DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitation(s) is/are:
Claim 15 recites the generic placeholder “computing device” followed by functional language without reciting sufficient structure to perform the function. Examiner looked into [0103] of the specification which recites the structure for the computing device such as the computing device comprises a processor and a memory device. Structure for memory device were found in [0029] and [0039] such as the memory device contains software programs executable by processor.
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Claim Rejections - 35 USC § 112
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 1-20 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.
Independent claims 1,8 and 15 recite the limitation, “associating temperature data with…” but there no definition of how the temperature data is obtained and what type of temperature data is used for association. It is not clear whether the temperature data is for EV charging or temperature data is related to weather data making the claim indefinite. Examiner looked into [0060] of the specification for temperature data definition. For the purpose of examination, Examiner interpreted temperature data to be ambient temperature data is view of [0060] of the specification.
Dependent claims 2-7, 9-14 and 16-20 depend from claims 1,8 and 15 inheriting each and every limitations of claims 1,8 and 15 and therefore rejected under 35 U.S.C. 112(b) for the reasons discussed above.
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.
Claim 1-5,7,8-12,14-19 rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter.
Step 1 for claim 1: The claim recites method which is a process and thus falls into one of the statutory categories of invention.
Step 2 Prong One for claim 1: Claim 1 recites, processing the input data over the time-range in the machine-learned model to generate output, wherein the output comprises a likelihood value of at least one EV charging event during the time-range. As evident from the background of the claimed limitation, the claim recites a process the input data and feed it to machine learning model to determine whether EV charging event took place for a period of time the data was collected. That is based on data analysis using mathematical formula, determine a value as an output or result of the mathematical computation which will indicate the occurrence of EV charging event over a period of time. Here machine learning model is used as a tool to perform calculation only not to make any control decisions to control anything physically as a solution to a problem. Furthermore the machine learning model is recited at high level of generality, without any details of complex mathematical computations. As such machine learning model is used only as an aid to perform mathematical computation. Thus this limitation recites a concept that falls into the “mathematical concept” group of abstract ideas. This limitation also falls into the “mental process” group of abstract ideas, because the recited mathematical calculation is simple enough that it can be practically performed in the human mind with the aid of calculator.
Step 2 Prong Two for claim 1: Beside the abstract idea, claim 1 recites the additional element, obtaining a time-series of electrical-consumption data of a service site over a time-range. The limitation recites a data gathering step of gathering electrical consumption data for a service site over a period of time. This additional element represents mere data gathering step that is necessary for use of the recited abstract idea. Claim 1 also recites additional element, converting the time-series of electrical-consumption data into a timeseries of consumption-change data. This is a mere data processing step of converting the gathered electrical consumption data over the period of time to consumption change data that is labelling data with exact consumption amount at the beginning and end of each timestep for the entire period of data collection. The mere data processing is a necessary step that is required to perform the above recited mathematical calculation. Claim 1 also recites, providing the input data over the time-range to a machine-learned model. This limitation recites to feed the processed data to the machine learning model/calculator to perform the necessary calculations for determining EV charging event. Machine learning model is used a tool to perform mathematical calculations only. The machine learning model is recited at high level of generality (no details of whatsoever provided other than just reciting machine learning model) that is represents no more than mere instructions to apply the judicial exception on a computer or calculator in this case. Claim 1 further recites, receiving output from the machine-learned model. This limitation recites to receive a value as an output from the above recited mathematical calculation which will indicate the EV charging event based on the gathered timeseries electrical consumption data. All the above recited steps as additional elements recite mere data gathering and data processing steps and amounts to extra-solution activity of receiving data (MPEP 2106.05(g): i.e. pre-solution activity of gathering data for use in the claimed process. Therefore even viewed together in combination, the recited additional elements do not integrate the recited judicial exception into a practical application and therefore claim 1 is directed to the judicial exception.
Step 2B for claim 1: The claim as a whole does not amounts to significantly more than the recited exception. The claim has five additional elements. The first additional element recites mere data gathering step followed by the second additional element that recites a mere data processing step followed by inputting the processed data to a computer/tool/calculator to perform the above recited mathematical calculation of the abstract idea. The fifth additional element recites to obtain a value from the mathematical calculation as an indication of EV charging event. Mere data gathering step and data processing step as explained previously are extra-solution activity and are considered as insignificant. Even though the fourth and fifth additional elements recite machine learning model, the machine learning model is used a tool only to perform mathematical calculation to perform data analysis. No specific details of machine learning model is provided or complex mathematical steps performed by the machine learning model is provided. These additional elements recite mere instructions to apply an exception on a computer/calculator because it amounts to no more than an idea of a solution or outcome and does not recite details of how a solution to a problem is accomplished; see MPEP 2106.05(f)(1) -“The recitation of claim limitations that attempt to cover any solution to an identified problem with no restriction on how the result is accomplished and no description of the mechanism for accomplishing the result, does not integrate a judicial exception into a practical application or provide significantly more because this type of recitation is equivalent to the words "apply it". Thus, when taken alone, the individual elements do not amount to significantly more than the above-identified judicial exception (the abstract idea). Looking at the limitations as an ordered combination represent mere instructions to apply an exception and
insignificant extra-solution activity, which do not provide an inventive concept. Therefore claim 1 is not eligible.
Claim 2 recites, wherein processing the input data over the time-range in the machine-learned model comprises: recognizing a change in consumption between two terms in the timeseries of consumption-change data, wherein the change in consumption is greater than a threshold value. This limitation recites an observation and evaluation step of observing a change in consumption in the timeseries consumption change data and evaluating where the consumption change is greater than a threshold value. Observation followed by evaluation can be performed in a human mind therefore the claim limitation falls into the “mental concept” group of abstract idea.
Claim 3 recites, wherein the machine-learned model comprises a convolutional neural network (CNN), and wherein processing the input data over the time-range in the CNN comprises: determining weights to associate with terms m the time-series of consumption-change data; and using the weights associated with a plurality of terms to derive the output from the CNN. The claim recites the type of machine learning model used to perform calculations only but nothing related how the machine learning model is physically altering or controlling any physical elements within the system or method as a solution to a problem. The type of machine learning model indicates the types of mathematical calculations performed and the weight adjustment indicates the step of adjusting parameters within the mathematical formulas used for the mathematical calculations. As such the claim falls into the “mathematical concept” of the abstract ideas and since the machine learning model is used as a tool to perform calculation only, it is viewed as mere instructions to apply the judicial exception on a computer or calculator.
Claim 4 recites, wherein the machine-learned model comprises a convolutional neural network (CNN), and wherein the CNN is trained on input comprising: labeled data based on EV charging events; and labeled data based on HVAC operational events. The claim recites a step adjusting the gathered data that is labelling which can be performed mentally with the aid of pen and paper. The next step is feed the data to the computer which is CNN as parameters to perform the necessary calculations. No details about training the CNN is mentioned that would integrate the recited judicial exception into practical application. The claim is recited about data labelling only. How the labelled data will be used by the machine learning model to control something physically is not mentioned. As such here the machine learning model is defined as a tool to perform calculations only. The tool could be viewed as a calculator or computer to perform mathematical calculations. A mere instruction to apply the gathered processed data into a computer/calculator (CNN training) cannot provide an inventive concept but rather recites an insignificant extra solution activity that is required to perform the recited mathematical calculations of the recited judicial exception. Therefore the claim 4 is still ineligible.
Claim 5 recites, additionally comprising: determining a change in temperature data coincident with terms in the time-series of consumption-change data indicating an increase in electricity consumption; and distinguishing the change in consumption from an EV charging event. The claim recites a combination of observation and evaluation of the gathered data followed by data processing of distinguishing certain data based on the result of data observation and evaluation against certain criteria. Thus the claimed limitation falls into the “mental concept” groupings of abstract idea and does not recite any additional elements that would integrate the recited judicial exception into practical application.
Claim 7 recites, wherein: the likelihood value comprises a value from 0.0 to 1.0; and the time-range is one week. The claim recites a range for numerical value of the mathematical calculation and time range for which data will be gathered. The claim does not recite any other additional elements that would integrate the recited judicial exception into practical application.
Independent claim 8 recites functional limitations similar to functional limitations recited in claim 1 and therefore not eligible for the reasons discussed above in claim 1. Claim 8 recites additional limitation, identifying load-changes within the time-range, wherein the load-changes are of a magnitude to indicate EV charging; and filtering the load-changes to remove load-changes coincident with temperature changes. This limitation recites a step of observing data that is identifying load changes indicating EV charging and evaluating data that is filtering that is removing certain data from the data set of the gathered data based on certain conditions. Therefore the limitation falls into the ”mental concept” groupings of abstract idea. Claim 8 recites other additional elements such as processor, memory device, subroutine which are recites at high level of generality such that they amount to no more than mere instructions to apply the exception using a generic component (MPEP 2106.05(f)).
Claims 9-12 and 14 recite functional limitations similar to functional limitations recited in claims 2-5 and 7 and therefore recites judicial exception without reciting any additional elements that would integrate the judicial exception into practical application as discussed above.
Independent claim 15 recites functional limitations similar to functional limitations recited in claim 1 and therefore not eligible for the reasons discussed above in claim 1. Claim 15 recites additional elements, one or more non-transitory computer-readable media and computing device which are recited at high level of generality such that they amount to no more than mere instructions to apply the exception using a generic component (MPEP 2106.05(f)).
Claims 16-20 recite functional limitations similar to functional limitations recited in claims 2-5 and therefore recites judicial exception without reciting any additional elements that would integrate the judicial exception into practical application as discussed above.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-4,6-7,15-18 and 20 are rejected under 35 U.S.C.103 as being unpatentable over Lu et al. (US 20200122598 A1) in view of Yan et al. (US 20210088563 A1).
For claim 1, Lu et al. teaches, a method of detecting electric vehicle (EV) charging (systems and methods for identifying electric charge events, [0014]), comprising:
obtaining a time-series of electrical-consumption data of a service site
over a time-range (obtaining time series electricity consumption data from a premise or location (service site) for a period of time, [0024], [0026] and [0040]);
converting the time-series of electrical-consumption data into a timeseries
of consumption-change data (by analyzing the electricity consumption data in conjunction to EV charging activity data over the period of time, consumption data related to EV charging event or consumption change can be determined for the obtained time series electricity consumption data, [0040], [0041], [0043],[0062] and see also [0044] reciting pre-processing raw KWh data particular magnitude and variance (consumption change) over a period of time);
providing the input data over the time-range to a machine-learned model (pre-processed data is fed into the machine learning model to determine EV charging event by analyzing the obtained and processed electricity consumption data, [0092] and [0093]);
processing the input data over the time-range in the machine-learned model to generate output, wherein the output comprises a likelihood value of at least one EV charging event during the time-range (the trained machine learning model analyze the processed electricity consumption data based on certain conditions of charging such as magnitude of the initial sharp jump in kWh when the suspected EV charge starts, a magnitude of the drop in kWh when the suspected EV charge ends, a duration of the suspected EV charge event, a standard deviation of kWh values during the suspected EV charge, a total kWh usage during the suspected EV charge, a maximum and/or minimum kWh value during the suspected EV charge. After analysis the trained machine learning model outputs a value indicating EV charging events, [0084] and [0092]-[0094], see also [0059]); and
receiving output from the machine-learned model (After analysis the trained machine learning model outputs a value indicating EV charging events, [0084] and [0092]-[0094], see also [0059]).
Lu et al. does not teach the details of associating temperature data with terms of the time-series of consumption-change data to thereby create input data over the time-range. However Lu et al. explicitly teaches to process the obtained raw electricity consumption data to obtain consumption change data.
Yan et a. teaches, associating temperature data with terms of the time-series of consumption-change data to thereby create input data over the time-range (time series data or power measurements from PMU are obtained followed by FTT transformation for consumption change data and weather data where the PMU is located is also obtained for a particular time window. That is associating temperature data (ambient temperature from weather data) with consumption change data [0023],[0053] and [0059]).
Lu et al. and Yan et al. are analogous art because that are from similar problem solving area of distinguishing between different power events based on analyzing electrical power consumption data.
Therefore it would have been obvious before the effective filing date of the claimed invention to a person of ordinary skill in the art to modify the system detecting EV charging event based on analyzing electrical consumption data and consumption change data by applying the known technique of associating ambient temperature data to consumption change data as taught by Yan et al. as an improvement to data processing of the electrical consumption data to yield predictable results for distinguishing between EV charging events and other events such as weather related HVAC usage as mentioned by Lu et al. in [0003].
Lu et al. teach:
[0024] House meter: This is an electronic device that records consumption of electric energy at a premise/location as electricity consumption data. The consumption amount is in kilowatts per hour (kWh) but other units may be used. The premise/location and thus the house meter are associated with a customer account. Although the term “house” is used for simplicity, it includes any type of premise that may have a meter. The house meter measures electric consumption for the entire premise which includes all appliances and components that draw electricity (including an EV if present). The measured data is typically collected in regular time intervals (e.g., 5 minute, 15 minute,
hour, etc.). A group of interval data is referred to as time series data. In one embodiment, the house meter is a smart meter that records consumption of electric energy and communicates the information via network communications to an electricity supplier (utility company) for monitoring and other purposes.
[0026] Account time series data: Data that represents the electric consumption in kWh units measured and collected from a house meter for an account under consideration as a whole over a period of time. The measured data is typically collected in time intervals. Fifteen (15) minute time intervals will be discussed herein but other intervals can be used (e.g., 5 minute, 30 minute, 1 hour, etc.).
[0042] Initially, the account time series data is analyzed without looking at the EV submeter data. To detect whether there is EV charging activity during the day from a known EV owner, the preprocessing module 120 analyzes the account time series data 110. As previously stated, the account time series data 110 shows house electricity usage (electricity consumption) in kWh from a known EV owner over a time period. The meter of a house records the electricity drawn and used by the entire house and thus includes the electricity used for EV charging, if any, combined with all other charges.
This is referred to herein as account time series data.
[0043] In one embodiment, the EV submeter data 215 is a second set of time series charging data that is also retrieved, which was collected from EV submeters. For example, each known EV owner also includes a respective EV submeter installed at their premise for directly monitoring the charging activity of the electric vehicle. The EV submeter is in addition to the house meter. As previously explained, the EV submeter records the electricity drawn only by the electric vehicle and thus includes charging data in time series of the electricity used for EV charging. This is referred to herein as
submeter time series data or EV submeter data. Thus by analyzing the submeter data, the system can easily identify the time intervals when an EV charge started and ended1. These time intervals are marked and become part of the generated answer key in block 225.
[0092] At 460, the machine learning classifier determines charge features from the suspected EV charge in a similar manner as the charge features previously discussed for block 260 of FIG. 2. For example, the kWh data collected in the account time series data that occurs before, during, and/or at the end of the suspected EV charge is read from memory or storage. One or more charge features are generated such as an average consumption of electricity during the suspected EV charge, a magnitude of the initial sharp jump in kWh when the suspected EV charge starts, a magnitude of the
drop in kWh when the suspected EV charge ends, a duration of the suspected EV charge event, a standard deviation of kWh values during the suspected EV charge, a total kWh usage during the suspected EV charge, a maximum and/or minimum kWh value during the suspected EV charge. Any combination of these charge features may be generated and they represent a charge characteristic (e.g., a signature) of the associated suspected EV charge.
[0094] This comparison may be performed for the other different types of charge features and a total score of matching results may be generated. The threshold amount of similarity of a match for each type of charge feature may be defined and set in the classifier algorithm. In one embodiment, the matching involves pattern matching using the learned observations from the known EV charge patterns/motifs and their corresponding charge features as learned from the process of FIG. 2.
[0084] In one embodiment, the system implements and uses a logistic classifier, and a decision-tree based algorithm (e.g., Support Vector Machine SVM) to identify EV charges. In the case of the logistic classifier, suspected EV events with an assigned probability of greater than 0.5 are classified as EV charges. Of course, other values may be used.
Yan et al. teach:
[0023] According to some embodiments, time-series data may be received from a collection of monitoring nodes (e.g., sensor, actuator, and/or controller nodes). Measurements of power, voltage, and frequency may be observed within a particular time window where various measurements are each associated with corresponding time stamps. Given a time window, such as five seconds or five minutes, depending on the particular application, for example, measurements of power, voltage, and/or frequency may be measured or otherwise observed for various nodes of a power system, such
as every node of the power system in some embodiments. For example, a measurement may be taken every second during a particular time window in some implementations. Various statistics may be determined for measurements throughout the time window, such as mean, median, standard deviation, kurtosis, skewness, mode, median, quartile, range, interquartile range, and/or variance, to name just a few examples among many.
[0059] FIG. 3 illustrates an embodiment 300 a system diagram of a signature identification system 310 and corresponding inputs 305 and output 315 according to an embodiment. As illustrated, various inputs may include PMU data (30-60 Hz), SCADA data (e.g., at 2-4 seconds), weather data2, DGA data, and PD monitor data, for example. PMU data may include three phase current magnitude, three phase current phase angle, three phase voltage magnitude, three phase voltage phase angle,
frequency, and frequency delta, for example. SCADA data may include voltage magnitude, current magnitude, transformer (Xfmr) tap position, digital inputs (e.g., circuit breaker (CB) status), and digital outputs (e.g., trips/alarms), for example.
Regarding claim 2 combination of Lu et al. and Yan et al. teach the method of claim 1. In addition Lu et al. teaches, wherein processing the input data over the
time-range in the machine-learned model (machine learning model reading collected timeseries kWh data, [0092]) comprises:
recognizing a change in consumption between two terms in the timeseries
of consumption-change data, wherein the change in consumption is greater
than a threshold value (the trained machine learning model can identify the start and stop time for EV charging event (change in consumption between two terms) by analyzing the collected kWh data and comparing it with known EV charge event features (such as kWh level remains at that high level for a sustained period of time and then drops thus the subsequent term in timeseries data will be much less than previous kWh data). Then the identified/suspected EV charge event is compared to a set threshold as a confirmation for EV charge event, [0063],[0064] and [0093]).
Regarding claim 3 combination of Lu et al. and Yan et al. teach the method of claim 1. In addition Yan et al. teaches, wherein the machine-learned model comprises a convolutional neural network (CNN) (neural network model used by machine learning model to differentiate between different power signatures, [0021], [0053], [0054]), and wherein processing the input data over the time-range in the CNN (machine learning technique or model uses real time power data to identify various power signatures, [0021]) comprises.
In addition Lu et al. teaches, determining weights to associate with terms m the time-series of consumption-change data (“…Each kWh value in each time interval is encoded with one of the encoded letters3 based on the usage level as discussed. A resulting encoding string 325 for the series of time intervals of the account data 300 is shown below the graph of FIG. 3. Each encoded letter of the encoded string 325 is positioned in an approximate alignment below its corresponding kWh value and time interval…”, [0048] and [0050]); and
using the weights associated with a plurality of terms to derive the output
from the CNN (the system using machine learning model looks into the encoded letters for high usage in the consecutive occurrences of the timeseries power consumption data to identify a suspected EV charging event, [0057]-[0059] and [0092]).
Regarding claim 4 combination of Lu et al. and Yan et al. teach the method of claim 1. In addition Yan et al. teaches, wherein the machine-learned model comprises a convolutional neural network (CNN) (neural network model used by machine learning model to differentiate between different power signatures, [0021], [0053], [0054]), and wherein the CNN (neural network in view of Yan et al.) is trained on input comprising (machine learning technique or model is trained with defined (labelled) signatures of different power events, [0025] and [0026]).
In addition Lu et al teaches, labeled data based on EV charging events (the machine learning classifier is trained with EV charging patterns that is labelling EV data, [0033], [0102] and [0103]); and
labeled data based on HVAC operational events (the machine learning classifier is also trained with non EV charging patterns which can include load for weather related HVAC usage, [0003], [0102] and [0103]).
Regarding claim 6 combination of Lu et al. and Yan et al. teach the method of claim 1. In addition Lu et al. teaches, additionally comprising, responsive to
detection of an EV charging event performing at least one of:
changing a transformer used by the service site (based on identified EV charging events, corrective actions can be taken by rerouting power flow from a different transformer, replacing or resizing the transformer for higher capacity, [0016] and [0099]);
changing a number of service sites served by the transformer (based on identified EV charging events, corrective actions can be taken by rerouting power flow from a different transformer, replacing or resizing the transformer for higher capacity, [0016] and [0099]); or
changing a phase of electricity provided to the transformer.
Regarding claim 7 combination of Lu et al. and Yan et al. teach the method of claim 1. In addition Lu et al. teaches, wherein:
the likelihood value comprises a value from 0.0 to 1.0 (if the assigned probability of a suspected EV charging event is greater than 0.5, than the suspected EV charging event is an actual EV charging event. That is the probability of suspected EV charging event is between 0-1, [0084]); and
the time-range is one week (data is collected for 30 days. To a person of ordinary skill in the art any range of time intervals can be selected based on system needs. Also there is no teaching on the reference that data can only be collected for 30 days not for any other time period. [0040] and [0042]).
Regarding claim 15, combination of Lu et al. and Yan et al. teach the claimed method of detecting EV charging. Together they teach the computing device (computing device as taught in [0109] and [0110] of Lu et al.) performing the functional limitations of detecting EV charging and therefore rejected for the reasons discussed above in claim 1. Claim 15 has additional limitation taught by Lu et al. that is, one or more non-transitory computer-readable media storing computer-executable instructions that, when executed by one or more processors (EV detection system and the computer is means structure hardware, non-transitory computer readable medium performing computer executable instructions by processor ([0111] and [0112], Lu et al.).
Claims 16-18 and 20 recite functional limitations similar to claims 2-4 and 6. Therefore combination of Lu et al. and Yan et al. teach the claims 16-18 and 20 and therefore rejected under 35 U.S.C.103 for the reasons discussed above in claims 2-4 and 6.
Claim(s) 5 and 19 are rejected under 35 U.S.C.103 as being unpatentable over Lu et al. (US 20200122598 A1) in view of Yan et al. (US 20210088563 A1) in further view of Franklin et al. (US 20190295190 A1).
Regarding claim 5, combination of Lu et al. and Yan et al. teach the method of claim 1. In addition Lu et al. teaches, distinguishing the change in consumption from an EV charging event (“…The charge features will help the system learn what an EV charge looks like and what an EV charge does not look like so that an EV charge can be distinguished...”, [0066] from other non EV charging events, [0023]).
Neither in combination nor individually Lu et al. and Yan et al. teach the details of determining a change in temperature data coincident with terms in the time-series of consumption-change data indicating an increase in electricity consumption. However both Lu et al. and Yan et al. look at different power usage data to identify specific power events such as EV charging.
Franklin et al. teaches, determining a change in temperature data coincident with terms in the time-series of consumption-change data indicating an increase in electricity consumption (an inferential model learns multiple loadshapes (consumption change data) to identify events for fluctuation in power consumption due to variation in real-time weather, vehicle charging and other events. Real time weather affects the ambient temperature thus causes change in electrical consumption or loadshapes that is temperature data coincident with consumption change data indicating variation that is indicating increase in electricity consumption, [0031] and [0013]).
Franklin et al. is an analogous art in combination with Lu et al. and Yan et al. because is from similar problem solving area that is analyzing electrical consumption data to predict or identify power events based on electrical power usage data analysis.
Therefore it would have been obvious before the effective filing date of the claimed invention to a person of ordinary skill in the art to modify the method of detecting Ev charging events by distinguishing the change in consumption from an EV charging event as taught by Lu et al. and Yan et al. by applying the known technique of determining change in temperature data such as change in ambient temperature due to change in weather and thus detecting variation in electrical consumption as taught by Franklin et al. as an improvement to the method of detecting EV charging event to yield predictable results for distinguishing between EV charging events and other power usage events caused by change in temperature.
Regarding claim 19, combination of Lu et al. and Yan et al. teach the one or more computer-readable media of claim 15. In addition Lu et al. teaches, distinguishing the change in consumption from an EV charging event (“…The charge features will help the system learn what an EV charge looks like and what an EV charge does not look like4 so that an EV charge can be distinguished...”, [0066] from other non EV charging events, [0023]).
Neither in combination nor individually Lu et al. and Yan et al. teach the details of determining a change in temperature data coincident with terms in the time-series of consumption-change data indicating an increase in electricity consumption. However both Lu et al. and Yan et al. look at different power usage data to identify specific power events such as EV charging.
Franklin et al. teaches, determining a change in temperature data coincident with terms in the time-series of consumption-change data indicating an increase in electricity consumption (an inferential model learns multiple loadshapes (consumption change data) to identify events for fluctuation in power consumption due to variation in real-time weather, vehicle charging and other events. Real time weather affects the ambient temperature thus causes change in electrical consumption or loadshapes that is temperature data coincident with consumption change data indicating variation that is indicating increase in electricity consumption, [0031] and [0013]).
Franklin et al. is an analogous art in combination with Lu et al. and Yan et al. because is from similar problem solving area that is analyzing electrical consumption data to predict or identify power events based on electrical power usage data analysis.
Therefore it would have been obvious before the effective filing date of the claimed invention to a person of ordinary skill in the art to modify the method of detecting Ev charging events by distinguishing the change in consumption from an EV charging event as taught by Lu et al. and Yan et al. by applying the known technique of determining change in temperature data such as change in ambient temperature due to change in weather and thus detecting variation in electrical consumption as taught by Franklin et al. as an improvement to the method of detecting EV charging event to yield predictable results for distinguishing between EV charging events and other power usage events caused by change in temperature.
Claim(s) 8-14 are rejected under 35 U.S.C.103 as being unpatentable over Lu et al. (US 20200122598 A1) in view of Yan et al. (US 20210088563 A1) in further view of Linchieh et al. (US 20240146060 A1).
Regarding claim 8 Lu et al. teaches, a computing device to detect electric vehicle (EV) charging events (computing device including a hardware processor and a memory, [0109] and [0110]), wherein the computing device comprises:
a processor (hardware processor 510, [0110]); and
a memory device (memory 515, [0110]), in communication with the processor (memory in communication with processor, [0109] and [0110]), wherein the memory device comprises statements executed by the processor to perform actions (computer including memory and processor execute instructions, firmware and or combinations, [0109]-[0111]) comprising:
obtaining a time-series of electrical-consumption data of a service
site over a time-range (obtaining time series electricity consumption data from a premise or location (service site) for a period of time, [0024], [0026] and [0040]);
converting the time-series of electrical-consumption data into a
time-series of consumption-change data (by analyzing the electricity consumption data in conjunction to EV charging activity data over the period of time, consumption data related to EV charging event or consumption change can be determined for the obtained time series electricity consumption data, [0040], [0041], [0043],[0062] and see also [0044] reciting pre-processing raw KWh data particular magnitude and variance (consumption change) over a period of time);
providing the input data over the time-range to a subroutine configured to detect EV charging incidents (pre-processed data is fed into the machine learning model to determine EV charging event by analyzing the obtained and processed electricity consumption data, [0092] and [0093]), wherein the subroutine performs actions comprising:
identifying load-changes within the time-range, wherein the load-changes are of a magnitude to indicate EV charging (the trained machine learning model analyze the processed electricity consumption data based on certain conditions of charging such as magnitude of the initial sharp jump in kWh when the suspected EV charge starts, a magnitude of the drop in kWh when the suspected EV charge ends, a duration of the suspected EV charge event, a standard deviation of kWh values during the suspected EV charge, a total kWh usage during the suspected EV charge, a maximum and/or minimum kWh value during the suspected EV charge. After analysis the trained machine learning model outputs a value indicating EV charging events, [0084] and [0092]-[0094], see also [0059]); and
responsive to the subroutine recognizing one or more possible EV
charging incidents (“…The match may be based on comparing corresponding types of
charge features and determining if the values match to a certain degree (e.g., to a set threshold amount). For example, the classifier determines whether the average consumption of electricity that was used during the suspected EV charge matches the average consumption of electricity that was used during a known EV charge event from a matching EV charge pattern/motif…”, [0093]), determining a likelihood of at least one EV charging event during the time-range based at least in part on the one or more possible EV charging events (Suspected EV charge events with an assigned probability greater than 0.5 is classified as EV charges [0084] and [0092]-[0094], see also [0059]).
Lu et al. does not teach the details of associating temperature data with terms of the time-series of consumption-change data to thereby create input data over the time-range and filtering the load-changes to remove load-changes coincident with temperature changes. Lu et al. teaches to distinguish between EV charging events and non- EV charging events which could be related to HVAC usage as mentioned in [0003]. But Lu et al. does not remove any load changes data but rather keeps and processes all the load changes data and encode them to identify which load change data is for EV charging and which load change is non EV charging event as taught in [0042] and [0066].
Yan et al. teaches, associating temperature data with terms of the time-series of consumption-change data to thereby create input data over the time-range (time series data or power measurements from PMU are obtained followed by FTT transformation for consumption change data and weather data where the PMU is located is also obtained for a particular time window. That is associating temperature data (ambient temperature from weather data) with consumption change data [0023],[0053] and [0059]).
Lu et al. and Yan et al. are analogous art because that are from similar problem solving area of distinguishing between different power events based on analyzing electrical power consumption data.
Therefore it would have been obvious before the effective filing date of the claimed invention to a person of ordinary skill in the art to modify the system detecting EV charging event based on analyzing electrical consumption data and consumption change data by applying the known technique of associating ambient temperature data to consumption change data as taught by Yan et al. as an improvement to data processing of the electrical consumption data to yield predictable results for distinguishing between EV charging events and other events such as weather related HVAC usage as mentioned by Lu et al. in [0003].
Neither in combination nor individually Lu et al. and Yan et al. teach the details of filtering the load-changes to remove load-changes coincident with temperature changes.
Linchieh et al. teaches, filtering the load-changes to remove load-changes
coincident with temperature changes (data from multiple sources are collected as taught in [0091] and [0093]. Sources include grid data, historical, real time and predicted weather data, and others as taught in [0093]). The collected data is preprocessed to remove outliers which can include excessive variation in power usage due to seasonal trends and many other factors as taught in [0169] and feed the processed data to the predictor to predict load usage in near real time, [0085] and [0086]).
Linchieh et al. is an analogous art because it is in the similar problem solving area which is analyzing collected electrical consumption data to determine or predict EV charging events and other power consumption events.
Therefore it would have been obvious before the effective filing date of the claimed invention to a person of ordinary skill in the art to modify the load changes within the time range as taught by combination Lu et al. and Yan et al. by applying the known technique of removing outlier data such as variation in usage due to seasonal or weather pattern (that is change in temperature) during data preprocessing as taught by Liechieh et al. as an improvement to load-changes data to yield predictable results for determining particular power events which will help to optimizing energy usage to minimize overall peak demand for the power grid as taught by Liechieh et al. in [0109].
Regarding claim 9 combination of Lu et al., Yan et al. and Liechieh et al. teach the computing device of claim 8. In addition Lu et al. teaches, wherein identifying load-changes within the time-range by the subroutine comprises:
recognizing a change in consumption between two terms in the timeseries
of consumption-change data (the trained machine learning model can identify the start and stop time for EV charging event (change in consumption between two terms) by analyzing the collected kWh data and comparing it with known EV charge event features (such as kWh level remains at that high level for a sustained period of time and then drops thus the subsequent term in timeseries data will be much less than previous kWh data). Then the identified/suspected EV charge event is compared to a set threshold as a confirmation for EV charge event, [0063],[0064] and [0093]), wherein the change in consumption is 3 kWh or more (consumption change data between 0-3 or 0-10 KWh, [0050]).
Regarding claim 10 combination of Lu et al., Yan et al. and Liechieh et al. teach the computing device of claim 8. In addition Yan et al. teaches, wherein the subroutine comprises a convolutional neural network (CNN) (neural network model used by machine learning model to differentiate between different power signatures, [0021], [0053], [0054]), and wherein the subroutine performs additional actions comprising.
In addition Lu et al. teaches, determining weights to associate with terms m the time-series of consumption-change data (“…Each kWh value in each time interval is encoded with one of the encoded letters5 based on the usage level as discussed. A resulting encoding string 325 for the series of time intervals of the account data 300 is shown below the graph of FIG. 3. Each encoded letter of the encoded string 325 is positioned in an approximate alignment below its corresponding kWh value and time interval…”, [0048] and [0050]); and
using the weights associated with a plurality of terms to derive an output
from the CNN (the system using machine learning model looks into the encoded letters for high usage in the consecutive occurrences of the timeseries power consumption data to identify a suspected EV charging event, [0057]-[0059] and [0092]).
Regarding claim 11 combination of Lu et al., Yan et al. and Liechieh et al. teach the computing device of claim 8. In addition Yan et al. teaches, wherein the subroutine comprises a convolutional neural network (CNN) (neural network model used by machine learning model to differentiate between different power signatures, [0021], [0053], [0054]), and wherein the CNN is trained on input comprising (machine learning technique or model is trained with defined (labelled) signatures of different power events, [0025] and [0026]).
In addition Lu et al teaches, labeled data based on EV charging events (the machine learning classifier is trained with EV charging patterns that is labelling EV data, [0033], [0102] and [0103]); and
labeled data based on HVAC operational events (the machine learning classifier is also trained with non EV charging patterns which can include load for weather related HVAC usage, [0003], [0102] and [0103]).
Regarding claim 12 combination of Lu et al., Yan et al. and Liechieh et al. teach the computing device of claim 8. In addition Liechieh et al. teaches, determining a change in temperature data coincident with terms in the time-series of consumption-change data indicating an increase in electricity consumption (seasonal trend data will show change in usage due change in temperature due to change in seasonal weather trend, [0093] and [0169]).
In addition Lu et al. teaches, distinguishing the change in consumption from an EV charging event (“…The charge features will help the system learn what an EV charge looks like and what an EV charge does not look like so that an EV charge can be distinguished...”, [0066] from other non EV charging events, [0023]).
Regarding claim 13 combination of Lu et al., Yan et al. and Liechieh et al. teach the computing device of claim 8. In addition Lu et al. teaches, based at least in part on the likelihood of the at least one EV charging event, performing at least one of:
changing a transformer used by the service site (based on identified EV charging events, corrective actions can be taken by rerouting power flow from a different transformer, replacing or resizing the transformer for higher capacity, [0016] and [0099]); or
changing a number of service sites served by the transformer (based on identified EV charging events, corrective actions can be taken by rerouting power flow from a different transformer, replacing or resizing the transformer for higher capacity, [0016] and [0099]).
Regarding claim 14 combination of Lu et al., Yan et al. and Liechieh et al. teach the computing device of claim 8. In addition Lu et al. teaches, wherein:
the likelihood value comprises a value from 0.0 to 1.0 (if the assigned probability of a suspected EV charging event is greater than 0.5, than the suspected EV charging event is an actual EV charging event. That is the probability of suspected EV charging event is between 0-1, [0084]); and
the time-range is one week (data is collected for 30 days. To a person of ordinary skill in the art any range of time intervals can be selected based on system needs. Also there is no teaching on the reference that data can only be collected for 30 days not for any other time period. [0040] and [0042]).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
CN74 (CN 112801374 A) teaches a model training method to predict electrical load based on electrical data collection. CN74 teaches in page 2 that variation in weather cause increase in energy consumption.
Barrad et al. (US 20240403671 A1) teaches an apparatus using machine learning model to predict future outcomes. Based on input data, the machine learning model adjusts its weights to better predict future outcomes.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ANZUMAN SHARMIN whose telephone number is (571)272-7365. The examiner can normally be reached M and Th 7:00am - 3:00pm and Tue 8:00am-12:00pm.
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, KAMINI SHAH can be reached at (571) 272-2279. 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.
/ANZUMAN SHARMIN/ Examiner, Art Unit 2115
/KAMINI S SHAH/ Supervisory Patent Examiner, Art Unit 2115
1 Based on house meter data and submeter data, distinguish between EV charging events and other usage events based on consumption change data determined by starting and stopping time for EV charging. .
2 Ambient temperature data associated with PMU data for a given time window.
3 Weights to associate power consumption terms in the time series of consumption change data.
4 Non EV charging event.
5 Weights to associate power consumption terms in the time series of consumption change data.