DETAILED ACTION
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 1-8 and 10-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Regarding claim 1,
Step 1: Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a method.
Step 2A Prong One: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
The limitations of:
comparing, by the processing circuit, a manufacturing date for each of the failed building devices with the design change date; (mental evaluation, a human can look at dates and mentally make a comparison)
removing, by the processing circuit, any building devices from the first data set in response to the manufacturing date preceding the design change date to create an updated first data set; (mental evaluation, after comparing the dates, the user can, for example on pen and paper, scratch out devices that were manufactured before the design change)
generating, by the processing circuit, a training data set comprising the updated first data set; (mental evaluation, a human can come up with (“generate”) training data that is simply the result of the above comparison)
Step 2A Prong Two: Does the claim recite additional elements that integrate the judicial exception into a practical application?
The limitations of:
obtaining, by a processing circuit, a first data set for failed building devices based on warranty claim data associated with the building devices; (data gathering, insignificant extra-solution activity, MPEP 2105.05(g))
receiving, by the processing circuit, design change data associated with the building devices and determining a design change date based on the design change data; (data gathering, insignificant extra-solution activity, MPEP 2105.05(g))
training, by the processing circuit, a fault probability model using the training data set to produce a trained model (applying the abstract idea to a generic computer through the use of generic training, MPEP 2106.05(f))
Step 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception?
The limitations of:
obtaining, by a processing circuit, a first data set for failed building devices based on warranty claim data associated with the building devices; (data gathering, insignificant extra-solution activity, MPEP 2105.05(g), transmitting data is well-understood, routine, and conventional in the art, MPEP 2106.05(d)(II)(i))
receiving, by the processing circuit, design change data associated with the building devices and determining a design change date based on the design change data; (data gathering, insignificant extra-solution activity, MPEP 2105.05(g), transmitting data is well-understood, routine, and conventional in the art, MPEP 2106.05(d)(II)(i))
training, by the processing circuit, a fault probability model using the training data set to produce a trained model (applying the abstract idea to a generic computer through the use of generic training, MPEP 2106.05(f))
Dependent claim 2 recites a warranty claim, applying the abstract idea to a particular field of use or technological environment, MPEP 2016.05(h).
Dependent claim 3 recites including an identifier, applying the abstract idea to a particular field of use or technological environment, MPEP 2016.05(h).
Dependent claim 4 recites including dates, applying the abstract idea to a particular field of use or technological environment, MPEP 2016.05(h).
Dependent claim 5 recites predicting a fault within a building, mental evaluation, and initiating an automated action, instructions to apply the abstract idea MPEP 2106.05(f).
Dependent claim 6 recites altering a load, applying the abstract idea to a particular field of use or technological environment, MPEP 2016.05(h).
Regarding claim 7,
Step 1: Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a method.
Step 2A Prong One: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
The limitations of:
generating, by a fault prediction model, a probability score for failure based on the operation data; (mental judgement, a human can look at operation data and then make a decision (“generate”) a likelihood/probability that something is about to fail)
generating, by a thresholder, a threshold value configured to classify the probability score; (mental evaluation, a human can arbitrarily come up with (“generate”) a threshold value)
classifying the probability score based on the threshold value; (mental judgement, a human can make a judgement (“classify”) based on how likely they think something is to fail)
predicting a fault for the building equipment based on the classification of the probability score (mental judgement, a human can come to a conclusion that failure is imminent (“predict”))
Step 2A Prong Two: Does the claim recite additional elements that integrate the judicial exception into a practical application?
The limitations of:
receiving operation data for the building equipment; (receiving/transmitting data, insignificant extra-solution activity MPEP 2106.05(g))
Step 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception?
The limitations of:
receiving operation data for the building equipment; (receiving/transmitting data, insignificant extra-solution activity MPEP 2106.05(g), MPEP 2106.05(d)(II)(i))
Dependent claim 8 recites training the prediction model, applying the abstract idea on generic computer components. MPEP 2106.05(f).
Dependent claim 10 recites an f1-optimization technique, mathematical concepts.
Dependent claim 11 recites receiving data, comparing the data, and classifying it, well-understood routine and conventional data gathering and mental evaluations.
Dependent claim 12 recites receiving data, classifying it, receiving more data, comparing and adjusting, well-understood routine and conventional data gathering and mental evaluations.
Dependent claim 13 recites a self-learning thresholder, applying the abstract idea to a particular field of use or technological environment, MPEP 2016.05(h).
Dependent claim 14 recites a robust thresholder, applying the abstract idea to a particular field of use or technological environment, MPEP 2016.05(h).
Dependent claim 15 recites initiating an automated action, applying the abstract idea to a particular field of use or technological environment, MPEP 2016.05(h).
Dependent claim 16 recites altering a load, applying the abstract idea to a particular field of use or technological environment, MPEP 2016.05(h).
Regarding claim 17,
Step 1: Is the claim to a process, machine, manufacture or composition of matter?
Yes, the claim is directed to a method.
Step 2A Prong One: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
The limitations of:
evaluating, [by a neural network model], the past fault data; (mental evaluation, other than the use of generic computer (neural network) a human can look at data and evaluate it)
generating, [as an output of the neural network model based on the past fault data], a future fault prediction for a predetermined future time period comprising a plurality of future sub- periods, the future fault prediction comprising a fault occurrence prediction for each of the plurality of future sub-periods; (mental judgement, a human can look at data and make a reasonable estimation as to when it will fail (“generating a prediction”) based on data)
Step 2A Prong Two: Does the claim recite additional elements that integrate the judicial exception into a practical application?
a neural network (applying the abstract idea on generic computer components, MPEP 2106.05(f))
receiving past fault data for building equipment for a predetermined past time period comprising a plurality of past sub-periods, the past fault data comprising a number of occurrences of each of one or more types of faults during each of the plurality of past sub- periods; (data gathering, insignificant extra-solution activity, MPEP 2105.05(g))
initiating an automated action for the building equipment in response to the future fault prediction (applying the abstract idea to a particular field of use or technological environment, MPEP 2016.05(h).)
Step 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception?
a neural network (applying the abstract idea on generic computer components, MPEP 2106.05(f))
receiving past fault data for building equipment for a predetermined past time period comprising a plurality of past sub-periods, the past fault data comprising a number of occurrences of each of one or more types of faults during each of the plurality of past sub- periods; (data gathering, insignificant extra-solution activity, MPEP 2105.05(g), 2106.05(d)(II)(i))
initiating an automated action for the building equipment in response to the future fault prediction (applying the abstract idea to a particular field of use or technological environment, MPEP 2016.05(h).)
Dependent claim 18 recites past fault data, applying the abstract idea to a particular field of use or technological environment, MPEP 2016.05(h).
Dependent claim 19 recites a probability, applying the abstract idea to a particular field of use or technological environment, MPEP 2016.05(h).
Dependent claim 20 recites an automated action, applying the abstract idea to a particular field of use or technological environment, MPEP 2016.05(h).
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 7-8, 11, and 14-16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Llopis et al. US 2021/0190354 in view of Michael et al. US 2023/0123527.
Regarding claim 7, Llopis teaches “a method for predicting faults for building equipment, the method comprising: receiving operation data for the building equipment” ([0140] “In step 802, fault detection system 402 may perform a CUSUM analysis on actual building data and corresponding predicted building data to obtain cumulative sum values for multiple times or time-steps, in some embodiments. Cumulative sum values may be cumulative error values for the aggregated error of a point of a BAS for time-steps up to and, in some cases, including the time associated with the cumulative sum value”);
More specifically, Michael teaches “generating, by a fault prediction model, a probability score for failure based on the operation data” (Michael [0076] “the data consolidation process 308 also includes training a machine learning to combine the extracted knowledge from the maintenance records 302 (the transactional information) with measurement readings 306 (the sensor data) to predict a likelihood of part failure”);
It would have been obvious to one having ordinary skill in the art at the time that the invention was effectively filed to combine the teachings of Llopis with that of Michael since a combination of known methods would yield predictable results. Llopis deals with early fault detection in building systems while Michael pertains specifically more to predictive fault detection. Therefore by combining the techniques, instead of detecting faults early, one would be able to anticipate beforehand. This allows for better building maintenance.
Llopis further teaches “generating, by a thresholder, a threshold value configured to classify the probability score” (Llopis [0064] “The processor may analyze the gradient of the cumulative sum values at various times until it identifies a gradient that is lower than a threshold. The processor may identify the time associated with the gradient below the threshold as the minimum and consequently the time that the fault began”);
“classifying the probability score based on the threshold value” ([0142] “In some embodiments, fault detection system 402 may determine that a fault occurred at the first time based on the CUSUM reaching the threshold at the first time.” i.e. classifying as a fault)
Lastly, Michael teaches “predicting a fault for the building equipment based on the classification of the probability score” (Michael abstract “using the sensor data and the extracted plurality of concepts, to predict part failure likelihood of the one or more parts”)
Regarding claim 8, the Llopis and Michael references have been addressed above. Michael further teaches “further comprising training the fault prediction model using training data based on a grouping of the building equipment according to one or more characteristics, wherein the one or more characteristics include at least one of an age of the building equipment, an operational load placed on the building equipment, a capacity of the building equipment, or an environmental condition of the building equipment” (Michael abstract “The system receives transactional data pertaining to replacement of, and sensor data pertaining to duty cycle of, one or more parts”)
Regarding claim 11, the Llopis and Michael references have been addressed above. Llopis further teaches “wherein classifying the probability score based on the threshold value comprises: receiving the threshold value; comparing the probability score to the threshold value; in response to the probability score being above the threshold value, classifying the probability score as faulty; and in response to the probability score being below the threshold value, classifying the probability score as normal” ([0095] “To do so, a processor may compare values of CUSUM 302 to fault threshold 306. Using methods previous to the methods described herein, the processor may determine that faults end when CUSUM 302 exceeds fault threshold 306 and ends when CUSUM 302 decreases below fault threshold 306.”)
Regarding claim 14, the Llopis and Michael references have been addressed above. Llopis further teaches “wherein the thresholder is a robust thresholder configured to determine the threshold value based one or more previous fault predictions made for the building equipment” ([0062] “The building manager may implement a processor to perform a cumulative sum analysis to generate cumulative sum values and determine when a cumulative sum value of a point reaches a fault threshold. The cumulative sum values may be cumulative error values. Using previous implementations, the processor may determine that faults begin at the time in which a cumulative sum value increased to a fault threshold.”)
Regarding claim 15, the Llopis and Michael references have been addressed above. Michael further teaches “the method further comprising initiating an automated action in response to predicting the fault for the building equipment” (Michael [0009] “One example is Uptake®, which may use machine learning models and asset sensor data to predict when the next failures are likely to occur, so that corrective maintenance can be performed”)
Regarding claim 16, the Llopis and Michael references have been addressed above. Michael further teaches “wherein the automated action comprises at least one of altering a load on the building equipment to mitigate or prevent the fault or performing maintenance on the building equipment to mitigate or prevent the fault” (Michael [0137] “The RCA process can also identify corrective actions that can be taken to eliminate these causes—automated shutdown control systems, operator training or adding a warning.”)
Claim(s) 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Llopis and Michael further in view of Lipton, Zachary Chase, Charles Elkan, and Balakrishnan Narayanaswamy. "Thresholding classifiers to maximize F1 score."
Regarding claim 10, the Llopis and Michael references have been addressed above. They do not explicitly teach the claim limitations. Lipton however teaches “wherein the thresholder generates a threshold based on an F-score selected by an fl-optimization technique” (Lipton abstract “For any classifier that pro duces a real-valued output, we derive the relationship between the best achievable F1 score and the decision-making threshold that achieves this optimum. As a special case, if the classifier outputs are well-calibrated conditional probabilities, then the optimal threshold is half the optimal F1 score”)
It would have been obvious to one having ordinary skill in the art at the time that the invention was effectively filed to combine the teachings of Llopis and Michael with that of Lipton since a combination of known methods would yield predictable results. As shown in Lipton, f1 optimization is a known technique. One would use this technique with the system above in order to improve model performance.
Claim(s) 12-13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Llopis and Michael further in view of Braundmeier et al. US 2019/0310906 [herein Braund].
Regarding claim 12, the Llopis and Michael references have been addressed above. Llopis further teaches “wherein the thresholder is a self-adaptive thresholder configured to: receive the probability score; classify the probability score based on the threshold value as faulty or normal” ([0095] “To do so, a processor may compare values of CUSUM 302 to fault threshold 306. Using methods previous to the methods described herein, the processor may determine that faults end when CUSUM 302 exceeds fault threshold 306 and ends when CUSUM 302 decreases below fault threshold 306.”);
“receive building equipment maintenance data” ([0090] “Integrated control layer 218 can be configured to provide feedback to demand response layer 214 so that demand response layer 214 checks that constraints (e.g., temperature, lighting levels, etc.) are properly maintained even while demanded load shedding is in progress. The constraints can also include setpoint or sensed boundaries relating to safety, equipment operating limits and performance, comfort, fire codes, electrical codes, energy codes, and the like.”);
“compare the classification of the probability score to the building equipment maintenance data to determine an accuracy of the threshold value” ([0091] “Automated measurement and validation (AM&V) layer 212 can be configured to verify that control strategies commanded by integrated control layer 218 or demand response layer 214 are working properly (e.g., using data aggregated by AM&V layer 212, integrated control layer 218, building subsystem integration layer 220, FDD layer 216, or otherwise). The calculations made by AM&V layer 212 can be based on building system energy models and/or equipment models for individual BAS devices or subsystems.” i.e. comparing data); and
The references do not explicitly teach adjusting the threshold. Braund however teaches “adjust the threshold value based on the accuracy” (Braund [0028] “In one embodiment, the FE platform is configured to compare the fault score for each fault event against a threshold value. The threshold value may be predefined by a user as a static value, or a dynamically changing value informed by various circumstances such as anticipated processing load for a component. When the fault score for a fault event exceeds the threshold value, the FE platform is configured to initiate a component remediation process.”)
It would have been obvious to one having ordinary skill in the art at the time that the invention was effectively filed to combine the teachings of Llopis and Michael with that of Braund since a combination of known methods would yield predictable results. As shown in Braund, it is known to modify threshold based on various criteria. This is analogous to adjusting a threshold based on accuracy since based on the data of a device, the threshold may need to be modified.
Regarding claim 13, the Llopis, Michael, and Braund references have been addressed above. Braund further teaches “wherein the thresholder is a self-learning thresholder configured to adjust the threshold value to account for a degradation of building equipment over time” (Braund [0028] “In one embodiment, the FE platform is configured to compare the fault score for each fault event against a threshold value. The threshold value may be predefined by a user as a static value, or a dynamically changing value informed by various circumstances such as anticipated processing load for a component. When the fault score for a fault event exceeds the threshold value, the FE platform is configured to initiate a component remediation process.” )
Claim(s) 17-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Michael in view of Llopis.
Regarding claim 17, Michael teaches “a method comprising: receiving past fault data for [building equipment] for [a predetermined past time period comprising a plurality of past sub-periods], the past fault data comprising a number of occurrences of each of one or more types of faults during each of the plurality of past sub- periods” (Michael [0099] “the third machine learning model uses the age of the part (how long since it was last changed—obtained using the first stage machine learning model), duty cycle (obtained using sensor data 306), and the predicted likelihood of failure (obtained from the second stage machine learning model) as inputs to the training data. Historical “run-to-failure” data (obtained from both the sensor data 306 and the first stage machine learning model) is used as ground truth (the desired output) for the training data” and [0102] “In step 2710, historical transactional data pertaining to replacement of, and historical sensor data pertaining to duty cycle of, parts is received. In step 2720, a first stage machine learning model is trained using the historical transactional data as training data for the first machine learning model.”);
“evaluating, by a neural network model, the past fault data” ([0100] “the third machine learning model is trained using a validation approach, such as k-fold cross validation, to prevent overfitting and promote generalization. Further, different types of machine learning models, such as neural networks, k-nearest neighbors, support vector machines, etc. may be used for the third machine learning model”);
“generating, as an output of the neural network model based on the past fault data, a future fault prediction for a predetermined future time period comprising a plurality of future sub- periods, the future fault prediction comprising a fault occurrence prediction for each of the plurality of future sub-periods” ([0097] “the machine learning model for the second stage classifier is not limited to neural networks and other machine learning models, such as a Bigram classifier, support vector machine, random forest of decision trees, or k-nearest neighbor, or a combination of different types of machine learning models may be used to predict the probability or likelihood of part failure”); and
“initiating an automated action for the building equipment in response to the future fault prediction” (Michael [0009] “One example is Uptake®, which may use machine learning models and asset sensor data to predict when the next failures are likely to occur, so that corrective maintenance can be performed”)
Michael however does not explicitly teach building data. Llopis however teaches “building data” (A building system for detecting faults in an operation of building equipment. The building system comprising one or more memory devices configured to store instructions thereon that cause the one or more processors to perform a cumulative sum (CUSUM) analysis on actual building data and corresponding predicted building data to obtain cumulative sum values for a first plurality of times within a first time period;)
“a predetermined past time period comprising a plurality of past sub-periods” (abstract “a first plurality of times within a first time period” i.e. multiple time periods)
It would have been obvious to one having ordinary skill in the art at the time that the invention was effectively filed to combine the teachings of Michael with that of Llopis since a combination of known methods would yield predictable results. Llopis deals with early fault detection in building systems while Michael pertains specifically more to predictive fault detection. Therefore by combining the techniques, instead of detecting faults early, one would be able to anticipate beforehand. This allows for better building maintenance.
Regarding claim 18, the Michael and Llopis references have been addressed above. Michael further teaches “wherein the past fault data includes occurred faults in a plurality of categories including at least one of a safety fault, a warning fault, a cyclic fault, or a health fault” (Michael [0107] “For example, an oil leak may not prevent a vehicle from operating but a steering arm failure may prevent the vehicle from operating”)
Regarding claim 19, the Michael and Llopis references have been addressed above. Michael further teaches “wherein the fault occurrence prediction for a sub-period of the plurality of future sub-periods comprises a predicted probability of at least one fault occurring during the sub-period” (abstract “The system determines the part failure likelihood of the one or more parts by providing new transactional data and new sensor data to the trained machine learning models”)
Regarding claim 20, the Michael and Llopis references have been addressed above. Michael further teaches “wherein the automated action comprises at least one of altering a load on the building equipment to mitigate or prevent a fault indicated by the future fault prediction or performing maintenance on the building equipment to mitigate or prevent the fault indicated by the future fault prediction” (Michael [0137] “The RCA process can also identify corrective actions that can be taken to eliminate these causes—automated shutdown control systems, operator training or adding a warning.”)
Allowable Subject Matter
No art has been cited for claims 1-6 and 9. Claims 1-6 remain rejected under 101.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Shinkle et al. US 2016/0091397
Rajpathak, Dnyanesh, and Soumen De. "A data-and ontology-driven text mining-based construction of reliability model to analyze and predict component failures." Knowledge and information systems 46.1 (2016): 87-113.
Sabri-Laghaie, Kamyar, et al. "Early detection of product reliability based on the parameters of the production line and warranty data." International Journal of Reliability, Quality and Safety Engineering 28.05 (2021): 2150035.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KEVIN W FIGUEROA whose telephone number is (571)272-4623. The examiner can normally be reached Monday-Friday, 10AM-6PM EST.
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, MIRANDA HUANG can be reached at (571)270-7092. 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.
KEVIN W FIGUEROA
Primary Examiner
Art Unit 2124
/Kevin W Figueroa/Primary Examiner, Art Unit 2124
Prosecution Insights