Whether a machine learning algorithm is separate or integral to the computer, an expected and predictable result is realized by supplying RTU data to the machine learning model for predicting RTU performance. The machine learning model algorithm of Pourmohammad is separable from the physical building components and which relocation or integration within a remote computer does not change the functionality of the algorithm for providing predictions based on received input. Pourmohammad does not limit the machine learning algorithm to the specific building or execution on a specific computer.
In response to applicant's argument that the examiner's conclusion of obviousness is based upon improper hindsight reasoning, it must be recognized that any judgment on obviousness is in a sense necessarily a reconstruction based upon hindsight reasoning. But so long as it takes into account only knowledge which was within the level of ordinary skill at the time the claimed invention was made, and does not include knowledge gleaned only from the applicant's disclosure, such a reconstruction is proper. See In re McLaughlin, 443 F.2d 1392, 170 USPQ 209 (CCPA 1971).
As per claim 2, the Examiner submits the external data source represents at least a vibration sensor while the data received by the circuitry from the air conditioner components is the computer receiving the data logger data comprising data from the air conditioner components such as the components power consumption, infra claim 2.
As per claim 11, Applicant argues the “analysis functions are not modifications of a native control logic.” The Examiner disagrees because the application of the remote-control program updates results in a modification of the native control program of Majewski via additional fault detection logic.
As per claim 24, Applicant argues the rationale provided does not address the additional limitation that the expression-based event processing logic and the machine learning algorithm are also both function during interruptions of the communications with the cloud system. As interpreted, the functions of the FDD and machine learning algorithm continue to operate despite the loss of communication because the claim does not limit the function of each to the continuous communication with a cloud server. As such, the application of Guss teaches “maintaining a minimal level of control” during communication loss, which minimal level of control when applied to the expressional based and machine learning model results in a continued operation of the computer executing these functions during communication loss with a rationale of maintaining minimal control during communication loss with a benefit of fault detection.
As per claim 39, the Examiner submits the FDD algorithm provided a diagnosis of an ongoing fault based on both the vibration and data logger data while inclusion of the machine learning algorithm predicts a future fault condition, see Pourmohammad, see machine learning algorithms applied to predict equipment performance, the performance corresponding to “abnormal” operation, 0002, 0121-0122, 0124. The application of these teachings to the RTU results in an expected and predictable result of predicting RTU abnormal operation.
Claim Objections
Claim 9 is objected to for insufficient antecedent basis for “the common data bus” in reference to a common data base.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1-2, 5, 15-16, 19, 25, 36, and 38-40 are rejected under 35 U.S.C. 103 as being unpatentable over Majewski et al. (PG/PUB 20140172400) in view over Poumohammad et al. (PG/PUB 20200380387).
Claim 1.
Majewski teaches a rooftop unit (Figure 2-11, Figure 5) but does not expressly teach the machine learning algorithm limitations described below. Poumohammad et al. teaches the machine learning algorithm limitations described below, comprising:
a housing (Figure 2-11, 0059)
air conditioning components coupled to the housing (Figure 2-11, 0059); and
circuitry enclosed within and/or coupled to the housing and programmed to execute a control logic for the air conditioning components (Figure 2-26, 0020, 0059, 0076-82 e.g. see computer coupled to rooftop unit), an expression-based event processing logic (0028, 0034, 0045, 0059, Figure 6, Figure 6 e.g. see fault identification algorithms and native control logic for processing) , and a machine learning algorithm (Poumohammad et al , Figure 6-646, 0088, 0092* (e.g. see embedded algorithm, 0118, 0126, Figure 7 e.g. “The machine learning model 646 can include one or more algorithms (e.g., supervised learning, unsupervised learning, reinforcement learning, etc.) to learn.”)
One of ordinary skill in the art before the effective filing date of the claimed invention applying the teachings of Poumohammad et al, namely providing machine learning models (e.g. including learning algorithms) to a computing device for fault prediction, to the teachings of Majewski , namely performing fault detection and analysis via a computer coupled to the rooftop unit, would achieve an expected and predictable result via combining said elements using known methods. One of ordinary skill in the art adapting the rooftop unit computer to integrate the computing device components, including the machine learning models comprising learning algorithms of Poumohammad et al., would achieve an expected and predictable result of proactively scheduling maintenance based on predicting anomalies and/or faults as well providing model updates for fault remediation. Poumohammad et al. is in the same field of endeavor and reasonably pertinent to a problem of predicting air conditioner faults, see summary of Invention.
Claim 2.
The rooftop unit of claim 1, wherein the expression-based event processing logic performs pattern recognition for data received by the circuitry ( 0076-77, RTU computer, the RTU comprising algorithms for fault detection based on receiving data logger-49 time series data ) from the air conditioning components (see data logger regarding at least energy consumed by the components) AND one and more external data sources (0039 e.g. see sensors such as vibration sensors attached to RTU, infra claim 8 for additional external sources) (Majewski et al., 0027, 0039 0044, 0059, 0076-77 0083, Figure 6 e.g. see identifying vibration patterns for potential faults via the algorithms based on received time series data, see RTU computer having FDD algorithm configured to receive data logger/external data in addition to vibration sensor data by the circuitry)
Claim 5.
The rooftop unit of claim 1, wherein the expression-based event processing logic diagnoses occurring fault conditions and the machine learning algorithm predicts future fault conditions ((Majewski et al. 0034, 0053, 0081, supra claim 1 for inclusion of machine learning algorithms for use by the predictive learning models for fault prediction in addition to the fault detection functions of Majewski)
Claim 15.
(Majewski et al., as modified, teaches a unit of building equipment comprising:
a mechanical component controllable to affect a condition of a building; and
circuitry packaged with the mechanical component and programmed to execute a control logic for the heating, ventilation, or cooling component, an expression-based event processing logic, and a machine learning algorithm, supra claim 1
Claim 19.
The unit of building equipment of claim 15, wherein the expression-based event processing logic diagnoses occurring fault conditions and the machine learning algorithm predicts future fault conditions, supra claim 5
claim 25.
The unit of building equipment of claim 15, wherein the control logic for the heating, ventilation, or cooling component is a native control logic, and wherein the expression-based event processing logic comprises a modification of the native control logic, supra claim 11
Claim 36.
Majewski et al. teaches a method comprising:
providing a package comprising a heating, ventilation, or cooling component and onboard circuitry; supra claim 1
executing, by the onboard circuitry, control logic to control the heating, ventilation, or cooling component; supra claim 1
executing, by the onboard circuitry, an expression-based event processing logic; supra claim 1and
executing, by the onboard circuitry, a machine learning algorithm, supra claim 1
Claim 38.
The method of claim 36, wherein executing the expression-based event processing logic provides recognition of patterns in data received at the onboard circuitry from the heating, ventilation, or cooling component or another data source, supra claim 2
Claim 39.
The method of claim 36, wherein executing the expression-based event processing logic diagnoses an occurring fault condition and wherein executing the machine learning algorithm predicts a future fault condition, supra claim 5
Claim 40.
The method of claim 36, further comprising receiving, at the onboard circuitry and from a cloud system, a set of expressions and a machine learning model;
wherein executing the expression-based event processing logic comprises using the set of expressions and executing the machine learning model comprises using the machine learning model, supra claim 1
Claims 3, 8, 17, and 22-23 are rejected under 35 U.S.C. 103 as being unpatentable over Majewski et al. (PG/PUB 20140172400) in view over Poumohammad et al. (PG/PUB 20200380387) in view over Darrah et al. (PG/PUB 20220414526).
Claim 3.
(Majewski et al. teaches the rooftop unit of claim 1 but does not expressly teach the model trained at the cloud system. Darrah teaches a model trained at the cloud system described below,
wherein the machine learning algorithm is based on a machine learning model trained at a cloud system remote from the rooftop unit (Darrah, ABSTRACT, Figure 3A, Figure 3B, 0008, 0077-81, Figure 2C. see also the cloud server and Figure 7, supra claim 1, for training machine learning models although the training location is not expressly taught (local or remote is not definitely explained)
One of ordinary skill in the art before the effective filing date of the claimed invention applying the teachings of Darrah, namely training a machine learning model at a cloud server, to the teachings of Poumohammad et al as modified, namely providing machine learning models from a cloud server to a local computer adapted to perform fault detection and prediction for a rooftop unit, would achieve an expected and predictable result via combining said elements using known methods. One of ordinary skill in the art would be motivated to remotely training a fault prediction learning model to offload local computing resources while providing a combined benefit of deploying updated machine learning models to fault analysis. Darrah is reasonably pertinent to fault prediction.
Claim 8.
The rooftop unit of claim but does not expressly teach the first and second data sets used by the machine learning algorithm. Darrah teaches a second data sets while Majewski teaches the first data set and a second data set used by the machine learning algorithm described below,
wherein the circuitry receives a first data set from the air conditioning components (supra claim 1 for data logger providing sensor data/consumption to RTU computer) and a second data set from an external sensor (see Darrah for external sensor such as air quality, supra claim 1 for additional data set), wherein the machine learning algorithm (e.g. applying data sets for learning) uses the first data set and the second data set as inputs (Darrah, Figure 3A, see Co2 as a second data set and additional data as first sets and see the sensor data set of Majewski as first set, as modified, supra claim 1, 0039-40, Figure 7 see also the component datasets of Majewski, Figure 4-49, 46, see also Poumohammad et al. for data sets received by circuitry, 0003-0004, claim 16, Figure 6 -670
One of ordinary skill in the art before the effective filing date of the claimed invention applying the teachings of Darrah, namely training a machine learning model at a cloud server based in part on data sets, to the teachings of Majewski, as modified, namely providing component level data sets as and other training data sets, would achieve an expected and predictable result of using first and second data sets for fault prediction by training the machine learning model by employing the learning algorithm. One of ordinary skill in the art adapting the inputs of the learning model to comprise the vibration sensor data, data logger 49 data, and air quality data would achieve an expected and predictable result of identifying faults based on first and second data seconds to account for internal and external HVAC conditions. The internal corresponds to the power consumption and external corresponding to at least temperature, air quality, etc.
Claim 17.
The unit of building equipment of claim 15, wherein the machine learning algorithm is based on a machine learning model trained at a cloud system remote from the unit of building equipment, supra claim 3
Claim 22.
The unit of building equipment of claim 15, wherein the circuitry receives a first data set from the mechanical component and a second data set from an external sensor, wherein the machine learning algorithm uses the first data set and the second data set as inputs, supra claim 8
Claim 23.
The unit of building equipment of claim 22, wherein the external sensor is an indoor air quality sensor, supra claim 9
Claims 4 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Majewski et al. (PG/PUB 20140172400) in view over Poumohammad et al. (PG/PUB 20200380387) in view over Darrah et al. (PG/PUB 20220414526) in view over Ningho et al. (PG/PUB 20230103149)
Claim 4.
The rooftop unit of claim 3 but does not expressly teach the modified version limitations described below. Ningbo teaches the modified version limitations described below
wherein the machine learning algorithm comprises a modified version of the machine learning model trained at the cloud system that is configured to execute on more limited processing resources of the circuitry relative to the cloud system (Ningbo, 0015 e.g. see model adaptation/compression based on limited computing/edge device capabilities)
One of ordinary skill in the art before the effective filing date of the claimed invention applying the teachings of Ningbo, namely adapting a model based on computing limitations, to the teachings of Majewski et as modified , namely uploading machine learning models (e.g. including learning algorithms) for fault prediction to a rooftop computer, would achieve an expected and predictable result via combining said elements using known methods for a purpose of providing a modified version of the learning algorithm by virtue of providing a simplified/compressed model in light of limited capabilities. The adaption of the learning algorithm within the machine learning model with the compression function of Ningbo accounts for limited computing capabilities and is reasonably pertinent to a problem of model deployment.
Claim 18.
The unit of building equipment of claim 17, wherein the machine learning algorithm comprises a modified version of the machine learning model trained at the cloud system that is configured to execute on more limited processing resources of the circuitry relative to the cloud system, supra claim 4
Claims 6, 11-13, 20 and 26-27 are rejected under 35 USC 103 as being unpatentable over Majewski et al. (PG/PUB 20140172400) in view over Poumohammad et al. (PG/PUB 20200380387) in view over Kawai (PG/PUB 20220113048)
Claim 6.
The rooftop unit of claim 1 but does not expressly teach the remote updates limitation described below. Kawai teaches the remote update limitation described below
wherein the circuitry is programmed to modify the expression-based event processing logic in response to remote updates received at the circuitry (ABSTRACT e.g. see adapter for performing model updates and control program updates, supra claim 1 for control programs/expression)
One of ordinary skill in the art before the effective filing date of the claimed invention applying the teachings of Kawai, namely implementing an adapter for performing model and program updates, to the teachings of Majewski et as modified , namely uploading machine learning models for fault prediction to a rooftop computer as well as providing fault detection algorithms/programs, would achieve an expected and predictable result via combining said elements using known methods for remotely updating control programs/expression logic for an air conditioning system. Kawai is in the same field of endeavor and would commend itself to improving remote updates as described, 0010.
Claim 11.
The rooftop unit of claim 1 but does not teach the modification described below. Kawai teaches the modification described below. wherein the control logic for the air conditioning components is a native control logic (Majewski, see computer functions, 0076-82 for localized/native processing), and wherein the expression-based event processing logic comprises a modification of the native control logic (see expression logic as fault detection, 0034-35, 0076-82, supra claim 1 e.g. see additional or modified functions such as data logging and additional analysis functions, see Kawai, ABSTRACT e.g. see adapter for performing model/program updates, supra claim 1 for control programs/expression)
One of ordinary skill in the art before the effective filing date of the claimed invention applying the teachings of Kawai, namely implementing an adapter for performing model and program updates, to the teachings of Majewski et as modified , namely uploading machine learning models for fault prediction to a rooftop computer as well as providing fault detection algorithms/programs, would achieve an expected and predictable result via combining said elements using known methods for remotely updating control programs for an air conditioning system. Kawai is in the same field of endeavor and would commend itself to improving remote updates as described, 0010.
Claim 12.
The rooftop unit of claim 11 but does not expressly teach the modification limitations described below. Kawai teaches the modification limitations described below,
wherein the modification of the native control logic is received from a cloud system or another computing system external from the rooftop unit via a network connection (ABSTRACT e.g. see adapter for performing model/program updates, supra claim 1 for control programs/expression)
One of ordinary skill in the art before the effective filing date of the claimed invention applying the teachings of Kawai, namely implementing an adapter for performing model and program updates, to the teachings of Majewski et as modified , namely uploading machine learning models for fault prediction to a rooftop computer as well as providing fault detection algorithms/programs, would achieve an expected and predictable result via combining said elements using known methods for remotely updating control programs for an air conditioning system. Kawai is in the same field of endeavor and would commend itself to improving remote updates as described, 0010.
Claim 13.
The rooftop unit of Claim 12, wherein the modification of the native control logic is received after installation of the rooftop unit while the rooftop unit is connected to the network connection and operational, supra claim 12 for updating an installed air conditioning system, supra claim 1 for the installed rooftop system in communication with the cloud server)
Claim 20.
The unit of building equipment of claim 15, wherein the circuitry is programmed to modify the expression-based event processing logic in response to remote updates received at the circuitry, supra claim 6
Claim 26.
The unit of building equipment of claim 25, wherein the modification of the native control logic is received from a cloud system or another computing system external from the unit via a network connection, supra claim 12
Claim 27. The unit of building equipment of claim 26, wherein the modification of the native control logic is received after installation of the unit while the unit is connected to the network connection and operational, supra claim 13
Claims 7 and 21 are rejected under 35 USC 103 as being unpatentable over Majewski et al. (PG/PUB 20140172400) in view over Poumohammad et al. (PG/PUB 20200380387) in view over Gray (PG/PUB 20210294624).
Claim 7.
The rooftop unit of claim 1 but does not expressly teach the memory footprint described below. Gray teaches the memory footprint described below
wherein the expression-based event processing logic and the machine learning algorithm have a combined memory footprint of less than 256 MB (Gray, 0017, 0035, 0054)
One of ordinary skill in the art before the effective filing date of the claimed invention applying the teachings of Gray, namely providing a memory footprint of less than 256, to the teachings of Majewski et al., namely providing a memory store and/or application memory, would achieve an expected and predictable result via combining said elements using known methods in light of the finite and quantifiable memory sizes. Gray pertains to allocating memory for embedded firmware applications and would commend itself to the embedded application programs of Majewski et al for minimizing memory footprints.
Claim 21.
The unit of building equipment of claim 15, wherein the expression-based event processing logic and the machine learning algorithm have a combined memory footprint of less than 256 MB, supra claim 7
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Majewski et al. (PG/PUB 20140172400) in view over Poumohammad et al. (PG/PUB 20200380387) in view over Darrah et al. (PG/PUB 20220414526) in view over Zeller (PG/PUB 20030037170)
Claim 9.
The rooftop unit of claim 8 but does not teach the common data bus described below. Zeller teaches the common data bus described below
wherein the circuitry provides a common data base and common data bus such that the control logic, the expression based event processing, and the machine learning algorithm read data from the common data bus, infra claim 16 analysis and mapping for equivalent mapping and rationale to modify.
Claim(s) 16 is rejected under 35 U.S.C. 103 as being unpatentable over Majewski et al. (PG/PUB 20140172400) in view over Poumohammad et al. (PG/PUB 20200380387) in view over Zeller et al. (PG/PUB 20030037170)
Claim 16.
The unit of building equipment of claim 15 but does not teach the common data bus limitations described below. Zeller teaches the common data bus limitations described below,
wherein the circuitry provides a common data bus (Majewski, see computer coupled to a first data source or a communication medium, 0076-77, 0058, see common data bus of Zeller, 0017, ABSTRACT, Figure 5, Figure 7-22 e.g. see shared data bus)
the expression-based event processing logic performs pattern recognition on data read from the common data bus (Majewski, see FDD algorithm within computer accessing data logger/first data source over a communication medium, Figure 6-46 -> 49, see Zeller for a shared data bus, Figure 7-22)
the control logic adjust operation of the heating, ventilation or cooling component based on data read from the common data bus (Majewski et al., Figure 5 -26-> sensors ->control signals over a communication medium accessing a second data source/sensors, see Zeller for a shared data bus, Figure 7-22)
the machine learning algorithm uses, as inputs, data from the common data bus (Majewski et al. supra claim 1, see computer comprising a machine learning algorithm accessing data sets over a communication medium, see Zeller for providing a shared data bus for multiple data sources, Figure 7-22)
One of ordinary skill in the art before the effective filing date of the claimed invention providing a shared data bus in place of the separate communication mediums for the RTU controller accessing and controlling the RTU based on feedback data; the RTU controller accessing the data logger for providing FDD analysis over a communication medium, and the machine learning algorithm with the controller accessing its data sets for prediction via a communication medium, to the teachings of Zeller, namely providing a shared/common data bus between multiple data sources, would achieve an expected and predictable result of using a shared data bus for the RTU controller of Majewski et al.. Zeller is reasonably pertinent to a problem of building equipment communication while providing a benefit of reducing cable harnessing and expenses, as described, 0007-0008, 0013.
Claims 10 and 24 are rejected under 35 USC 103 as being unpatentable over Majewski et al. (PG/PUB 20140172400) in view over Poumohammad et al. (PG/PUB 20200380387) in view over Gust (PG/PUB 20130310986)
Claim 10.
The rooftop unit of claim 1 but does not expressly teach the interruptions described below. Gust teaches the interruptions described below,
wherein:
the circuitry is configured to established communications with a cloud system (supra claim 1, see Gust, Figure 1); and
the control logic for the air conditioning components, the expression-based event processing logic, and the machine learning algorithm are functional during interruptions of the communications with the cloud system (supra claim 1, Gust, 0014 e.g. see maintaining control despite communication loss with the server/”maintaining minimla level of control or operational control , supra claim 1 for cloud communications of Poumohammad et al., 0015
One of ordinary skill in the art before the effective filing date of the claimed invention applying the teachings of Gust, namely providing a minimal level of control in light of communication loss, to the teachings of Majewski et al., namely providing the control logic , would achieve an expected and predictable result via maintaining control in light of a communication loss. Gust is in the same field of endeavor and recognizes the need for internal control in light of communication losses as described.
Claim 24.
The unit of building equipment of claim 15, wherein:
the circuitry is configured to established communications with a cloud system; and
the control logic for the mechanical component, the expression-based event processing logic, and the machine learning algorithm are functional during interruptions of the communications with the cloud system, supra claim 10
Claims 14 and 24 are rejected under 35 USC 103 as being unpatentable over Majewski et al. (PG/PUB 20140172400) in view over Poumohammad et al. (PG/PUB 20200380387) in view over Kar et al. (PG/PUB 20180004180)
Claim 14.
The rooftop unit of claim 1 but does not expressly teach the second set limitations described below. Kar teaches the second set limitations described below (e.g. see providing additional fault detection logic via a server) wherein the control logic comprises a first set of one or more fault detection and/or diagnostics rules (supra claim 1 for FDD algorithms), and wherein the expression-based event processing logic comprises a second set of one or more fault detection and/or diagnostics rules that supplement (e.g. second or additional expressions or machine learning models, Kar ABSTRACT, 0008, Figure 3, 0018, 0028, 0037, 0057) or modify the first set of one or more fault detection and/or diagnostics rules, the second set of one or more fault detection and/or diagnostics rules received from a cloud system or another source remote from the rooftop unit (Kar ABSTRACT, 0008, Figure 3, 0018, 0028, 0037, 0057) supra claim 1 for receiving learning models for predicting faults that are in addition to the FDD algorithms) and defined according to an expression-based language (supra claim 1, see expression-based language as machine learning/training, supra claim 1)
One of ordinary skill in the art before the effective filing date of the claimed invention applying the teachings of Kar, namely providing a software application for providing additional fault detection via a cloud server, to the teachings of Majewski, as modified, namely providing a rooftop unit coupled to a cloud server for receiving fault detection machine learning algorithms for fault prediction while providing fault detection algorithms, would achieve an expected and predictable result of receiving a second set of fault detection logic for redundancy as well as expanding upon the capabilities of existing fault detection logic. Kar is reasonably pertinent to fault detection and would commend itself to expanding upon the fault detection capabilities of rooftop units as described.
Claim 28. The unit of building equipment of claim 15, wherein the control logic comprises a first set of one or more fault detection and/or diagnostics rules, and wherein the expression-based event processing logic comprises a second set of one or more fault detection and/or diagnostics rules that supplement or modify the first set of one or more fault detection and/or diagnostics rules, the second set of one or more fault detection and/or diagnostics rules received from a cloud system or another source remote from the unit and defined according to an expression-based language, supra claim 14
Claim 28 is rejected under the same rationale and prior art set forth in claim 14.
Claim 37 is rejected under 35 USC 103 as being unpatentable over Majewski et al. (PG/PUB 20140172400) in view over Poumohammad et al. (PG/PUB 20200380387) in view over Darrah in view over Hicks (PG/PUB 20220405568)
claim 37.
The method of claim 36 but does not expressly teach the neural network and historical data sets limitations described below. Hicks teaches the neural network and Darrah teaches historical data sets limitations described below, wherein the method further comprises:
training, by a computing system remote from the onboard circuitry, a neural network on a training data set comprises historical data from at least one of the heating, ventilation, or cooling component or other heating, ventilation, or cooling components (supra claim 3 for historical data sets for training a learning model for fault prediction, and see Hicks for determining an optimal learning algorithm from a trained neural network, 0003, 0004-0006, figure 2)
generating the machine learning algorithm to transmit to the onboard circuitry using the neural network (Hicks, Figure 2, ABSTRACT e.g. see determining the learning algorithm from multiple learning algorithms based on the trained neural network, and see model deployment of Poumohammad et al., supra claim 1)
One of ordinary skill in the art before the effective filing date of the claimed invention applying the teachings of Hicks, namely training a neural network, to the teachings of Majewski et al., as modified by Darrah, supra teachings employing historical training data obtained from environmental and HVAC components, would achieve an expected and predictable result of training a neural network using historical data including but not limited to air quality and vibration parameters for fault prediction.
The combination does not expressly teach generating the machine learning algorithm from the trained neural network, but Hicks teaches generating the machine learning algorithm from the trained neural network.
Accordingly, one of ordinary skill in the art before the effective filing date of the claimed invention applying the teachings of Hicks, namely generating the learning algorithm from the neural network, to the teachings of Majewski, as modified, namely training a neural network for fault prediction, would achieve an expected and predictable result of determining which learning algorithm of multiple is best suited for machine learning to minimize training time while maximizing accuracy. Hicks is reasonably pertinent to a problem of training neural networks and would commend itself to the training methods of Majewski, as modified, supra claim 1.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure..
claim1 relevancy
20230116964 20140172400 20080033674 20180373234
claim 3 relevancy
20230185652 20230038034 20230009603 20220146136 11307570 20210262689 20200380387 20200379464 10984338
20220414526
Claim 4 relevancy
11455555 20210385233 11828479 20110153089 20230103149 20200327371 20190310634 20210385233
Claim 6 relevancy
10387136 20150074658 20110153089 20120078839 20080301717 6658492 (updating software)
Claim 7 relevancy
8738860 20210294624 6658492
Claim 10 relevancy
20220360467 20190331358 20150045960 20130310986 20160246312 20150345804
Claim 12 relevancy
20250146691c 20240310804
Claim 14 relevancy
20140325291
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DARRIN D DUNN whose telephone number is (571)270-1645. The examiner can normally be reached M-Sat (10-8) PST.
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 at 571-272-2748. 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.
/DARRIN D DUNN/Patent Examiner, Art Unit 2117