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 Objections
Claims 9-20 are objected to because of the following informalities:
Claim 9, line 10; change “mode” to –model--
Claim 15, line 9; change “mode” to –model--
Appropriate correction is required.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-4, 6-12, 15, 17, 19 and 20 are rejected under 35 U.S.C. 102(a)(1) and 102(a)(2) as being anticipated by Lu et al. U.S. PGPub 2022/0289064 A1 (hereinafter Lu).
Regarding Claim 1, Lu teaches a system (Lu, Fig. 1, Element 100, “EV Detection System”) comprising: a processor (Lu, Fig. 5, Element 510; Para. [0110]); and a non-transitory, computer-readable memory (Lu, Fig. 5, Element 515; Para. [0107]) that includes instructions executable by the processor (Lu, Para. [0112]) for causing the processor to perform operations (Lu, Para. [0119]) comprising: accessing premises consumption data of a premises in a power distribution network (Lu, Fig. 1, Element 120, “Pre-Processing Module” Paras. [0024] and [0031], and Fig. 2, Elements 220-240 and 220a-240a; Paras. [0039] - [0047]), wherein the premises consumption data comprises an indication of premises resource consumption over a period of time (Lu, Fig. 1, Element 130, “Detection Module” Paras. [0024] and [0032], and Fig. 2, Elements 250-250a, “Detect EV Charge Events and Patterns”; and Fig. 3, Paras. [0047] - [0051]); applying a machine-learning model to the premises consumption data (Lu, Fig. 1, Element 140, “Verification Module”, and Fig. 2, Element 270, “Train Classifier with Motifs and Charge Features”; Paras. [0024], [0033] and [0072] - [0078]), wherein the machine-learning model is trained to generate an output corresponding to an electric vehicle classification of the premises (Lu, Fig. 1, Element 160, “Results/Predictions”; Paras. [0033] - [0034] and [0072] - [0073], “classifier”); generating the electric vehicle classification of the premises using the output of the machine-learning model (Lu, Paras. [0072] - [0073]); and controlling power generation of the power distribution network based on the electric vehicle classification of the premises (Lu, Paras. [0016] – [0017] and [0097] - [0104]. Where the output of the analysis and determinations provide information for utilities to identify hot-spots in the grid and based on periodically monitoring and identifying EV owners which allows the utilities to take corrective actions and modifying or resizing transformers, rerouting power lines, etc. that is, control the power generation of the power distribution network based on the electric vehicle classification of the premises.).
Regarding Claim 2, The Lu reference discloses the claimed invention as stated above in claim 1. Furthermore, Lu teaches wherein the operations further comprise: training the machine-learning model to generate the output corresponding to the electric vehicle classification of the premises using training vectors (Lu, Fig. 2, Element 220-220a; Para. [0040], “data vector of 1 rowx96 columns” per day; and Fig. 3, Paras. [0063] and [0076] – [0087], “support-vector machine”) of ground-truth data of a plurality of premises of an additional power distribution network (Lu, Paras. [0022] - [0028], Where “ground-truth data” is merely accurate data from real-world scenarios used to train and validate machine learning models”).
Regarding Claim 3, The Lu reference discloses the claimed invention as stated above in claims 2/1. Furthermore, Lu teaches wherein the operations further comprise: updating the machine-learning model using additional consumption data from a plurality of premises of the power distribution network (Lu, Paras. [0022] - [0028] , Lu describes using a multiple of vehicle chargers at various homes, i.e. plurality of premises.).
Regarding Claim 4, The Lu reference discloses the claimed invention as stated above in claim 1. Furthermore, Lu teaches wherein the electric vehicle classification of the premises comprises an indication that the premises does not charge an electric vehicle, an indication that the premises charges the electric vehicle using a first type of electric vehicle charger, or an indication that the premises charges the electric vehicle using a second type of electric vehicle charger (Lu, Paras. [0022] - [0028], Lu describes using a multiple of vehicle chargers at various homes/premises which would inherently be different types of chargers.).
Regarding Claim 6, The Lu reference discloses the claimed invention as stated above in claim 1. Furthermore, Lu teaches wherein the indication of premises resource consumption over the period of time comprises a time series of power consumption by the premises over a plurality of days at regular time intervals (Lu, Fig. 3; Para. [0040], “30 days of data”).
Regarding Claim 7, The Lu reference discloses the claimed invention as stated above in claim 1. Furthermore, Lu teaches wherein the operations further comprise: normalizing the premises consumption data using min-max scaling also used to normalize training consumption data used to train the machine-learning model (Lu, Para. [0044], “other techniques for normalizing the values may be performed”).
Regarding Claim 8, The Lu reference discloses the claimed invention as stated above in claim 1. Furthermore, Lu teaches wherein the premises consumption data comprises time-domain data (Lu, Fig. 1, Element 130, “Detection Module” Paras. [0024] and [0032], and Fig. 2, Elements 250-250a, “Detect EV Charge Events and Patterns”; and Fig. 3, Paras. [0047] - [0051]).
Regarding Claim 9, Lu teaches a non-transitory, computer-readable medium comprising instructions that are executable by a processor for causing the processor to perform operations (Lu, Para. [0107]) comprising: accessing premises consumption data of a premises in a power distribution network (Lu, Fig. 1, Element 120, “Pre-Processing Module” Paras. [0024] and [0031], and Fig. 2, Elements 220-240 and 220a-240a; Paras. [0039] - [0047]), wherein the premises consumption data comprises an indication of premises resource consumption over a period of time (Lu, Fig. 1, Element 130, “Detection Module” Paras. [0024] and [0032], and Fig. 2, Elements 250-250a, “Detect EV Charge Events and Patterns”; and Fig. 3, Paras. [0047] - [0051]); applying a machine-learning model to the premises consumption data (Lu, Fig. 1, Element 140, “Verification Module”, and Fig. 2, Element 270, “Train Classifier with Motifs and Charge Features”; Paras. [0024], [0033] and [0072] - [0078]), wherein the machine-learning model is trained to generate an output corresponding to an electric vehicle classification of the premises (Lu, Fig. 1, Element 160, “Results/Predictions”; Paras. [0033] - [0034] and [0072] - [0073], “classifier”); generating the electric vehicle classification of the premises using the output of the machine-learning mode (Lu, Paras. [0072] - [0073]); and controlling power generation of the power distribution network based on the electric vehicle classification of the premises (Lu, Paras. [0016] – [0017] and [0097] - [0104]. Where the output of the analysis and determinations provide information for utilities to identify hot-spots in the grid and based on periodically monitoring and identifying EV owners which allows the utilities to take corrective actions and modifying or resizing transformers, rerouting power lines, etc. that is, control the power generation of the power distribution network based on the electric vehicle classification of the premises.).
Regarding Claim 10, The Lu reference discloses the claimed invention as stated above in claim 1. Furthermore, Lu teaches wherein the operations further comprise: training the machine-learning model to generate the output corresponding to the electric vehicle classification of the premises using training vectors (Lu, Fig. 2, Element 220-220a; Para. [0040], “data vector of 1 rowx96 columns” per day; and Fig. 3, Paras. [0063] and [0076] – [0087], “support-vector machine”) of ground-truth data of a plurality of premises of an additional power distribution network (Lu, Paras. [0022] - [0028], Where “ground-truth data” is merely accurate data from real-world scenarios used to train and validate machine learning models”).
Regarding Claim 11, The Lu reference discloses the claimed invention as stated above in claims 10/9. Furthermore, Lu teaches wherein the operations further comprise: updating the machine-learning model using additional consumption data from a plurality of premises of the power distribution network. (Lu, Paras. [0022] - [0028] , Lu describes using a multiple of vehicle chargers at various homes, i.e. plurality of premises.).
Regarding Claim 12, The Lu reference discloses the claimed invention as stated above in claim 9. Furthermore, Lu teaches wherein the electric vehicle classification of the premises comprises an indication that the premises does not charge an electric vehicle, an indication that the premises charges the electric vehicle using a level 1 electric vehicle charger, or an indication that the premises charges the electric vehicle using a level 2 electric vehicle charger (Lu, Paras. [0022] - [0028], Lu describes using a multiple of vehicle chargers at various homes/premises which would inherently be different types of chargers, and as illustrated in Fig. 3, and described in Paras. [0047] – [0057], due to the kWh level of power draw difference in level 1 and level 2 charging, an indication of using a level 1 charger or a level 2 charger is easily indicated.).
Regarding Claim 15, Lu teaches a computer-implemented method (Lu, Fig. 1, Element 100, “EV Detection System”; Para. 0008]) comprising: accessing premises consumption data of a premises in a power distribution network (Lu, Fig. 1, Element 120, “Pre-Processing Module” Paras. [0024] and [0031], and Fig. 2, Elements 220-240 and 220a-240a; Paras. [0039] - [0047]), wherein the premises consumption data comprises an indication of premises resource consumption over a period of time (Lu, Fig. 1, Element 130, “Detection Module” Paras. [0024] and [0032], and Fig. 2, Elements 250-250a, “Detect EV Charge Events and Patterns”; and Fig. 3, Paras. [0047] - [0051]); applying a machine-learning model to the premises consumption data (Lu, Fig. 1, Element 140, “Verification Module”, and Fig. 2, Element 270, “Train Classifier with Motifs and Charge Features”; Paras. [0024], [0033] and [0072] - [0078]), wherein the machine-learning model is trained to generate an output corresponding to an electric vehicle classification of the premises (Lu, Fig. 1, Element 160, “Results/Predictions”; Paras. [0033] - [0034] and [0072] - [0073], “classifier”); generating the electric vehicle classification of the premises using the output of the machine-learning mode (Lu, Paras. [0072] - [0073]); and controlling power generation of the power distribution network based on the electric vehicle classification of the premises (Lu, Paras. [0016] – [0017] and [0097] - [0104]. Where the output of the analysis and determinations provide information for utilities to identify hot-spots in the grid and based on periodically monitoring and identifying EV owners which allows the utilities to take corrective actions and modifying or resizing transformers, rerouting power lines, etc. that is, control the power generation of the power distribution network based on the electric vehicle classification of the premises.).
Regarding Claim 17, The Lu reference discloses the claimed invention as stated above in claim 15. Furthermore, Lu teaches wherein the electric vehicle classification of the premises comprises an indication that the premises does not charge an electric vehicle, an indication that the premises charges the electric vehicle using a level 1 electric vehicle charger, or an indication that the premises charges the electric vehicle using a level 2 electric vehicle charger (Lu, Paras. [0022] - [0028], Lu describes using a multiple of vehicle chargers at various homes/premises which would inherently be different types of chargers, and as illustrated in Fig. 3, and described in Paras. [0047] – [0057], due to the kWh level of power draw difference in level 1 and level 2 charging, an indication of using a level 1 charger or a level 2 charger is easily indicated.).
Regarding Claim 19, The Lu reference discloses the claimed invention as stated above in claim 15. Furthermore, Lu teaches wherein the indication of premises resource consumption over the period of time comprises a time series of power consumption by the premises over a plurality of days at regular time intervals (Lu, Fig. 3; Para. [0040], “30 days of data”).
Regarding Claim 20, The Lu reference discloses the claimed invention as stated above in claim 15. Furthermore, Lu teaches wherein the premises consumption data comprises time-domain data (Lu, Fig. 1, Element 130, “Detection Module” Paras. [0024] and [0032], and Fig. 2, Elements 250-250a, “Detect EV Charge Events and Patterns”; and Fig. 3, Paras. [0047] - [0051]).
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 5 is rejected under 35 U.S.C. 103 as being unpatentable over Lu et al. U.S. PGPub 2022/0289064 A1 (hereinafter Lu) as applied to claim 1 above, and further in view of Guda et al. U.S. PGPub 2022/0129621 A1 (hereinafter Guda).
Regarding Claim 5, The Lu reference discloses the claimed invention as stated above in claim 1. Furthermore, Lu teaches wherein the electric vehicle classification of the premises comprises a set of possible electric vehicle classifications (Lu, Para. [0033]), but does not teach using a one-hot encoding of a SoftMax function.
Guda, however, teaches wherein the classification comprises a one-hot encoding of a SoftMax function of a set of possible classifications (Guda, Paras. [0027], [0042] and [0052]).
It would have been obvious to a person having ordinary skill in the art to understand that although Lu explicitly teaches using a different normalized exponential function, Lu would inherently incorporate some type of conventional logistics function commonly understood in the art. The normalized exponential function taught by Guda, teaches one of the many conventional normalized exponential function utilized in the art for multinomial logistic regression. A person of ordinary skill in the art would have been motivated to choose based on desirability, one of the many known conventional methods, such as the one taught by Guda, to provide the results of the modeling of Lu.
Claim 13 is rejected under 35 U.S.C. 103 as being unpatentable over Lu et al. U.S. PGPub 2022/0289064 A1 (hereinafter Lu) as applied to claim 9 above, and further in view of Guda et al. U.S. PGPub 2022/0129621 A1 (hereinafter Guda).
Regarding Claim 13, The Lu reference discloses the claimed invention as stated above in claim 9. Furthermore, Lu teaches wherein the electric vehicle classification of the premises comprises a set of possible electric vehicle classifications (Lu, Para. [0033]), but does not teach using a one-hot encoding of a SoftMax function.
Guda, however, teaches wherein the classification comprises a one-hot encoding of a SoftMax function of a set of possible classifications (Guda, Paras. [0027], [0042] and [0052]).
It would have been obvious to a person having ordinary skill in the art to understand that although Lu explicitly teaches using a different normalized exponential function, Lu would inherently incorporate some type of conventional logistics function commonly understood in the art. The normalized exponential function taught by Guda, teaches one of the many conventional normalized exponential function utilized in the art for multinomial logistic regression. A person of ordinary skill in the art would have been motivated to choose based on desirability, one of the many known conventional methods, such as the one taught by Guda, to provide the results of the modeling of Lu.
Claim 14 is rejected under 35 U.S.C. 103 as being unpatentable over Lu et al. U.S. PGPub 2022/0289064 A1 (hereinafter Lu) as applied to claim 9 above, and further in view of Spalt et al. U.S. PGPub 2022/0294217 A1 (hereinafter Spalt).
Regarding Claim 14, The Lu reference discloses the claimed invention as stated above in claim 9. Furthermore, Lu teaches applying a machine-learning model to the electric vehicle classification of the premises, but does not explicitly teach applying an additional machine-learning model to the electric vehicle classification of the premises; and generating a forecast of future electric vehicle charging operations using an output of the additional machine-learning model.
Seabloom, however, teaches wherein the operations further include: applying an additional machine-learning model to the classification; and generating a forecast of future operations using an output of the additional machine-learning model (Seabloom, Para. [0026]).
It would have been obvious to a person having ordinary skill in the art to understand that although Lu does not explicitly teach applying an additional machine learning model to the classification operation, Lu would inherently incorporate some type of conventional classification operation commonly understood in the art. The classification operation taught by Seabloom, teaches one of the many conventional classification operations utilized in the art for improving the modeling functions. A person of ordinary skill in the art would have been motivated to choose based on desirability, one of the many known conventional methods, such as the one taught by Seabloom, to improve the results of the modeling of Lu.
Claim 16 is rejected under 35 U.S.C. 103 as being unpatentable over Lu et al. U.S. PGPub 2022/0289064 A1 (hereinafter Lu) as applied to claim 15 above, and further in view of Spalt et al. U.S. PGPub 2022/0294217 A1 (hereinafter Spalt).
Regarding Claim 16, The Lu reference discloses the claimed invention as stated above in claim 15. Furthermore, Lu teaches applying a machine-learning model to the electric vehicle classification of the premises and a plurality of additional electric vehicle classifications of additional premises in the power distribution network (Lu, Paras. [0022] - [0028] , Lu describes using a multiple of vehicle chargers at various homes, i.e. plurality of premises.), but does not explicitly teach applying an additional machine-learning model to the classification; and generating a forecast of future operations using an output of the additional machine-learning model.
Seabloom, however, teaches further comprising: applying an additional machine-learning model to the classification; and generating a forecast of future operations using an output of the additional machine-learning model.
It would have been obvious to a person having ordinary skill in the art to understand that although Lu does not explicitly teach applying an additional machine learning model to the classification operation, Lu would inherently incorporate some type of conventional classification operation commonly understood in the art. The classification operation taught by Seabloom, teaches one of the many conventional classification operations utilized in the art for improving the modeling functions. A person of ordinary skill in the art would have been motivated to choose based on desirability, one of the many known conventional methods, such as the one taught by Seabloom, to improve the results of the modeling of Lu.
Claim 18 is rejected under 35 U.S.C. 103 as being unpatentable over Lu et al. U.S. PGPub 2022/0289064 A1 (hereinafter Lu) as applied to claim 15 above, and further in view of Guda et al. U.S. PGPub 2022/0129621 A1 (hereinafter Guda).
Regarding Claim 18, The Lu reference discloses the claimed invention as stated above in claim 15. Furthermore, Lu teaches wherein the electric vehicle classification of the premises comprises a set of possible electric vehicle classifications (Lu, Para. [0033]), but does not teach using a one-hot encoding of a SoftMax function.
Guda, however, teaches wherein the classification comprises a one-hot encoding of a SoftMax function of a set of possible classifications (Guda, Paras. [0027], [0042] and [0052]).
It would have been obvious to a person having ordinary skill in the art to understand that although Lu explicitly teaches using a different normalized exponential function, Lu would inherently incorporate some type of conventional logistics function commonly understood in the art. The normalized exponential function taught by Guda, teaches one of the many conventional normalized exponential function utilized in the art for multinomial logistic regression. A person of ordinary skill in the art would have been motivated to choose based on desirability, one of the many known conventional methods, such as the one taught by Guda, to provide the results of the modeling of Lu.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Torpy et al. U.S. PGPub 2020/0380619 teaches an integrated utility meter.
Wilhelm et al. U.S. PGPub 2017/0148039 teaches a method of power monitoring.
Decker et al. U.S. PGPub 2022/0190641 teaches an adaptive metering of a grid.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JERRY D ROBBINS whose telephone number is (571)272-7585. The examiner can normally be reached 9:00AM - 6:00PM Tuesday-Saturday.
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, Julian Huffman can be reached at 571-272-2147. 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.
/JERRY D ROBBINS/ Examiner, Art Unit 2859