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 .
Specification
The specification is objected to as failing to provide proper antecedent basis for the claimed subject matter. See 37 CFR 1.75(d)(1) and MPEP § 608.01(o). Correction of the following is required: The term “two-headed autoencoder”, as used in the claims, does not have an apparent meaning in the specification. The term has no set meaning in the art and its usage is it not further clarified.
Claim Rejections - 35 USC § 101
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. Below is a claim-by-claim analysis.
Claim 1, 8, 14
Step 1: Recites a system (claim 1), a non-transitory computer readable medium (claim 8) and a method (claim 14). Therefore, they are directed to the statutory categories of invention.
Step 2A Prong 1: The claim recites:
determining statistical measures of a set of differential voltage-discharge curves over a range of discharge cycles based on the second battery dataset
This limitation, in its broadest interpretation, could encompass mentally generating values based on a set of numbers, which is an abstract idea that can be done is one’s head.
Step 2B Prong 2: The judicial exception is not integrated into a practical application. The remaining
limitations of the claim are directed to insignificant extra-solution activity (“receive a first battery dataset…”, receiving a second battery dataset…”), or are mere instructions to apply the judicial exception by a generic computer algorithm (“train a two-headed autoencoder… to predict”, utilizing the two-headed a two-headed autoencoder… to predict”) with no explicit improvement to functioning of the computer itself or any other technology or technical field.
Step 2B: The claim does not contain significantly more than the judicial exception. The analysis mirrors
the analysis of step 2A prong 2.
Claim 2, 9, 15
Step 1: Recites a system (claim 2), a non-transitory computer readable medium (claim 9) and a method (claim 15). Therefore, they are directed to the statutory categories of invention.
Step 2A Prong 1: The claim recites the abstract idea it inherits from the claim it depends on.
Step 2B Prong 2: The judicial exception is not integrated into a practical application. The remaining
limitations of the claim are additional elements of the mere instruction to apply the judicial exception by a generic computer algorithm with no explicit improvement to functioning of the computer itself or any other technology or technical field (“utilizes loss function based on an autoencoder loss…”).
Step 2B: The claim does not contain significantly more than the judicial exception. The analysis mirrors
the analysis of step 2A prong 2.
Claim 3, 10, 16
Step 1: Recites a system (claim 3), a non-transitory computer readable medium (claim 10) and a method (claim 16). Therefore, they are directed to the statutory categories of invention.
Step 2A Prong 1: The claim recites the abstract idea it inherits from the claim it depends on.
Step 2B Prong 2: The judicial exception is not integrated into a practical application. The remaining
limitations of the claim are additional elements of the mere instruction to apply the judicial exception by a generic computer algorithm with no explicit improvement to functioning of the computer itself or any other technology or technical field (“… adjusted respectively by an autoencoder loss…”).
Step 2B: The claim does not contain significantly more than the judicial exception. The analysis mirrors
the analysis of step 2A prong 2.
Claim 4, 11, 17
Step 1: Recites a system (claim 4), a non-transitory computer readable medium (claim 11) and a method (claim 17). Therefore, they are directed to the statutory categories of invention.
Step 2A Prong 1: The claim recites the abstract idea it inherits from the claim it depends on. Additionally, it recites:
Reject the at least one rechargeable battery if the batter life does not satisfy a battery life criteria
This limitation, in its broadest interpretation, could encompass mentally determining the validity of a set of values based on passing a simple arithmetic threshold.
Step 2B Prong 2: The judicial exception is not integrated into a practical application. There are no further limitations in the claim.
Step 2B: The claim does not contain significantly more than the judicial exception. The analysis mirrors
the analysis of step 2A prong 2.
Claim 5
Step 1: Recites a system. Therefore, it is directed to the statutory categories of invention.
Step 2A Prong 1: The claim recites the abstract idea it inherits from the claim it depends on.
Step 2B Prong 2: The judicial exception is not integrated into a practical application. The remaining
limitations of the claim are directed to limiting the judicial exception that is not significant enough to meaningfully integrate into a practical application (“… range… begins with second discharge cycle…”).
Step 2B: The claim does not contain significantly more than the judicial exception. The analysis mirrors
the analysis of step 2A prong 2.
Claim 6, 12, 19
Step 1: Recites a system (claim 6), a non-transitory computer readable medium (claim 12) and a method (claim 19). Therefore, they are directed to the statutory categories of invention.
Step 2A Prong 1: The claim recites the abstract idea it inherits from the claim it depends on. Additionally, it recites:
wherein the statistical measures of a set of differential voltage-discharge curves are variances of the set of differential voltage-discharge curves
This limits the judicial exception to the calculation of variances, which, in the broadest interpretation is still a mental process of arithmetic that can be done in one’s head (with aid of paper and
pencil, MPEP 2106.04(a)(2), III)
Step 2B Prong 2: The judicial exception is not integrated into a practical application. There are no further limitations of the claim.
Step 2B: The claim does not contain significantly more than the judicial exception. The analysis mirrors
the analysis of step 2A prong 2.
Claim 7, 13, 20
Step 1: Recites a system (claim 7), a non-transitory computer readable medium (claim 13) and a method (claim 20). Therefore, they are directed to the statutory categories of invention.
Step 2A Prong 1: The claim recites the abstract idea it inherits from the claim it depends on.
Step 2B Prong 2: The remaining limitations of the claim are directed to insignificant extra-solution activity (“add battery measurements…when its battery life is exhausted”)
Step 2B: The claim does not contain significantly more than the judicial exception. The analysis mirrors
the analysis of step 2A prong 2.
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.
Claims 1, 6, 8, 12, 14, 19 are rejected under 35 U.S.C. 103 as being unpatentable over Severson et al. (“US 20190113577”) in view of Ju et al. (“NeuroInspect: Interpretable Neuron-based Debugging Framework through Class-conditional Visualizations”, 2023).
Regarding claim 1, Severson teaches a processor;
and a memory communicably coupled to the processor and storing machine-readable instructions that, when executed by the processor, cause the processor to:
receive a first battery dataset (Abstract, “A method of using data-driven predictive modeling to predict and classify battery cells by lifetime is provided that includes collecting a training dataset…”) for a first set of rechargeable batteries (Paragraph 3, “Lithium-ion batteries are deployed in a wide range of applications due to their low and falling costs, high energy densities, and long cycle lives”) that includes battery life measurements for the first set of rechargeable batteries (Paragraph 7, “using a battery cycling instrument, a plurality of battery cells between a voltage V1 and a voltage V2, continuously measuring battery cell physical properties that include a battery cell voltage, a battery cell current, a battery cell can temperature, a battery cell internal resistance of each battery cell during cycling…”)
receiving a second battery dataset for a second set of rechargeable batteries (Paragraph 15, “The testing data are used to assess generalizability of the model. The primary test and secondary test datasets are differentiated because the latter was generated after model development”)
determining statistical measures of a set of differential voltage-discharge curves (Paragraph 44, “Summary statistics, e.g. minimum, mean, and variance, were then calculated for the ΔQ(V) curves of each cell”) over a range of discharge cycles (Paragraph 45, “In all cases, data were taken from the first 100 cycles.”) based on the second battery dataset (Figure 5B1)
utilizing… to predict battery life for at least one rechargeable battery of the second set of rechargeable batteries (Figure 9)
Severson fails to teach training a two-headed autoencoder coupled to an elastic net module. However, Ju teaches train a two-headed autoencoder (Page 4, Column 2, Paragraph 2, “…leveraging CLIP networks [35], which comprise two encoders2 trained on…”) coupled to an elastic net module (Page 4, Column 1, Paragraph 1, “we employ elastic net regularization [26], a generalization of LASSO and ridge regression”) …3
Severson and Ju are considered analogous to the invention because all are directed towards machine learning methods. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to have modified Severson to incorporate the teachings of Ju, and included training two-headed autoencoder coupled to an elastic net module to make the battery predictions. Doing so allows a model to better handle inputs with many variables of varying importance to the output (See Page 4, Column 1, Paragraph 2 of Ju)
Regarding claim 6, Severson teaches wherein the statistical measures of a set of differential voltage-discharge curves are variances of the set of differential voltage-discharge curves (Figure 2A).
Claim 8 is a non-transitory computer-readable medium claim corresponding to system claim 1 and is rejected for the same reasons as given in the rejection of that claim.
Claim 12 is a non-transitory computer-readable medium claim corresponding to system claim 6 and is rejected for the same reasons as given in the rejection of that claim.
Claim 14 is a method claim corresponding to system claim 1 and is rejected for the same reasons as given in the rejection of that claim.
Claim 19 is a method claim corresponding to system claim 6 and is rejected for the same reasons as given in the rejection of that claim.
Claims 2-3, 9-10, 15-16 are rejected under 35 U.S.C. 103 as being unpatentable over Severson et al. (“US 20190113577”) in view of Ju et al. (“NeuroInspect: Interpretable Neuron-based Debugging Framework through Class-conditional Visualizations”, 2023) and in further view of Feng et al. (“Cascaded Structure-Learning Network with Using Adversarial Training for Robust Facial Landmark Detection”, 2022) and Kang et al. (“A Deep Graph Network with Multiple Similarity for User Clustering in Human–Computer Interaction”, 2023).
Regarding claim 2, Severson fails to teach training the two-headed autoencoder coupled to an elastic net module utilizes a loss function based on an autoencoder loss, an initial prediction loss, and an elastic net regularization metric. However,
Ju teaches training a two-headed autoencoder couple to an elastic net module (see claim 1 analysis) that utilizes a loss function based on an elastic net regularization metric (Page, Column 1, Equation 14).
Feng teaches a loss function based on an autoencoder loss (Page 46:10, Equation 205), and
Kang teaches a loss function based on an initial prediction loss (Page 46:9, Equation 66).
Severson, Ju, Feng and Kang are considered analogous to the invention because all are directed towards machine learning methods. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to have modified Severson to incorporate the teachings of Ju, Feng and Kang and included a means to adjust the different components of the composite loss function. Doing so allows one to optimize over multiple objectives when training a model.
Regarding claim 3, Severson fails to teach the autoencoder loss, the initial prediction loss, and the elastic net regularization metric can be adjusted respectively by an autoencoder loss sensitivity hyperparameter, an initial prediction loss sensitivity hyperparameter, and an elastic net regularization metric sensitivity hyperparameter. However,
Ju teaches an elastic net regularization metric that can be adjusted by an elastic net regularization metric sensitivity hyperparameter (Page, Column 1, Equation 17)
Feng teaches an autoencoder loss that can be adjusted by an autoencoder loss sensitivity hyperparameter (Page 46:10, Equation 20, “where μ > 0is the hyperparameter controlling the loss of feature graph reconstruction”), and
Kang teaches an initial prediction loss that can be adjusted by an initial prediction loss sensitivity hyperparameter (Page 46:9, Equation 6, “where β is a trade-off coefficient8”)
Severson, Ju, Feng and Kang are considered analogous to the invention because all are directed towards machine learning methods. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to have modified Severson to incorporate the teachings of Ju, Feng and Kang and included a means to adjust the different components of the composite loss function. Doing so allows one to optimize over multiple objectives when training a model.
Claim 9 is a non-transitory computer-readable medium claim corresponding to system claim 2 and is rejected for the same reasons as given in the rejection of that claim.
Claim 10 is a non-transitory computer-readable medium claim corresponding to system claim 3 and is rejected for the same reasons as given in the rejection of that claim.
Claim 15 is a method claim corresponding to system claim 2 and is rejected for the same reasons as given in the rejection of that claim.
Claim 16 is a method claim corresponding to system claim 3 and is rejected for the same reasons as given in the rejection of that claim.
Claims 4, 11, 17 are rejected under 35 U.S.C. 103 as being unpatentable over Severson et al. (“US 20190113577”) in view of Ju et al. (“NeuroInspect: Interpretable Neuron-based Debugging Framework through Class-conditional Visualizations”, 2023) and in further view of Liaw et al. (“US 20220214399”).
Regarding claim 4, Severson fails to teach the further limitations of the claim. However, Liaw discloses rejecting the at least one rechargeable (Paragraph 3, “This disclosure relates generally… to qualification of rechargeable batteries into classifications”) battery if the battery life does not satisfy a battery life criteria (Paragraph 66, “the criteria to remove disqualified cells using “test data-based” direct screening, including the cell capacity, internal resistance, rest open circuit voltage, and/or self-discharge rate; embodiments disclosed herein use additional cell qualification metric... These additional cell qualification metrics include criteria of certain thresholds based on capacity failure modes and effects as defined by eCAD FMEA”).
Severson and Liaw are analogous to the invention because all are directed towards battery prediction methods. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to have modified Severson to incorporate the teachings of Liaw, and included rejecting batteries that don’t satisfy specific criteria. Doing so removes edge cases from the prediction training, thus better focusing the training of prediction apparatus.
Claim 11 is a non-transitory computer-readable medium claim corresponding to system claim 4 and is rejected for the same reasons as given in the rejection of that claim.
Claim 17 is a method claim corresponding to system claim 4 and is rejected for the same reasons as given in the rejection of that claim.
Claims 5, 18 are rejected under 35 U.S.C. 103 as being unpatentable over Severson et al. (“US 20190113577”) in view of Ju et al. (“NeuroInspect: Interpretable Neuron-based Debugging Framework through Class-conditional Visualizations”, 2023) and in further view of Deshpande et al. (“Battery Cycle Life Prediction with Coupled Chemical Degradation and Fatigue Mechanics”, 2012).
Regarding claim 5, Severson fails to teach the further limitations of the claim. However, Deshpande teaches wherein the range of discharge cycles begins with a second discharge cycle (Page A1731, Column 2, Paragraph 3, “We designate the first cycle of our testing to be cycle number 2.”)
Severson and Deshpande are analogous to the invention because all are directed towards battery prediction methods. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to have modified Severson to incorporate the teachings of Deshpande, and begin the range of discharge cycles with the second discharge cycle. Doing so provides are more accurate baseline for predicting battery life, and reduces possibility of noisy data.
Claim 18 is a method claim corresponding to system claim 5 and is rejected for the same reasons as given in the rejection of that claim.
Claims 7, 13, 20 are rejected under 35 U.S.C. 103 as being unpatentable over Severson et al. (“US 20190113577”) in view of Ju et al. (“NeuroInspect: Interpretable Neuron-based Debugging Framework through Class-conditional Visualizations”, 2023) and in further view of Binder et al. (“Lifetime Modelling of Lead Acid Batteries”, 2005).
Regarding claim 7, Severson teaches adding battery measurements of the at least one rechargeable battery to a first battery data set (see claim 1 analysis). Severson fails to teach that the rechargeable battery is measured when its battery life is exhausted. However, Lee teaches that the at least one rechargeable battery is measured when its battery life is exhausted (Page 23, Table 39).
Severson and Binder are analogous to the invention because all are directed towards battery prediction methods. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to have modified Severson to incorporate the teachings of Binder, and take measurements when the battery life is exhausted. Doing so reduces likelihood of inaccurate data due variability of first discharge cycles.
Claim 13 is a non-transitory computer-readable medium claim corresponding to system claim 7 and is rejected for the same reasons as given in the rejection of that claim.
Claim 20 is a method claim corresponding to system claim 7 and is rejected for the same reasons as given in the rejection of that claim.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MATTHEWOS MESFIN whose telephone number is (571)270-0782. The examiner can normally be reached Monday-Friday 8am-5pm.
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, Cesar Paula can be reached at (571) 272-4128. 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.
/MATTHEWOS MESFIN/ Examiner, Art Unit 2145
/CESAR B PAULA/ Supervisory Patent Examiner, Art Unit 2145
1 Error graph implies that statistical measures were taken for said dataset
2 We are interpreting two-head autoencoder as a system with two separate encoders
3 The limitations omitted are taught by Severson, as shown above
4 “λ1|ω|1 +λ2|ω|2” is equivalent to the elastic net regularization metric shown in the specification (Equation 6)
5 “The reconstruction loss objective function is defined as LR”, Page 46:7. Reconstruction loss is equivalent to autoencoder loss.
6 LReg, as shown in Equation 4 of Page 46:9 is based on the difference between ground truth and generated heatmaps, thus is a form of initial prediction loss
7 Either λ1 or λ2 can be considered a hyperparameter that adjusts the sensitivity. Equivalent to what’s shown in the specification (Equation 6).
8 Within this context, it can be interpreted as a loss sensitivity hyperparameter
9 Cycles to failure can be interpreted as the number of discharge cycles before battery is exhausted, and the calculated throughput can be interpreted as a measurement taken
Prosecution Insights