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 .
1. Claims 1-17 are presented for examination.
Claim Rejections - 35 USC § 112
2. The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 10 and 16 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
In claim 1, line 5 the use of “its” are unclear , what the metes and bounds of “its” is unclear.
Claim Rejections - 35 USC § 101
3. 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.
3.1 Claims 1-17 rejected under 35 U.S.C. 101 because abstract idea without significantly more.
When considering subject matter eligibility under 35 U.S.C. 101, in step 1 it must be determined whether the claim is directed to one of the four statutory categories of invention, i.e., process, machine, manufacture, or composition of matter. If the claim does fall within one of the statutory categories, in step 2A prong 1 it must then be determined whether the claim is recites a judicial exception (i.e., law of nature, natural phenomenon, and abstract idea). If the claim recites a judicial exception, under step 2A prong 2 it must additionally be determined whether the recites additional elements that integrate the judicial exception into a practical application. If a claim does not integrate the Abstract idea into a practical application, under step 2B it must then be determined if the claim provides an inventive concept.
that To facilitate examination, the Office has set forth an approach to identifying abstract ideas that distills the relevant case law into enumerated groupings of abstract ideas. The enumerated groupings are firmly rooted in Supreme Court precedent as well as Federal Circuit decisions interpreting that precedent, as is explained in MPEP § 2106.04(a)(2). This approach represents a shift from the former case-comparison approach that required examiners to rely on individual judicial cases when determining whether a claim recites an abstract idea. By grouping the abstract ideas, the examiners' focus has been shifted from relying on individual cases to generally applying the wide body of case law spanning all technologies and claim types.
Step 2A, Prong one
The claim 1 recites:
- grouping the feature data to generated power consumption behavior groups, which can perform in the human mind or by a human using a pen and paper (Mental processes concepts performed in the human mind (including an observation, evaluation, judgment, opinion) (see MPEP § 2106.04(a)(2), subsection III)); thus, it is an abstract idea;
- filtering the power consumption behavior group based on the threshold to generate or classify a normal and an anomaly or noise power consumption, which is an abstract mathematical concept (Mathematical concepts - mathematical relationships, mathematical formulas or equations, mathematical calculations (see MPEP § 2106.04(a)(2), subsection I); thus, it is an abstract idea;
- Verification by inputting the normal power consumption data which can perform in the human mind or by a human using a pen and paper (Mental processes concepts performed in the human mind (including an observation, evaluation, judgment, opinion) (see MPEP § 2106.04(a)(2), subsection III)); and the noise data to single classification model to generated detection results, is a mathematical algorithm (Mathematical concepts - mathematical relationships, mathematical formulas or equations, mathematical calculations (see MPEP § 2106.04(a)(2), subsection I); thus, it is an abstract idea as a mental process or mathematical concept.
The above listed limitations, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind or the mathematical concept but for the recitation of generic computer components (processor). That is, other than reciting “a processor,” nothing in the claim element precludes the step from practically being performed in the mind. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind or mathematical concept but for the recitation of generic computer components, then it falls within a mathematical algorithm or mental process) grouping of abstract ideas. Accordingly, the claim 1 recites an abstract idea.
Step 2A, Prong Two
This judicial exception is not integrated into a practical application. In particular, the claim only recites additional element – a processing unit and a storage unit, the storage unit is coupled to the processing unit, the storage unit stores an anomaly detection model, however, are recited at a high level of generality and given the broadest reasonable interpretation are simply generic computers performing generic computer functions. Generic computers performing generic computer functions, alone, do not amount to significantly more than the abstract idea and mere instructions to implement an abstract idea on a computer. The computer is recited at a high level of generality. In limitation (a), the computer is used as a tool to perform the generic computer function of receiving data. See MPEP 2106.05(f). In limitations (b) and (c), the computer is used to perform an abstract idea, as discussed above in Step 2A, Prong One, such that it amounts to no more than mere instructions to apply the exception using a generic computer. See MPEP 2106.05(f).
-a processing unit for “obtaining historical data… to obtain feature data”, falls under insignificant extra-solution activity or data gathering, see MPEP § 2106.05(g); (“whether the limitation is significant”); in addition, all uses of the recited judicial exceptions require such data gathering and output, and, as such, these limitations do not impose any meaningful limits on the claim. These limitations amount to necessary data gathering and outputting. See MPEP 2106.05, and
-using processing unit (processor) training process anomaly detection model with the processing unit and inputting normal power consumption data to single classification model for training, the computer is recited at a high level of generality, the computer is used as a tool to perform the generic computer function of receiving data. See MPEP 2106.05(f). the limitation “classification model” the computer is used to perform an abstract idea, as discussed above in Step 2A, Prong One, such that it amounts to no more than mere instructions to apply the exception using a generic computer. See MPEP 2106.05(f). The judicial exception of “detecting one or more anomalies in a data set using the train classification model is generally apply the abstract idea without placing any limits on how the trained model functions. Rather, these limitations only recite the outcome of “detecting one or more anomalies” and “verify” the one or more detected anomalies” and do not include any details about how the “detecting” and “verifying” are accomplished. See MPEP 2106.05(f).
-storing the anomaly detection model in the storage unit …. is considered an insignificant extra-solution activity does not amount to an inventive concept, see MPEP 2106.05(g)
Those limitations merely confine the use of the abstract idea to a particular technological environment (train model) and thus, fails to add an inventive concept to the claims. See MPEP 2106.05(h). Even when viewed in combination, these additional elements do not integrate the recited judicial exception into a practical application (Step 2A, Prong Two: NO), and the claim is directed to the judicial exception. (Step 2A: YES).
Step 2B
The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception. As discussed above with respect to integration of the abstract idea
into a practical application, the additional element of listed in Step 2A Prong Two, At Step 2B, the evaluation of the insignificant extra-solution activity consideration takes into account whether or not the extra-solution activity is well understood, routine, and conventional in the field. See MPEP 2106.05(g). As discussed in Step 2A, Prong Two above, the recitations of obtaining historical data, training data using classification model and storing the anomaly data from the trained are recited at a high level of generality. These elements amount to receiving training data or transmitting data over a network and are well understood, routine, conventional activity, as show in the prior art, Himeur et al. (Artificial intelligence-based anomaly detection of energy consumption in buildings) discloses and detecting anomalous consumption using OCSVM One-class support vector machine learning model; and See MPEP 2106.05(d), subsection II. Even when considered in combination, these additional elements represent mere instructions to implement an abstract idea or other exception on a computer and insignificant extra-solution activity, which do not provide an inventive concept. (Step 2B: NO). Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The claim is not patent eligible.
Regarding claims 6 and 12,
Step 2A, Prong One
claims 6 and 12, recite:
grouping the feature data to generated power consumption behavior groups, which can perform in the human mind or by a human using a pen and paper (Mental processes concepts performed in the human mind (including an observation, evaluation, judgment, opinion) (see MPEP § 2106.04(a)(2), subsection III)); thus, it is an abstract idea;
differentiating the electricity load data of the user according to unit time to become a plurality segments of sub-electricity load data, which is an abstract mathematical concept (Mathematical concepts - mathematical relationships, mathematical formulas or equations, mathematical calculations (see MPEP § 2106.04(a)(2), subsection I); thus, it is an abstract idea;
comparing each of the segments of sub-electricity load data with the historical load data of the user to output a plurality of anomaly electricity consumption periods, which can perform in the human mind or by a human using a pen and paper (Mental processes concepts performed in the human mind (including an observation, evaluation, judgment, opinion) (see MPEP § 2106.04(a)(2), subsection III)); thus, it is an abstract idea.
The above listed limitations, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind or the mathematical concept but for the recitation of generic computer components (processor). That is, other than reciting “a processor,” nothing in the claim element precludes the step from practically being performed in the mind. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind or mathematical concept but for the recitation of generic computer components, then it falls within a mathematical algorithm or mental process) grouping of abstract ideas. Accordingly, the claim 1 recites an abstract idea.
Step 2A, Prong Two
This judicial exception is not integrated into a practical application. In particular, the claim only recites additional element – a processing unit and a storage unit, the storage unit is coupled to the processing unit, the storage unit stores an anomaly detection model, however, are recited at a high level of generality and given the broadest reasonable interpretation are simply generic computers performing generic computer functions. Generic computers performing generic computer functions, alone, do not amount to significantly more than the abstract idea and mere instructions to implement an abstract idea on a computer. The computer is recited at a high level of generality. In limitation (a), the computer is used as a tool to perform the generic computer function of receiving data. See MPEP 2106.05(f). In limitations (b) and (c), the computer is used to perform an abstract idea, as discussed above in Step 2A, Prong One, such that it amounts to no more than mere instructions to apply the exception using a generic computer. See MPEP 2106.05(f).
-a processing unit for “obtaining historical data… to obtain feature data”, falls under insignificant extra-solution activity or data gathering, see MPEP § 2106.05(g); (“whether the limitation is significant”); in addition, all uses of the recited judicial exceptions require such data gathering and output, and, as such, these limitations do not impose any meaningful limits on the claim. These limitations amount to necessary data gathering and outputting. See MPEP 2106.05, and
-using a processor, inputting the power consumption behavior groups to the single classification model, and inputting the detection result into integration layer network to generate an anomaly electricity detection result; the computer is recited at a high level of generality, the computer(processor) is used as a tool to perform the generic computer function of receiving data. See MPEP 2106.05(f). the limitation “classification model” the computer is used to perform an abstract idea, as discussed above in Step 2A, Prong One, such that it amounts to no more than mere instructions to apply the exception using a generic computer. See MPEP 2106.05(f).
The judicial exception of “detecting one or more anomalies in a data set using the train classification model is generally apply the abstract idea without placing any limits on how the trained model functions. Rather, these limitations only recite the outcome of “detecting one or more anomalies” and “comparing” the one or more detected anomalies” and do not include any details about how the “detecting” and “comparing” are accomplished. See MPEP 2106.05(f).
Those limitations merely confine the use of the abstract idea to a particular technological environment (train model) and thus, fails to add an inventive concept to the claims. See MPEP 2106.05(h). Even when viewed in combination, these additional elements do not integrate the recited judicial exception into a practical application (Step 2A, Prong Two: NO), and the claim is directed to the judicial exception. (Step 2A: YES).
Step 2B
The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception. As discussed above with respect to integration of the abstract idea
into a practical application, the additional element of listed in Step 2A Prong Two, At Step 2B, the evaluation of the insignificant extra-solution activity consideration takes into account whether or not the extra-solution activity is well understood, routine, and conventional in the field. See MPEP 2106.05(g).
As discussed in Step 2A, Prong Two above, the recitations of obtaining historical data, training data using classification model and differentiating the electricity load data of the user according to unit time to become a plurality segments of sub-electricity load data; and comparing … output a plurality of anomaly electricity consumption periods,
The additional element(s) adds insignificant extra-solution activity to the judicial exception,
Even when considered in combination, these additional elements represent mere instructions to implement an abstract idea or other exception on a computer and insignificant extra-solution activity, which do not provide an inventive concept. (Step 2B: NO). The additional element of using generic computer elements and machines to perform the steps amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instruction to apply an exception using a generic computer component cannot provide an inventive concept. The claim is not patent eligible.
Regarding claims 2, 7 and 13, recite -defining the power consumption high and low usage, falls under insignificant extra-solution activity or data gathering, see MPEP § 2106.05(g); thus, the claims are an abstract idea.
Regarding claims 3-4, 8 and 14, recite -training the single classification model, falls under mathematical concept Mathematical concepts - mathematical relationships, mathematical formulas or equations, mathematical calculations (see MPEP § 2106.04(a)(2), subsection I); from the received normal power consumption data, falls under insignificant extra-solution activity or data gathering, see MPEP § 2106.05(g); thus, the claims are an abstract idea.
Regarding claims 5, 9, and 15, recite – defining the single classification, falls under insignificant extra-solution activity or data gathering, see MPEP § 2106.05(g); thus, the claims are an abstract idea.
Regarding claims 10 and 16, recite -input layer, output layer and weight layer and transmitted … falls under insignificant extra-solution activity or data gathering, see MPEP § 2106.05(g); thus, the claims are an abstract idea.
Regarding claims 11 and 17, recite – further defining the integrated layer network, falls under insignificant extra-solution activity or data gathering, see MPEP § 2106.05(g); thus, the claims are an abstract idea.
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.
4. 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.
4.1 Claim(s) 1-2 and 5 is/are rejected under 35 U.S.C. 103 as being unpatentable over Himeur et al. (Artificial intelligence-based anomaly detection of energy consumption in buildings) in view of Bos et al. (US 20210064933 A1) further in view of Tsai (US 20180157310 A1).
Regarding claim 1, Himeur discloses an anomaly detection model training (method for household electricity, applied to a load detection device (page 3, column 2, section 2.1, 2.1.1, Fig. 1-3, AI algorithms used to detect anomalies. The classification of anomaly detection techniques in building energy consumption with reference to different aspects), wherein the load detection device (Fig. 2 and 3, page 12, column 2, par. 2, page 10, column 2, section 2.4, energy consumption collection, smart-meters and smart sensors, which collecting power consumption);
the anomaly detection model comprises a first group of single classification models and a second group of single classification models (Page 3, column 1, par. 2, column 11, column 2, Fig. 4 and 5, anomaly detection schemes in building energy consumption, in which a comprehensive classification is adopted to classify them into various categories based on the nature of machine learning model used to identify the anomalies, feature extraction, detection level, computing platform, application scenario and privacy preservation),
the anomaly detection model training method performs a training process on the anomaly detection model with the processing unit (page 3, column 2, section 2.1, Fig. 1, anomaly detection methods based on the nature of implemented AI algorithms used to detect anomalies),
a processing unit and a storage unit, the storage unit is coupled to the processing unit, the storage unit stores an anomaly detection model (page 10, column 2, section 2.4, data pre-processing, computing, storage and analysis are conducted in the layer located between the data collection devices and the cloud the computational ability of the anomaly detection solution is carried out close to both the data recording devices and the cloud, in which data are produced and handled. Edge computing platforms: refer to distributed computational models that allow to drop the computing resources and information storage capabilities close to the end-user application, where it can directly be used, e.g. in energy consumption applications this can be done on the smart sensor platforms or smart plug devices, Specifically, a smart plug is being developed to incorporate different sensors to collect consumption and contextual data along with a microcontroller to pre-process data, segregate the main consumption signal into device specific footprints, and detect abnormal behaviors);
the training process comprises the following steps:
obtaining historical load data of a user and performing electricity feature extraction to obtain feature data (Fig. 2, Fig. 3, page 5, column 2, par. 4, page 8, column 2, par. 3, consumption behaviors using their recent/past consumption data are collect for the appliances, pre-processing and feature extraction to collect the appliance feature data);
grouping the feature data to generate a first electricity consumption behavior group and a second electricity consumption behavior group (page 8, column 1 and column 2, section 2.1.4, feature extraction to perform power consumption observations in novel spaces (e.g. high dimensional spaces); (ii) utilizing appropriate measures and functions (e.g. distance, density) to discriminate between normal and abnormal consumption; and (iii) representing the consumption flowchart using new representation structures (e.g. graph-based representation) Distance-based, Time-series analysis);
an electricity noise data (page 5, column 2, par. 6, page 9, column 1, par. 2, ANN could help in solving the anomaly detection issue when recorded data is noisy due to various reasons, e.g. noise generated during data transmission or from electrical appliances connected), wherein the first normal electricity consumption data and the second normal electricity consumption data do not have the electricity noise data (page 9, column 1, section 1, 2.1.5. Hybrid learning). Annotating normal power consumption is much easier than labeling anomalous patterns, consequently, hybrid or semi-supervised anomaly detection has been adopted in several frameworks [166]. It leverages available annotated normal footprints (having labels) and pertaining to the positive class to identify abnormalities from the negative class. This is the case of deep autoencoder (DAE) architecture when it is only applied to learn normal consumption patterns (with no anomalies); and
storing the anomaly detection model in the storage unit when the detection results are all greater than a preset anomaly detection value (page 10, column 2, section 2.4, data pre-processing, computing, storage and analysis are conducted in the layer located between the data collection devices and the cloud the computational ability of the anomaly detection solution is carried out close to both the data recording devices and the cloud, in which data are produced and handled. Edge computing platforms: refer to distributed computational models that allow to drop the computing resources and information storage capabilities close to the end-user application, where it can directly be used, e.g. in energy consumption applications this can be done on the smart sensor platforms or smart plug devices, Specifically, a smart plug is being developed to incorporate different sensors to collect consumption and contextual data along with a microcontroller to pre-process data, segregate the main consumption signal into device specific footprints, and detect abnormal behaviors).
Himeur fails to disclose training step, inputting the first normal electricity consumption data and the second normal electricity consumption data to the first group of single classification models and the second group of single classification models for training; verification step, inputting the first normal electricity consumption data, the second normal electricity consumption data, and the electricity noise data to the first group of single classification models and the second group of single classification models to generate detection results corresponding to the first group of single classification models and the second group of single classification models.
However, Bos discloses training step, inputting the first normal electricity consumption data and the second normal electricity consumption data to the first group of single classification models and the second group of single classification models for training (Fig. 1, Abstract, [0004], new inputs to a value indicating normal operation of the system; training a new anomaly detection model using incremental learning to update the trained machine learning model using the labeled set of new inputs and setting a label (classification) for each of the set of new inputs to a value indicating normal operation of the system); and
verification step, inputting the first normal electricity consumption data, the second normal electricity consumption data, and the electricity noise data to the first group of single classification models and the second group of single classification models to generate detection results corresponding to the first group of single classification models and the second group of single classification models (Fig. 1, [0004]-[0006], receiving a set of past model inputs with an associated label; producing a verification set by inputting the set of past model inputs into the new anomaly detection model; and comparing the verification set with the labelled past model inputs to determine if an anomaly is present. An anomaly is determined when the number of items in the verification set that do not match the labelled past model inputs exceeds a threshold value. hen an anomaly is present in the verification set: (a) dividing the new set of new inputs into a plurality of subsets; (b) setting a label for each of the set of new inputs to a value indicating normal operation of the system; (c) training a plurality of new anomaly detection models using incremental learning to update the trained machine learning model using each of the labeled subset of new inputs; (d) producing a set of verification subsets by inputting the set of past model inputs into the each of the plurality of new anomaly detection models; and (e) comparing each of the plurality of verification sets with the labelled past model inputs to determine if an anomaly is present in each of the plurality of subsets of new inputs).
Bos and Himeur are analogous art. They relate to monitoring and anomaly detection of the power consumption appliance.
Therefore, before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to modify anomaly detection in building energy consumption, taught by Himeur, incorporated with trained machine learning model that detects anomalies, taught by Bos, in order to remove the need to install individual sub-meters for each appliance and hence helps in significantly reducing the cost of anomaly detection solutions.
The combination of Bos and Himeur fail to disclose filtering the first electricity consumption behavior group and the second electricity consumption behavior group based on an anomaly threshold to generate a first normal electricity consumption data corresponding to the first electricity consumption behavior group, a second normal electricity consumption data corresponding to the second electricity consumption behavior.
However, Tsia discloses filtering the first electricity consumption behavior group and the second electricity consumption behavior group based on an anomaly threshold to generate a first normal electricity consumption data corresponding to the first electricity consumption behavior group, a second normal electricity consumption data corresponding to the second electricity consumption behavior group ([0038]-[0039], filtering the load operation modes of a (plurality the analysis of client events of an electric power consumers), the processing unit 503 of the server 5 uses a support algorithm to calculate the appearance frequency of each load operation mode and delete the load operation modes with an appearance frequency lower than a threshold value for giving the plurality of load operation modes).
Tsia, Bos and Himeur are analogous art. They relate to monitoring and anomaly detection of the power consumption appliance.
Therefore, before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to modify analyzing client events of an electric power consumer, taught by Tsia, incorporated with the teaching of Himeur and Bos, as state above, in order to enabled to correspond to the load operation relation mode to give the behavior mode of the electric power consumer.
Regarding claim 2, Himeur discloses defining the first electricity consumption behavior group as a high electricity consumption load and defining the second electricity consumption behavior group as a low electricity consumption load based on the historical load data (Fig. 1, page 12, column 2, par. 2-3, each appliance in Fig. 2, has different power consumption level, higher or lower than usual consumption footprints, as it is the case in other applications).
Regarding claim 5, Bos and Himeur disclose:
Bos discloses the first group of single classification models and the second group of single classification models are a one-class SVM (OCSVM) model and an isolation forest model, respectively ([0031], machine learning model architectures include support vector machines (SVM), linear classifiers, nearest neighbor, decision trees, boosted trees, random forests, and neural networks. During training, various aspects and parameters of the machine learning model and architecture may be used in order to optimize a loss function associated with the training process); and Himeur discloses in page 4, column 1, section U2, One-class classification: also named one-class learning (OCL) relies on considering initial power consumption patterns to be parts of two groups, positive (normal) and negative (abnormal), one-class support vector machine (OCSVM) and the energy consumption anomaly detection process performed using an isolated forest (iForest) model.
4.2 Claim(s) 6-7, 12-13, 9, 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Elbsat et al. (US 20150316907 A1) in view of Himeur et al. (Artificial intelligence-based anomaly detection of energy consumption in buildings).
Regarding claims 6 and 12, Elbsat discloses anomaly detection method for household electricity (Abstract, a novel anomaly detection method detecting electrical faults in household appliances based on the analysis of their power signatures with unsupervised deep learning techniques), applied to a load detection device (load sensor BMS 400),
wherein the load detection device (load sensor BMS 400), comprises a processing unit and a storage unit (a processor of BMS controller 366 and ), the storage unit is coupled to the processing unitI ([0066], memory 408 is communicably connected to processor) the storage unit stores an anomaly detection model ([0066] Memory 408 (e.g., memory, memory unit, storage device, etc.) may include one or more devices (e.g., RAM, ROM, Flash memory, hard disk storage, etc.) for storing data and/or computer code for completing or facilitating the various processes, layers and module),
the anomaly detection model comprises a first group of single classification models and a second group of single classification models ( page 4, column 1, section U2, One-class classification: also named one-class learning (OCL) relies on considering initial power consumption patterns to be parts of two groups, positive (normal) and negative (abnormal),
the processing unit performs the anomaly detection method, and the anomaly detection method comprises the following steps: obtaining historical load data of a user ([0086]-[0087], load values in load history database 508) and performing electricity feature extraction to obtain feature data ([0086]-[0087], a history of time series load values and/or other time series values that are measured or calculated in BMS 400);
grouping the feature data to generate a first electricity consumption behavior group and a second electricity consumption behavior group ([0089], divide the historical load data into multiple different bins n.sub.bins based on the schedule data in schedule database 512, where n.sub.bins is the total number of bins. The historical load data are divided into bins based on the type of load associated with the load data);
inputting the first electricity consumption behavior group and the second electricity consumption behavior group to the first group of single classification models and the second group of single classification models to generate the detection results corresponding to the first group of single classification models and the second group of single classification models, respectively ([0104]-[105], Day-type classifier 604 may be configured to analyze the binned load data to determine which days of the week have similar load profiles. The load profile of a facility can varies significantly from one day of the week to another. For example, the historical load data for an office building may indicate that Monday through Friday (i.e., when workers are present) are similar to one another in terms of electricity consumption, whereas Saturday and Sunday have a different electricity consumption profile. In this example, day-type classifier 604 may classify Monday through Friday as a first day-type, and Saturday and Sunday as a second day-type. FIG. 10 illustrates an exemplary electricity consumption curve over several weeks for a facility that has different load profiles on weekdays and weekends).
Elbsat fails to discloses inputting the detection results into an integration layer network to generate an anomaly electricity detection result; differentiating, based on the anomaly electricity detection results, the electricity load data of the user according to unit time to become a plurality segment of sub-electricity; and comparing each of the segments of sub-electricity load data with the historical load data of the user to output a plurality of anomaly electricity consumption periods.
However, Himeur discloses inputting the detection results into an integration layer network to generate an anomaly electricity detection result (Fig. 1, page 9, column 1, section 2.1.5, deep autoencoder (DAE) architecture when it is only applied to learn normal consumption patterns (with no anomalies) using enough training consumption observations from the normal category, the autoencoder could generate low reconstruction errors for normal observations over abnormal patterns);
differentiating, based on the anomaly electricity detection results, the electricity load data of the user according to unit time to become a plurality segments of sub-electricity load data (Fig. 4-6, anomaly detection based on DNN and micro-moment analysis with reference to energy data and occupancy patterns. These visualization plots are derived using DRED dataset (for the case of a television): time-series energy consumption traces, and bottom) micro-moment detection scheme based on deep learning); and
comparing each of the segments of sub-electricity load data with the historical load data of the user to output a plurality of anomaly electricity consumption periods (Page 2, column 1, par. 2, page 12-14, column 1, section 3.1-3.2, requires comparing current consumption footprints with the past and ideal consumption cycles and not only using outlier detection algorithms, which can detect the anomalies at the sample level).
Elbsat and Himeur are analogous art. They relate to appliance power consumption analyzing.
Therefore, before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to modify, measure time series values of building variables, taught by Elbsat, incorporated with detect power consumption abnormalities, taught by Himeur, in order to optimal set of control actions to affect one or more of the building variables monitored by the BMS by operation of the building equipment.
Regarding claims 7 and 13, Himeur discloses defining the first electricity consumption behavior group as a high electricity consumption load and defining the second electricity consumption behavior group as a low electricity consumption load based on the historical load data (Fig. 1, page 12, column 2, par. 2-3, each appliance in Fig. 2, has different power consumption level, higher or lower than usual consumption footprints, as it is the case in other applications).
Regarding claims 9 and 15, Himeur discloses the first group of single classification models and the second group of single classification models are a one-class SVM (OCSVM) model and an isolation forest model, respectively (page 4, column 1, section U2, One-class classification: also named one-class learning (OCL) relies on considering initial power consumption patterns to be parts of two groups, positive (normal) and negative (abnormal), one-class support vector machine (OCSVM) and the energy consumption anomaly detection process performed using an isolated forest (iForest) model).
4.3 Claim(s) 10-11 and 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Elbsat et al. (US 20150316907 A1) in view of Himeur et al. (Artificial intelligence-based anomaly detection of energy consumption in buildings) further in view of Apaydin-Özkan (Appliance-Level Anomaly Detection by Using Control Charts and Artificial Neural Networks with Power Profile).
Regarding claims 10-11 and 17, the combination Elbsat and Himeur disclose the limitations of claims 6 and 12, but fail to disclose the limitation of claims 10-11 and 17. However, Apaydin-Özkan discloses the limitation of claims 10-11 and 17, as follow:
Regarding claims 10, Apaydin-Özkan discloses the integration layer network (Fig. 6) comprises an input layer, an output layer, and an expert weight layer connected between the input layer and the output layer, the first detection result and the second detection result are transmitted to the expert weight layer through the input layer, the expert weight layer generates a first product of the first detection result and its corresponding weight value, as well as a second product of the second detection result and its corresponding weight value, respectively, and the output layer integrates the first product and the second product and then outputs an anomaly electricity detection result (Fig. 6, page 9, section 4.2, ANNs are trained by using training data sets until a predefined terminating condition is met for the error. Then the accuracy and performance of the trained ANN can be estimated by testing the data set, The number of hidden layers and neurons in the layers may vary according to the problem studied. A typical feed-forward multilayered neural network, which consists of three layers such as an input layer (with n input nodes), one hidden layer (with m hidden nodes), and an output layer (with k output nodes), is given in Figure 6).
Regarding claims 11 and 17, Apaydin-Özkan discloses the integrated layer network is a backpropagation neural network. (Fig. 6, Page 9. Section 4.2, Backpropagation Algorithm (BPA) is used training algorithm for feed-forward multilayered ANNs. based on propagating the input in the forward direction and backpropagating the output in the backward direction by updating the weights correspondingly until a predefined terminating condition is met for the error).
Apaydin-Özkan, Elbsat and Himeur are analogous art. They relate to appliance power consumption analyzing.
Therefore, before the effective filing date of the claimed invention, it would have been obvious to a person of ordinary skill in the art to modify, measure time series values of building variables, taught by Apaydin-Özkan, incorporated with teaching of Elbsat and Himeur, as state above, in order to increase energy management, safety, and user comfort, that make human life easier.
Allowable Subject Matter
5. Claims 3-4, 8 and 14 would be allowable if rewritten to overcome the rejection(s) under 35 U.S.C. 101 set forth in this Office action and to include all of the limitations of the base claim and any intervening claims.
Citation Pertinent prior art
6. The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Dhurandhar - discloses a method for detecting anomalous energy usage of building or household entities. The method applies a number of successively stringent anomaly detection techniques to isolate households that are highly suspect for having engaged in electricity theft via meter tampering.
Zhang – discloses a Clustering Analysis of Electricity Consumption Behavior.
Yuin -discloses dynamic real-time abnormal energy consumption detection and energy effciency optimization analysis consideration uncertainty.
A reference to specific paragraphs, columns, pages, or figures in a cited prior art reference is not limited to preferred embodiments or any specific examples. It is well settled that a prior art reference, in its entirety, must be considered for allthat it expressly teaches and fairly suggests to one having ordinary skill in the art. Stated differently, a prior art disclosure reading on a limitation of Applicant's claim cannot be ignored on the ground that other embodiments disclosed wereinstead cited. Therefore, the Examiner's citation to a specific portion of a single prior art reference is not intended to exclusively dictate, but rather, to demonstrate an exemplary disclosure commensurate with the specific limitations being addressed. In re Heck, 699 F.2d 1331, 1332-33,216 USPQ 1038, 1039 (Fed. Cir. 1983) (quoting In re Lemelson, 397 F.2d 1006, 1 009, 158 USPQ 275, 277 (CCPA 1968)). In re: Upsher-Smith Labs. v. Pamlab, LLC, 412 F.3d 1319, 1323, 75 USPQ2d 1213, 1215 (Fed. Cir. 2005); In re Fritch, 972 F.2d 1260, 1264, 23 USPQ2d 1780, 1782 (Fed. Cir. 1992); Merck& Co. v. Biocraft Labs., Inc., 874 F.2d804, 807, 10 USPQ2d 1843, 1846 (Fed. Cir. 1989); In re Fracalossi, 681 F.2d 792,794 n.1, 215 USPQ 569, 570 n.1 (CCPA 1982); In re Lamberti, 545 F.2d 747, 750, 192 USPQ 278, 280 (CCPA 1976); In re Bozek, 416 F.2d 1385, 1390, 163USPQ 545, 549 (CCPA 1969).
Conclusion
7. Any inquiry concerning this communication or earlier communications from the examiner should be directed Kidest Worku whose telephone number is 571-272-3737. If attempts to reach the examiner by telephone are unsuccessful, the examiner's supervisor, Ali Mohammad can be reached on 571-272-4105. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Examiner interviews are available via telephone 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.
Information regarding the status of an application may be obtained from the Patent Application information Retrieval IPAIRI system. Status information for published applications may be obtained from either Private PMR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAG system, contact the Electronic Business Center (EBC) at 866-217- 9197.
/KIDEST WORKU/ Primary Examiner, Art Unit 2119
Prosecution Insights