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 .
This action is responsive to communication filed on 06/30/2022.
Claims 1-20 are pending.
Claim Objections
Claims 14-20 objected to because of the following informalities: the claims 14-20 recite “[t]he computer-readable medium” in the preamble of the claims, the claims should be amended to recite --The non-transitory, computer-readable medium-- to be consistent with the language of independent claim 13 and in order to avoid antecedent basis issues. Appropriate correction is required.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. A subject matter eligibility analysis is set forth below. See MPEP 2106.
Under Step 1 of the analysis, claim 1, belongs to a statutory category namely a system. Likely claims 5, belongs to a statutory category, namely it is a method and claim 13, belongs to a statutory category, namely it is a non-transitory computer-readable medium.
Under Step 2A, prong 1: This part of the eligibility analysis evaluates whether the claim recites a judicial exception. As explained in MPEP 2106.04, subsection II, a claim “recites” a judicial exception when the judicial exception is “set forth” or “described” in the claim.
The claim(s) 1, 5 and 13 recite(s) concepts related to mathematical algorithms/concepts, and mental processes and concepts performed in the human mind e.g. observation, evaluation, judgment, opinion for “determine home devices and how much power is consumed by each of the home devices”, “determine, based on time series data, a plurality of devices and an amount of power consumed by each device of the plurality of devices”; “generating, based on the time series data, a plurality of streams of time series data, each stream of the plurality of streams corresponding to a device of the plurality of devices that has used electricity during the time period;”, “identification of each device of the plurality of devices and an amount of power each device of the plurality of devices used during the time period” and mere data characterization which is part of the abstract idea (i.e. time series data corresponding to a time period of electricity consumption at a location, wherein the time series data indicates a quantity of electricity used during each interval of a plurality of intervals within the time period, wherein the time series data comprises weather information at the location for each interval of the plurality of intervals)” (claim 1); “identify, based on received time series data comprising electricity consumption patterns, devices and amounts of electricity consumed by the devices; generating …an identification of each device of the plurality of devices and an amount of power each device of the plurality of devices used during the time period” (claim 5); and “identify devices based on electricity consumption data; an identification of each device of the plurality of devices and an amount of power each device of the plurality of devices used during the time period; (claim 13). The concepts discussed above can be considered to describe mental processes, namely concepts performed in the human mind or with pen and paper, and/or mathematical concepts, namely a series of calculations leading to one or more numerical results or answers. Although, the claim does not spell out any particular equation or formula being used, the lack of specific equations for individual steps merely points out that the claim would monopolize all possible calculations in performing the steps. These steps recited by the claims, therefore amount to a series of mental or mathematical steps, making these limitations amount to an abstract idea.
Step 2A, prong 2 of the eligibility analysis evaluates whether the claim as a whole integrates the recited judicial exception(s) into a practical application of the exception. This evaluation is performed by (a) identifying whether there are any additional elements recited in the claim beyond the judicial exception, and (b) evaluating those additional elements individually and in combination to determine whether the claim as a whole integrates the exception into a practical application.
This judicial exception is not integrated into a practical application because the abstract idea is not performed by using any particular device and because the model implemented as a machine learning (claims 1, 5 and 13) which amounts to the implementation of the abstract idea on a generic computer also merely indicates a field of use or technological environment in which the judicial exception is performed, this type of limitation merely confines the use of the abstract idea to a particular technological environment (machine learning) and thus fails to add an inventive concept to the claims. See MPEP 2106.05(h); the “system for using machine learning and time series power consumption data” and “control circuitry that performs operations” and “user device” recited by claim 1, “user device” recited by claim 5, “one or mor processors” and “user device” recited by claim 13, amounts to the recitation of a general purpose computer used to apply the abstract idea; and because the recitation of “obtaining time series data corresponding to a time period of electricity consumption at a location, wherein the time series data indicates a quantity of electricity used during each interval of a plurality of intervals within the time period, wherein the time series data comprises weather information at the location for each interval of the plurality of intervals”, “receiving …an identification of each device of the plurality of devices and an amount of power each device of the plurality of devices used during the time period” (claim 1), “obtaining time series data corresponding to a time period of electricity consumption at a location” (claim 5); and “obtaining time series data corresponding to a time period of electricity consumption at a location” and “receiving, …an identification of each device of the plurality of devices and an amount of power each device of the plurality of devices used during the time period” (claim 13), is mere gathering recited at high level of generality and data characterization and the results of the algorithm are merely output/stored as part of insignificant post-solution activity (i.e. store a machine learning model, a non-transitory computer readable medium, output comprising an identification… sending…a notification [claims 1, 5, 13]) and are not used in any particular matter as to integrate the abstract idea in a practical application.
Under Step 2B, the claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements, as described above with respect to Step 2A Prong 2, merely amount to a general purpose computer (i.e. “system for using machine learning and time series power consumption data” and “control circuitry that performs operations” and “user device” recited by claim 1, “user device” recited by claim 5, “one or mor processors” and “user device” recited by claim 13), used to apply the abstract idea and mere data gathering/output recited at a high level of generality and insignificant extra-solution activity that when further analyzed under Step 2B is found to be well-understood, routine and conventional activities as evidenced by MPEP 2106.05(d)(II); and because the data of performing the algorithm must necessarily be “obtained” and the use of a general purpose computer to implement the abstract idea for performing the algorithm does not amount to significantly more than the recitation of the abstract idea itself.
Therefore, claims 1, 5 and 13 are rejected under 35 U.S.C. 101 as directed to an abstract idea without significantly more.
Dependent claims 2-4, 6-12, 14-20 merely expand on the abstract idea by appending additional steps to the mathematical algorithm on their respective independent claims 1, 5 and 13.
Dependent claims 2-14 merely expands on the abstract idea by reciting additional steps related to mathematical algorithms/concepts, and mental processes and concepts performed in the human mind e.g. observation, evaluation, judgment, opinion and mere characterization of the data acquired and applied for performing the abstract idea for “determining that a first stream of the plurality of streams of time series data corresponds to the first device; determining, based on an anomaly detection model, that the first stream comprises an anomaly” (claim 2); “comparing the output with previous data generated by the machine learning model, based on comparing the output with previous data generated by the machine learning model, determining that a second device is missing from the output” (claim 4); “determining a plurality of streams within the time series data” (claim 6); “determining that a subset of the plurality of streams of time series data corresponds to a first type of device; and based on determining that the subset corresponds to the first type of device, aggregating the output for each stream in the subset” (claim 7); “determining, based on a plurality of previous output of the machine learning model, that power consumption by the first device has increased over a threshold period of time” (claim 8); “determining that a first stream of the plurality of streams of time series data corresponds to the first device; determining, based on an anomaly detection model, that the first stream comprises an anomaly” (claim 9); “comparing the output with previous data generated by the machine learning model; based on comparing the output with previous data generated by the machine learning model, determining that a second device is missing from the output” (claim 11); “determining that the plurality of critical devices comprises the second device” (claim 12); “determining a plurality of streams within the time series data” (claim 14); “determining that a subset of the plurality of streams of time series data corresponds to a first type of device; and based on determining that the subset corresponds to the first type of device, aggregating the output for each stream in the subset” (claim 15); “determining, based on a plurality of previous output of the machine learning model, that power consumption by the first device has increased over a threshold period of time” (claim 16); “determining that a first stream of the plurality of streams of time series data corresponds to the first device; determining, based on an anomaly detection model, that the first stream comprises an anomaly” (claim 17); “comparing the output with previous data generated by the machine learning model; based on comparing the output with previous data generated by the machine learning model, determining that a second device is missing from the output” (claim 19); “determining that the plurality of critical devices comprises the second device” (claim 20).
This judicial exception is not integrated into a practical application in claims 2-4, 6-12, and 14-20 because the abstract idea is not performed by using any particular device and because the “system”, “control circuitry” recited in claims 2-4 amounts to the recitation of a general purpose computer used to apply the abstract idea; and because the model implemented as a machine learning (claims 3, 4, 8, 10-11, 13, 16, 18, and 19,) which amounts to the implementation of the abstract idea on a generic computer also merely indicates a field of use or technological environment in which the judicial exception is performed, this type of limitation merely confines the use of the abstract idea to a particular technological environment (machine learning) and thus fails to add an inventive concept to the claims. See MPEP 2106.05(h); and because the recitation of “receiving, from the machine learning model, second output indicating that a new device is consuming electricity at the location” (claims 3, 10 and 18), amounts to mere data gathering recited at a high level of generality, the limitations merely add further details as to the type of data, the means of collecting data being received/input/stored (non-transitory computer-readable medium) and used with the mental process and/or math concepts recited in the independent claims, also further calculations and math, so they are properly viewed as part of the recited abstract idea; and the results of the algorithm are merely output/stored as part of insignificant post-solution activity (claims 4, 6-8, 10-11, 14-16 and 18-19) and are not used in any particular matter as to integrate the abstract idea in a practical application.
The claim(s) claims 2-4, 6-12 and 14-20 does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the only additional elements are general purpose computer used to apply the abstract idea and mere data gathering/output recited at a high level of generality and insignificant extra-solution activity that when further analyzed under Step 2B is found to be well-understood, routine and conventional activities as evidenced by MPEP 2106.05(d)(II); and because the data of performing the algorithm must necessarily be “obtained” and the use of a general purpose computer to implement the abstract idea for performing the algorithm does not amount to significantly more than the recitation of the abstract idea itself.
Therefore claims 1-20 are rejected under 35 USC 101 as being directed to non-statutory subject matter.
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) 1, 5-8 and 13-16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Mimaroglu et al. US Patent 11,593,645 B2 (hereinafter Mimaroglu) in view of Vega et al. US2021/0125129A1 (hereinafter Vega).
Regarding claim 1, Mimaroglu discloses a system (see Figs. 1-2) for using machine learning and time series power consumption data to determine home devices and how much power is consumed by each of the home devices (see abstract, col. 2, ll. 32-47, wherein disaggregated target device energy usage data from within source location (i.e. a household) energy usage data over a period of time, to determine energy usage for one or more appliances, electric vehicles, and other devices that use energy at the source location is disclosed), the system comprising: storage circuitry configured to store a machine learning model (col. 1, ll. 36-50, wherein non-intrusive load monitoring using machine learning is disclosed and a trained convolutional neural network (CNN) can be stored; col. 7, ll. 12-20, wherein a processor including one or more general or specific purpose processors to perform computation and control functions of system 200 is disclosed and wherein processor 222 may execute computer programs and other applications stored within memory 214), wherein the machine learning model is trained to determine, based on time series data, a plurality of devices and an amount of power consumed by each device of the plurality of devices (see abstract; col. 7, ll. 36-51, wherein training data is disclosed; Figs. 7, and 10, col. 2, ll. 48-67, col. 3, ll. 10-29, col.3, ll. 64 through col. 4, ll. 3, wherein training a machine learning model to disaggregate energy usage associated with a target device over a period of time is disclosed); and
control circuitry (see Fig. 2, col. 7, ll. 12-21, wherein processor 222, may include one or more general or specific processors to perform computation and control functions of system 200) that performs operations comprising: obtaining time series data corresponding to a time period of electricity consumption at a location, wherein the time series data indicates a quantity of electricity used during each interval of a plurality of intervals within the time period (see col. 2, ll. 48-60; col. 12, ll. 54-67, col. 31, ll. 8-20, wherein usage data for a source location over a period of time is obtained), wherein the time series data comprises weather information at the location for each interval of the plurality of intervals (see Figs. 3 5A-5G; col. 8, ll. 28-53, col.12, ll. 19-53, wherein the training data can include information other than usage information e.g. weather at the time the energy usage was measured, such as precipitation, temperature or the like, wherein the data is obtained over a period of time for a source location);
generating, based on the time series data, a plurality of streams of time series data, each stream of the plurality of streams corresponding to a device of the plurality of devices that has used electricity during the time period (see Figs 5A-5G, wherein graphs that depict disaggregated energy usage data for a target device; see col. 11, ll. 45-67, col. 12, ll. 1-67, and wherein the overall source location energy usage data values depicted in Figs. 5a-5G can be combined with labeled energy usage data values for one or more devices and measurement, metering or some other technique for receiving/monitoring energy usage for specific devices can be implemented);
inputting the plurality of streams of time series data into the machine learning model (see col. 11, ll. 45-67, col. 12, ll.1-67, wherein prediction module is trained to disaggregate energy usage data within an overall source location energy usage data and input total energy usage at a source location and estimating usage for one or mor appliances electric vehicles and other devices that use energy at the source locations; see Figs. 5A-5G, wherein a graphical representation of total energy usage data, labeled energy usage data for a target device, and predicted usage data for the target device, e.g., predicted by a trained embodiment of prediction module 306, is depicted);
in response to inputting the plurality of streams of time series data into the machine learning model, receiving, from the machine learning model, output comprising an identification of each device of the plurality of devices and an amount of power each device of the plurality of devices used during the time period (see col. 11, ll. 45-67, col. 12, ll.1-67, wherein prediction module is trained to disaggregate energy usage data within an overall source location energy usage data and input total energy usage at a source location and estimating usage for one or mor appliances electric vehicles and other devices that use energy at the source locations; see Figs. 5A-5G, wherein a graphical representation of total energy usage data, labeled energy usage data for a target device, and predicted usage data for the target device, e.g., predicted by a trained embodiment of prediction module 306, is depicted and wherein Figs. 5A-5G can be combined with labeled energy usage data values for one or more devices and this resultant combination can be processed to arrive at training data, and wherein measurement, metering or some other technique for receiving/monitoring energy usage for specific devices within the source location can be implemented to generate the device specific labeled energy usage data for training; see col. 13, Table1, col. 14, Table 2, Tables 3-6, wherein data includes identifier, timestamp, total energy usage, and labeled device specific energy usage over time).
Mimaroglu further discloses an ensemble approach which can combine outputs from multiple trained model combining multiple deep learning models designed to solve disaggregation and detection/identification problems and that the results from disaggregating and detection/identification models can be combined in several ways e.g. the models can be combined into a final output based on multiple factors: thresholds, a distance between each model’s prediction output and the final output (see col. 5, ll. 20-53) and further teaches system 200 ma include memory for storing information and instructions for execution by processor and may contain various components for retrieving, presenting, modifying ad storing data and a display coupled to communication device to enable a user to interface with the system (col. 7, ll. 12-51; col. 8, ll. ) and wherein output data is disclosed (col. 8, l. 28-52).
However Mimaroglu do not expressly or explicitly discloses sending, to a user device, a notification indicating a quantity of power used by a first device of the plurality of devices.
Vega discloses sending, to a user device, a notification indicating a quantity of power used by a first device of the plurality of devices (see abstract, para. 0064, 0071-0072, 0201, 0222, , wherein a system for generating at least one utility fingerprint associated with at least one premises in which utility energy consumption information for energy devices associated with said premises and alerting to an end-user of variances in energy use is disclosed).
Therefore, it would have been obvious to one of ordinary skilled in the art before the effective filing date of the claimed invention to configure the system of Mimaroglu with the teachings of Vega for sending, to a user device, a notification indicating a quantity of power used by a first device of the plurality of devices for the benefit of providing a robust and enhanced system capable of alerting an user of variances in energy use by appliances/energy devices in a household/premises to more accurately monitor energy usage at a location over a period of time.
Regarding claim 5, Mimaroglu discloses a method comprising:
obtaining time series data corresponding to a time period of electricity consumption at a location (see col. 2, ll. 48-60; col. 12, ll. 54-67, col. 31, ll. 8-20, wherein usage data for a source location over a period of time is obtained);
inputting the time series data into a machine learning model, wherein the machine learning model has been trained to identify, based on received time series data comprising electricity consumption patterns, devices and amounts of electricity consumed by the devices (col. 1, ll. 36-50, wherein non-intrusive load monitoring using machine learning is disclosed and a trained convolutional neural network (CNN) can be stored; col. 7, ll. 12-20, wherein a processor including one or more general or specific purpose processors to perform computation and control functions of system 200 is disclosed and wherein processor 222 may execute computer programs and other applications stored within memory 214; see abstract; col. 7, ll. 36-51, wherein training data is disclosed; Figs. 7, and 10, col. 2, ll. 48-67, col. 3, ll. 10-29, col.3, ll. 64 through col. 4, ll. 3,; see col. 11, ll. 45-67, col. 12, ll.1-67, wherein prediction module is trained to disaggregate energy usage data within an overall source location energy usage data associated with a target device over a period of time and input total energy usage at a source location and estimating usage for one or mor appliances electric vehicles and other devices that use energy at the source locations; see Figs. 5A-5G, wherein a graphical representation of total energy usage data, labeled energy usage data for a target device, and predicted usage data for the target device, e.g., predicted by a trained embodiment of prediction module 306, is depicted);
in response to inputting the time series data into the machine learning model, generating, via the machine learning model, output comprising an identification of each device of the plurality of devices and an amount of power each device of the plurality of devices used during the time period (see col. 11, ll. 45-67, col. 12, ll.1-67, wherein prediction module is trained to disaggregate energy usage data within an overall source location energy usage data and input total energy usage at a source location and estimating usage for one or mor appliances electric vehicles and other devices that use energy at the source locations; see Figs. 5A-5G, wherein a graphical representation of total energy usage data, labeled energy usage data for a target device, and predicted usage data for the target device, e.g., predicted by a trained embodiment of prediction module 306, is depicted and wherein Figs. 5A-5G can be combined with labeled energy usage data values for one or more devices and this resultant combination can be processed to arrive at training data, and wherein measurement, metering or some other technique for receiving/monitoring energy usage for specific devices within the source location can be implemented to generate the device specific labeled energy usage data for training; see col. 13, Table1, col. 14, Table 2, Tables 3-6, wherein data includes identifier, timestamp, total energy usage, and labeled device specific energy usage over time).
Mimaroglu further discloses an ensemble approach which can combine outputs from multiple trained model combining multiple deep learning models designed to solve disaggregation and detection/identification problems and that the results from disaggregating and detection/identification models can be combined in several ways e.g. the models can be combined into a final output based on multiple factors: thresholds, a distance between each model’s prediction output and the final output (see col. 5, ll. 20-53) and further teaches system 200 ma include memory for storing information and instructions for execution by processor and may contain various components for retrieving, presenting, modifying ad storing data and a display coupled to communication device to enable a user to interface with the system (col. 7, ll. 12-51; col. 8, ll. ) and wherein output data is disclosed (col. 8, l. 28-52).
However Mimaroglu do not expressly or explicitly discloses sending, to a user device, a notification indicating a quantity of power used by a first device of the plurality of devices.
Vega discloses sending, to a user device, a notification indicating a quantity of power used by a first device of the plurality of devices (see abstract, para. 0064, 0071-0072, 0201, 0222, , wherein a system for generating at least one utility fingerprint associated with at least one premises in which utility energy consumption information for energy devices associated with said premises and alerting to an end-user of variances in energy use is disclosed).
Therefore, it would have been obvious to one of ordinary skilled in the art before the effective filing date of the claimed invention to configure the system of Mimaroglu with the teachings of Vega for sending, to a user device, a notification indicating a quantity of power used by a first device of the plurality of devices for the benefit of providing a robust and enhanced system capable of alerting an user of variances in energy use by appliances/energy devices in a household/premises to more accurately monitor energy usage at a location over a period of time.
Regarding claim 6, the combination of Mimaroglu and Vega discloses the materials as discussed above with respect to claim 5. Mimaroglu further discloses,
determining a plurality of streams within the time series data period (see Figs 5A-5G, wherein graphs that depict disaggregated energy usage data for a target device; see col. 11, ll. 45-67, col. 12, ll. 1-67, and wherein the overall source location energy usage data values depicted in Figs. 5a-5G can be combined with labeled energy usage data values for one or more devices and measurement, metering or some other technique for receiving/monitoring energy usage for specific devices can be implemented); and
generating, based on the plurality of streams, the output (see col. 11, ll. 45-67, col. 12, ll.1-67, wherein prediction module is trained to disaggregate energy usage data within an overall source location energy usage data and input total energy usage at a source location and estimating usage for one or mor appliances electric vehicles and other devices that use energy at the source locations; see Figs. 5A-5G, wherein a graphical representation of total energy usage data, labeled energy usage data for a target device, and predicted usage data for the target device, e.g., predicted by a trained embodiment of prediction module 306, is depicted and wherein Figs. 5A-5G can be combined with labeled energy usage data values for one or more devices and this resultant combination can be processed to arrive at training data, and wherein measurement, metering or some other technique for receiving/monitoring energy usage for specific devices within the source location can be implemented to generate the device specific labeled energy usage data for training; see col. 13, Table1, col. 14, Table 2, Tables 3-6, wherein data includes identifier, timestamp, total energy usage, and labeled device specific energy usage over time).
Regarding claim 7, the combination of Mimaroglu and Vega discloses the materials discussed above. Mimaroglu further discloses determining that a subset of the plurality of streams of time series data corresponds to a first type of device (see Table 1, col. 14, ll. 44-50, wherein a subset of series data corresponding to a type of device and an aggregation of data is disclosed); and based on determining that the subset corresponds to the first type of device, aggregating the output for each stream in the subset (see Table 1, col. 14, ll. 44-50, wherein a subset of series data corresponding to a type of device and an aggregation of data is shown for each stream in the subset for each type of device, wherein the aggregating the output resides in the total shown; see Fig. 6, “output”; col. 8, ll. 27-52; col. 20, ll. 4-43).
Regarding claim 8, the combination of Mimaroglu and Vega discloses the materials discussed above.
However Mimaroglu is silent as disclosing : determining, based on a plurality of previous output of the machine learning model, that power consumption by the first device has increased over a threshold period of time; and in response to determining that power consumption by the first device has increased over a threshold period of time, sending an indication that power consumption by the first device has increased to the user device.
Vega discloses determining, based on a plurality of previous output of the machine learning model, that power consumption by the first device has increased over a threshold period of time (see para. 0064, 0071-0072, 0222, wherein variants in energy use of said energy devices based on one or more selected set points, excessive usage and unintentional usage at premises are disclosed; see para. 0097, wherein utility consumption variation based on comparing first utility consumption information and second utility consumption information is disclosed; see para. 0098, wherein first utility consumption information may include a baseline utility consumption information; see para. 0099, wherein the first time period may include duration of 12 months or any other duration sufficient for capturing all periodic variations, e.g. seasonal variations with regards to environmental conditions, behavioral variations etc.) and in response to determining that power consumption by the first device has increased over a threshold period of time, sending an indication that power consumption by the first device has increased to the user device (see para. 0064, 0222, 0307-0328, wherein displaying and alerting an end-user of variances in energy use based on one or more selected set points, excessive usage and unintentional usage is disclosed).
Therefore, it would have been obvious to one of ordinary skilled in the art before the effective filing date of the claimed invention to modify the system of Mimaroglu with the teachings of Vega to determining, based on a plurality of previous output of the machine learning model, that power consumption by the first device has increased over a threshold period of time; and in response to determining that power consumption by the first device has increased over a threshold period of time, sending an indication that power consumption by the first device has increased to the user device for the benefit of providing an enhanced and robust energy monitoring system capable of detecting consumption variations capable of alerting an user of variances in energy use by appliances/energy devices in a household/premises and to more accurately monitor energy usage at a location over a period of time.
Regarding claim 13, Mimaroglu discloses a non-transitory, computer-readable medium comprising instructions that when executed by one or more processors, causes operations (col. 1, ll. 36-50, wherein non-intrusive load monitoring using machine learning is disclosed and a trained convolutional neural network (CNN) can be stored; col. 7, ll. 12-20, wherein a processor including one or more general or specific purpose processors to perform computation and control functions of system 200 is disclosed and wherein processor 222 may execute computer programs and other applications stored within memory 214) comprising:
obtaining time series data corresponding to a time period of electricity consumption at a location (see col. 2, ll. 48-60; col. 12, ll. 54-67, col. 31, ll. 8-20, wherein usage data for a source location over a period of time is obtained);
inputting the time series data into a machine learning model, wherein the machine learning model is trained to identify devices based on electricity consumption data (col. 1, ll. 36-50, wherein non-intrusive load monitoring using machine learning is disclosed and a trained convolutional neural network (CNN) can be stored; col. 7, ll. 12-20, wherein a processor including one or more general or specific purpose processors to perform computation and control functions of system 200 is disclosed and wherein processor 222 may execute computer programs and other applications stored within memory 214; see abstract; col. 7, ll. 36-51, wherein training data is disclosed; Figs. 7, and 10, col. 2, ll. 48-67, col. 3, ll. 10-29, col.3, ll. 64 through col. 4, ll. 3,; see col. 11, ll. 45-67, col. 12, ll.1-67, wherein prediction module is trained to disaggregate energy usage data within an overall source location energy usage data associated with a target device over a period of time and input total energy usage at a source location and estimating usage for one or mor appliances electric vehicles and other devices that use energy at the source locations; see Figs. 5A-5G, wherein a graphical representation of total energy usage data, labeled energy usage data for a target device, and predicted usage data for the target device, e.g., predicted by a trained embodiment of prediction module 306, is depicted);
in response to inputting the time series data into the machine learning model, receiving, from the machine learning model, output comprising an identification of each device of the plurality of devices and an amount of power each device of the plurality of devices used during the time period (see col. 11, ll. 45-67, col. 12, ll.1-67, wherein prediction module is trained to disaggregate energy usage data within an overall source location energy usage data and input total energy usage at a source location and estimating usage for one or mor appliances electric vehicles and other devices that use energy at the source locations; see Figs. 5A-5G, wherein a graphical representation of total energy usage data, labeled energy usage data for a target device, and predicted usage data for the target device, e.g., predicted by a trained embodiment of prediction module 306, is depicted and wherein Figs. 5A-5G can be combined with labeled energy usage data values for one or more devices and this resultant combination can be processed to arrive at training data, and wherein measurement, metering or some other technique for receiving/monitoring energy usage for specific devices within the source location can be implemented to generate the device specific labeled energy usage data for training; see col. 13, Table1, col. 14, Table 2, Tables 3-6, wherein data includes identifier, timestamp, total energy usage, and labeled device specific energy usage over time).
Mimaroglu further discloses an ensemble approach which can combine outputs from multiple trained model combining multiple deep learning models designed to solve disaggregation and detection/identification problems and that the results from disaggregating and detection/identification models can be combined in several ways e.g. the models can be combined into a final output based on multiple factors: thresholds, a distance between each model’s prediction output and the final output (see col. 5, ll. 20-53) and further teaches system 200 ma include memory for storing information and instructions for execution by processor and may contain various components for retrieving, presenting, modifying ad storing data and a display coupled to communication device to enable a user to interface with the system (col. 7, ll. 12-51; col. 8, ll. ) and wherein output data is disclosed (col. 8, l. 28-52).
However Mimaroglu do not expressly or explicitly discloses sending, to a user device, a notification indicating a quantity of power used by a first device of the plurality of devices.
Vega discloses sending, to a user device, a notification indicating a quantity of power used by a first device of the plurality of devices (see abstract, para. 0064, 0071-0072, 0201, 0222, , wherein a system for generating at least one utility fingerprint associated with at least one premises in which utility energy consumption information for energy devices associated with said premises and alerting to an end-user of variances in energy use is disclosed).
Therefore, it would have been obvious to one of ordinary skilled in the art before the effective filing date of the claimed invention to configure the system of Mimaroglu with the teachings of Vega for sending, to a user device, a notification indicating a quantity of power used by a first device of the plurality of devices for the benefit of providing a robust and enhanced system capable of alerting an user of variances in energy use by appliances/energy devices in a household/premises to more accurately monitor energy usage at a location over a period of time.
Regarding claim 14, the combination of Mimaroglu and Vega discloses the materials as discussed above with respect to claim 5. Mimaroglu further discloses,
determining a plurality of streams within the time series data period (see Figs 5A-5G, wherein graphs that depict disaggregated energy usage data for a target device; see col. 11, ll. 45-67, col. 12, ll. 1-67, and wherein the overall source location energy usage data values depicted in Figs. 5a-5G can be combined with labeled energy usage data values for one or more devices and measurement, metering or some other technique for receiving/monitoring energy usage for specific devices can be implemented); and
generating, based on the plurality of streams, the output (see col. 11, ll. 45-67, col. 12, ll.1-67, wherein prediction module is trained to disaggregate energy usage data within an overall source location energy usage data and input total energy usage at a source location and estimating usage for one or mor appliances electric vehicles and other devices that use energy at the source locations; see Figs. 5A-5G, wherein a graphical representation of total energy usage data, labeled energy usage data for a target device, and predicted usage data for the target device, e.g., predicted by a trained embodiment of prediction module 306, is depicted and wherein Figs. 5A-5G can be combined with labeled energy usage data values for one or more devices and this resultant combination can be processed to arrive at training data, and wherein measurement, metering or some other technique for receiving/monitoring energy usage for specific devices within the source location can be implemented to generate the device specific labeled energy usage data for training; see col. 13, Table1, col. 14, Table 2, Tables 3-6, wherein data includes identifier, timestamp, total energy usage, and labeled device specific energy usage over time).
Regarding claim 15, the combination of Mimaroglu and Vega discloses the materials discussed above. Mimaroglu further discloses determining that a subset of the plurality of streams of time series data corresponds to a first type of device (see Table 1, col. 14, ll. 44-50, wherein a subset of series data corresponding to a type of device and an aggregation of data is disclosed); and based on determining that the subset corresponds to the first type of device, aggregating the output for each stream in the subset (see Table 1, col. 14, ll. 44-50, wherein a subset of series data corresponding to a type of device and an aggregation of data is shown for each stream in the subset for each type of device, wherein the aggregating the output resides in the total shown; see Fig. 6, “output”; col. 8, ll. 27-52; col. 20, ll. 4-43).
Regarding claim 16, the combination of Mimaroglu and Vega discloses the materials discussed above.
However Mimaroglu is silent as disclosing : determining, based on a plurality of previous output of the machine learning model, that power consumption by the first device has increased over a threshold period of time; and in response to determining that power consumption by the first device has increased over a threshold period of time, sending an indication that power consumption by the first device has increased to the user device.
Vega discloses determining, based on a plurality of previous output of the machine learning model, that power consumption by the first device has increased over a threshold period of time (see para. 0064, 0071-0072, 0222, wherein variants in energy use of said energy devices based on one or more selected set points, excessive usage and unintentional usage at premises are disclosed; see para. 0097, wherein utility consumption variation based on comparing first utility consumption information and second utility consumption information is disclosed; see para. 0098, wherein first utility consumption information may include a baseline utility consumption information; see para. 0099, wherein the first time period may include duration of 12 months or any other duration sufficient for capturing all periodic variations, e.g. seasonal variations with regards to environmental conditions, behavioral variations etc.) and in response to determining that power consumption by the first device has increased over a threshold period of time, sending an indication that power consumption by the first device has increased to the user device (see para. 0064, 0222, 0307-0328, wherein displaying and alerting an end-user of variances in energy use based on one or more selected set points, excessive usage and unintentional usage is disclosed).
Therefore, it would have been obvious to one of ordinary skilled in the art before the effective filing date of the claimed invention to modify the system of Mimaroglu with the teachings of Vega to determining, based on a plurality of previous output of the machine learning model, that power consumption by the first device has increased over a threshold period of time; and in response to determining that power consumption by the first device has increased over a threshold period of time, sending an indication that power consumption by the first device has increased to the user device for the benefit of providing an enhanced and robust energy monitoring system capable of detecting consumption variations capable of alerting an user of variances in energy use by appliances/energy devices in a household/premises and to more accurately monitor energy usage at a location over a period of time.
Claim(s) 2-4, 9-12 and 17-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Mimaroglu et al. US Patent 11,593,645 B2 (hereinafter Mimaroglu) in view of Vega et al. US2021/0125129A1 (hereinafter Vega) in view of Norwood et al. US2016/0212506A1 (hereinafter Norwood).
Regarding claims 2, 9 and 17 , the combination of Mimaroglu discloses the materials discussed above with respect to respective claims 1, 5 and 13. Mimaroglu further discloses that the control circuitry is configured to perform operations further comprising: determining that a first stream of the plurality of streams of time series data corresponds to the first device (see Figs 5A-5G, wherein graphs that depict disaggregated energy usage data for a target device; see col. 11, ll. 45-67, col. 12, ll. 1-67, and wherein the overall source location energy usage data values depicted in Figs. 5a-5G can be combined with labeled energy usage data values for one or more devices and measurement, metering or some other technique for receiving/monitoring energy usage for specific devices can be implemented);
However Mimaroglu does not expressly or explicitly discloses:
determining, based on an anomaly detection model, that the first stream comprises an anomaly; and in response to determining that the first stream comprises an anomaly, sending, to the user device, a recommendation to repair the first device.
Vega further discloses determining, based on an anomaly detection model, that the first stream comprises an anomaly, and in response to determining that the first stream comprises an anomaly, sending, to the user device, a recommendation (see para. 0064, 0066, 0068, 0071-0072, 0193-0195, 0202, a clustering analytics by the use of Gaussian approach with the use of probability process method to help classify the data and to plot the results on actual energy usage data for a specific period of time for a specific premise and using statistical inferences for analysis, forecasting and other related use and wherein the Gaussian methods may be developed for the detection and identification in real or near-real time of outliers and anomalies and alerting and end-user of variances in energy use based on one or mor of selected points, excessive usage, and unintentional usage, prompting recommendations for available energy reduction choices and further discloses consumption analysis breakdown to determine electricity consumption by end-use appliances to assist in understanding the contribution of specific appliances usage to total electricity consumption for a given premises and may assist in assessing the performance of such appliances and in identifying replacement savings opportunities).
Therefore it would have been obvious to one of ordinary skilled in the art before the effective filing date of the claimed invention to given the teachings of Vega discussed above to configure the system of Mimaroglu to determining, based on an anomaly detection model, that the first stream comprises an anomaly and in response to determining that the first stream comprises an anomaly, sending, to the user device, a recommendation for the benefit of providing a robust and efficient system that would allow for efficient energy consumption analysis and to detect outliers and anomalies such excessive energy usage and unintentional usage providing the user with information assessing the performance of appliances and to aid in identifying replacement savings opportunities (para. 0202).
However, the combination of Mimaroglu and Vega do not expressly or explicitly discloses in response to determining that the first stream comprises an anomaly, sending, to the user device, a recommendation to repair the first device (emphasis added).
Norwood discloses in response to determining that the first stream comprises an anomaly, sending, to the user device, a recommendation to repair the first device (see abstract, para.0007, 0075, 0147, 0165-0166, 0171, 0181, 0227, 0237, wherein abnormal and excess power consumption of electrical devices and loads i.e. desk lamps and computer and wherein disaggregation, power consumption reporting, specific device and zone related notifications, recommendations are disclosed, and wherein the system provides recommendations for corrective action and/or for replacement or repair of specific devices using the electrical signatures and measurement power consumption by specific devices).
Therefore it would have been obvious to one of ordinary skilled in the art before the effective filing date of the claimed invention to configure the system of Mimaroglu as modified by Vega and Norwood to in response to determining that the first stream comprises an anomaly, sending, to the user device, a recommendation to repair the first device for the benefit of providing a robust and enhanced system by incorporating notifications that may help the user save money and to provide additional convenience or improve the safety of the building and residence (see para. 0164).
Regarding claim 3, 10, and 18 the combination of Mimaroglu, Vega and Norwood discloses the materials as discussed above. Mimaroglu further discloses that the control circuitry is configured to perform operations further comprising: in response to inputting the plurality of streams of time series data into the machine learning model, receiving, from the machine learning model, second output indicating that a device is consuming electricity at the location (see col. 11, ll. 45-67, col. 12, ll.1-67, wherein prediction module is trained to disaggregate energy usage data within an overall source location energy usage data and input total energy usage at a source location and estimating usage for one or more appliances electric vehicles and other devices that use energy at the source locations therefore it is implied that outputs for a plurality of energy using devices are produced; see Figs. 5A-5G, wherein a graphical representation of total energy usage data, labeled energy usage data for a target device, and predicted usage data for the target device, e.g., predicted by a trained embodiment of prediction module 306, is depicted and wherein Figs. 5A-5G can be combined with labeled energy usage data values for one or more devices and this resultant combination can be processed to arrive at training data, and wherein measurement, metering or some other technique for receiving/monitoring energy usage for specific devices within the source location can be implemented to generate the device specific labeled energy usage data for training; see col. 13, Table1, col. 14, Table 2, Tables 3-6, wherein data includes identifier, timestamp, total energy usage, and labeled device specific energy usage over time). Mimaroglu further discloses an ensemble approach which can combine outputs from multiple trained model combining multiple deep learning models designed to solve disaggregation and detection/identification problems and that the results from disaggregating and detection/identification models can be combined in several ways e.g. the models can be combined into a final output based on multiple factors: thresholds, a distance between each model’s prediction output and the final output (see col. 5, ll. 20-53) and further teaches system 200 ma include memory for storing information and instructions for execution by processor and may contain various components for retrieving, presenting, modifying ad storing data and a display coupled to communication device to enable a user to interface with the system (col. 7, ll. 12-51; col. 8, ll. ) and wherein output data is disclosed (col. 8, l. 28-52).
However Mimaroglu do not expressly or explicitly discloses receiving, from the machine learning model, second output indicating that a new device is consuming electricity at the location; and in response to receiving second output indicating that a new device is consuming electricity, sending a second notification to the user device.
Vega discloses sending, to a user device, a notification indicating a quantity of power used by a first device of the plurality of devices (see abstract, para. 0064, 0071-0072, 0201, 0222, , wherein a system for generating at least one utility fingerprint associated with at least one premises in which utility energy consumption information for energy devices associated with said premises and alerting to an end-user of variances in energy use is disclosed).
Therefore, it would have been obvious to one of ordinary skilled in the art before the effective filing date of the claimed invention to configure the system of Mimaroglu with the teachings of Vega for sending, to a user device, a notification indicating a quantity of power used by a first device of the plurality of devices for the benefit of providing a robust and enhanced system capable of alerting an user of variances in energy use by appliances/energy devices in a household/premises to more accurately monitor energy usage at a location over a period of time.
However Mimaroglu and Vega do not expressly or explicitly discloses receiving, second output indicating that a new device is consuming electricity at the location; and in response to receiving second output indicating that a new device is consuming electricity, sending a second notification to the user device.
Norwood discloses receiving, second output indicating that a new device is consuming electricity at the location (see para. 0160, wherein electrical power may be measured to detect the state of the specific devices in the residence and wherein the state may include whether a specific device is on or off, usage, and or power consumption of the specific electrical devices, wherein electrical signatures foe ach of the electrical device may be used to assess operation of the specific device, including determining when a given device is turned on or turned off, by identifying whether a given device is on it is essentially determining that a new device is consuming electricity at the location), and further discloses in response to receiving second output indicating that a new device is consuming electricity, sending a second notification to the user device (see Fig. 5, para. 0020, wherein a banner may show specific energy consumption details about which loads are on or off, see para. 0173, 0175, wherein notifications may be delivered as warning to the occupant based on the state i.e. on/off of many devices in the residence; para. 0189 and wherein a user may be presented with a graph in which each device is represented by a different color for ON and OFF transitions for a given device).
Therefore it would have been obvious to one of ordinary skilled in the art before the effective filing date of the claimed invention to configure the system of Mimaroglu as modified by Vega and Norwood to receiving, second output indicating that a new device is consuming electricity at the location; and in response to receiving second output indicating that a new device is consuming electricity, sending a second notification to the user device, for the benefit of providing a robust and enhanced system by incorporating notifications that may help the user save money and to provide additional convenience or improve the safety of the building and residence (see para. 0164).
Regarding claim 4, 11 and 19, the combination of Mimaroglu and Vega discloses the materials as applied above. Mimaroglu further teaches comparing the output with previous data generated by the machine learning model (col. 11, ll. 9-22, 45-67, col. 12, ll. 1-18, wherein predicted value can be compared to known value to generate an accuracy metric); based on comparing the output with previous data generated by the machine learning model, determining that a second device is missing from the output (col. 20, ll. 44-57, wherein training data which trains prediction module to generate detection prediction can include detected energy usage over a time span and the labeled device specific energy data within training data can represent whether energy beyond a threshold was used e.g. a binary value that represents ON or OFF).
Mimaroglu further teaches system 200 ma include memory for storing information and instructions for execution by processor and may contain various components for retrieving, presenting, modifying ad storing data and a display coupled to communication device to enable a user to interface with the system (col. 7, ll. 12-51; col. 8, ll. ) and wherein output data is disclosed (col. 8, l. 28-52).
However Mimaroglu do not expressly or explicitly discloses sending a second notification to the user device, wherein the second notification indicates that the second device is off.
Vega discloses sending, to a user device, a notification indicating a quantity of power used by a device of the plurality of devices (see abstract, para. 0064, 0071-0072, 0201, 0222, , wherein a system for generating at least one utility fingerprint associated with at least one premises in which utility energy consumption information for energy devices associated with said premises and alerting to an end-user of variances in energy use is disclosed).
Therefore, it would have been obvious to one of ordinary skilled in the art before the effective filing date of the claimed invention to configure the system of Mimaroglu with the teachings of Vega for sending, to a user device, a notification indicating a quantity of power used by a first device of the plurality of devices for the benefit of providing a robust and enhanced system capable of alerting an user of variances in energy use by appliances/energy devices in a household/premises to more accurately monitor energy usage at a location over a period of time.
However the combination of Mimaroglu and Vega do not expressly or explicitly discloses a second notification to the user device, wherein the second notification indicates that the second device is off.
Norwood discloses receiving, second output indicating that a new device is consuming electricity at the location (see para. 0160, wherein electrical power may be measured to detect the state of the specific devices in the residence and wherein the state may include whether a specific device is on or off, usage, and or power consumption of the specific electrical devices, wherein electrical signatures foe ach of the electrical device may be used to assess operation of the specific device, including determining when a given device is turned on or turned off, by identifying whether a given device is on it is essentially determining that a new device is consuming electricity at the location), and further discloses in response to determining that a second device is missing from the output, sending a second notification to the user device, wherein the second notification indicates that the second device is off.
(see Fig. 5, para. 0020, wherein a banner may show specific energy consumption details about which loads are on or off, see para. 0173, 0175, wherein notifications may be delivered as warning to the occupant based on the state i.e. on/off of many devices in the residence; para. 0189 and wherein a user may be presented with a graph in which each device is represented by a different color for ON and OFF transitions for a given device).
Therefore it would have been obvious to one of ordinary skilled in the art before the effective filing date of the claimed invention to configure the system of Mimaroglu as modified by Vega and Norwood for based on comparing the output with previous data generated by the machine learning model, determining that a second device is missing from the output; and in response to determining that a second device is missing from the output, sending a second notification to the user device, wherein the second notification indicates that the second device is off, for the benefit of providing a robust and enhanced system by incorporating notifications that may help the user save money and to provide additional convenience or improve the safety of the building and residence (see para. 0164).
Regarding claims 12 and 20, Mimaroglu and Vega discloses the materials discussed above. Mimaroglu further discloses receiving user input indicating a plurality of critical devices that consume electricity at the location (see col. 2, ll. 48-60, wherein machine learning model is trained using labeled energy usage data, which can be labeled with device specific energy usage, i.e. the household energy usage values can cover a period of time and within that period of time individual device energy usage values (e.g. appliance 1, electric vehicle, appliance 2 and the like) can be labeled, it is implied that the labels are user input data that has been used to train the machine learning model and that the labels correspond to critical devices i.e. AC, EV, Washer, Dryer, Refrigerator, see col. 6, ll. 6-18, Tables 1-6) ; determining that the plurality of critical devices comprises the second device (see abstract, wherein target device energy usage data is predicted ; col. 1, ll.37-47; col. 2, ll. 39-47; col. 5, ll. 66-67; col. 6, ll. 1-18; col. 11, ll. 9-22).
and further teaches system 200, include memory for storing information and instructions for execution by processor and may contain various components for retrieving, presenting, modifying ad storing data and a display coupled to communication device to enable a user to interface with the system (col. 7, ll. 12-51; col. 8, ll. ) and wherein output data is disclosed (col. 8, l. 28-52).
However Mimaroglu do not expressly or explicitly discloses in response to determining that the plurality of critical devices comprises the second device, sending the second notification.
Vega discloses sending, to a user device, a notification indicating a quantity of power used by a device/critical device of the plurality of devices (see abstract, para. 0064, 0071-0072, 0201, 0222, , wherein a system for generating at least one utility fingerprint associated with at least one premises in which utility energy consumption information for energy devices associated with said premises and alerting to an end-user of variances in energy use is disclosed).
Therefore, it would have been obvious to one of ordinary skilled in the art before the effective filing date of the claimed invention to configure the system of Mimaroglu with the teachings of Vega for sending, to a user device, a notification indicating a quantity of power used by a device/critical device of the plurality of devices for the benefit of providing a robust and enhanced system capable of alerting an user of variances in energy use by appliances/energy devices in a household/premises to more accurately monitor energy usage at a location over a period of time.
However Mimaroglu and Vega do not expressly or explicitly discloses and in response to determining that the plurality of critical devices comprises the second device, sending the second notification.
Norwood discloses receiving, second output indicating that a critical device consuming electricity at the location (see para. 0160, wherein electrical power may be measured to detect the state of the specific devices in the residence and wherein the state may include whether a specific device is on or off, usage, and or power consumption of the specific electrical devices, wherein electrical signatures foe ach of the electrical device may be used to assess operation of the specific device, including determining when a given device is turned on or turned off, by identifying whether a given device is on it is essentially determining that a critical device is consuming electricity at the location), and further teaches in response to determining that the plurality of critical devices comprises the second device, sending the second notification (see Fig. 5, para. 0020, wherein a banner may show specific energy consumption details about which loads are on or off, see para. 0173, 0175, wherein notifications may be delivered as warning to the occupant based on the state i.e. on/off of many devices in the residence; para. 0189 and wherein a user may be presented with a graph in which each device is represented by a different color for ON and OFF transitions for a given device).
Therefore it would have been obvious to one of ordinary skilled in the art before the effective filing date of the claimed invention to configure the system of Mimaroglu as modified by Vega and Norwood to and in response to determining that the plurality of critical devices comprises the second device, sending the second notification, for the benefit of providing a robust and enhanced system by incorporating notifications that may help the user save money and to provide additional convenience or improve the safety of the building and residence (see para. 0164).
Conclusion
The prior art made of record cited in form PTOL-892 and not relied upon is considered pertinent to applicant's disclosure.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to YARITZA H PEREZ BERMUDEZ whose telephone number is (571)270-1520. The examiner can normally be reached Monday-Friday.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Shelby A Turner can be reached at (571) 272-6334. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/YARITZA H. PEREZ BERMUDEZ/
Examiner
Art Unit 2857
/SHELBY A TURNER/Supervisory Patent Examiner, Art Unit 2857