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 .
Response to Arguments
The reply filed on 13 March 2026 has been entered. Applicant’s arguments with respect to claims 1-20 have been considered but are moot in view of new ground(s) of rejection caused by the amendments.
Information Disclosure Statement
The IDS dated 13 February 2013 that has been previously considered remains placed in the application file.
1st Claim Interpretation
Under MPEP 2143.03, "All words in a claim must be considered in judging the patentability of that claim against the prior art." In re Wilson, 424 F.2d 1382, 1385, 165 USPQ 494, 496 (CCPA 1970). As a general matter, the grammar and ordinary meaning of terms as understood by one having ordinary skill in the art used in a claim will dictate whether, and to what extent, the language limits the claim scope. Language that suggests or makes a feature or step optional but does not require that feature or step does not limit the scope of a claim under the broadest reasonable claim interpretation. In addition, when a claim requires selection of an element from a list of alternatives, the prior art teaches the element if one of the alternatives is taught by the prior art. See, e.g., Fresenius USA, Inc. v. Baxter Int’l, Inc., 582 F.3d 1288, 1298, 92 USPQ2d 1163, 1171 (Fed. Cir. 2009).
Claims 1, 5-7, 10, 14, 16 and 18-20 recite “one or more,” or “at least one of.” Since “one or more” and “at least one of” are disjunctive, any one of the elements found in the prior art is sufficient to reject the claim. While citations have been provided for completeness and rapid prosecution, only one element is required. Because, on balance, it appears the disjunctive interpretation enjoys the most specification support and for that reason the disjunctive interpretation (one of A, B OR C) is being adopted for the purposes of this Office Action. Applicant’s comments and/or amendments relating to this issue are invited to clarify the claim language and the prosecution history.
2nd 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 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), 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):
(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.
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). The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f), is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
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), 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:
“a monitoring system receiving the plurality of images and configured to” in claim 10.
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f), they 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), applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) (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).
3rd Claim Interpretation
Claims 4, 13 and 19 recite “rejecting the null hypothesis.” The phrase “rejecting” is considered to be a negative limitation because the word “rejecting” is exclusionary in nature. According to MPEP § 2173.05(i) “Any negative limitation or exclusionary proviso must have basis in the original disclosure.” The specification defines this phrase in paragraph [0039]. As showing a negative is not reasonable, any prior art reference that does not explicitly show the recited limitation suffices to reject the limitation.
4thClaim Interpretation
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.
The following terms in the claims have been given the following interpretations in light of the specification:
hypothesis testing, Claim 1, 3, 10, 12, 18 and 19: paragraph [0039], “null hypothesis is defined as follows, Ho: There is no difference between the two image populations P1 and P2. Next, clustering is applied to the two sets of features {X = G(i, Z), i ∈P}, k = 1,2 and a determination is made if the populations can be separated with an accuracy significantly different from random.”
Thus, “hypothesis testing” is testing the similarity of two images. This definition is used for purposes of searching for prior art, but cannot be incorporated into the claims.
probability being greater than a threshold for a defined significance level, Claims 4, 13 and 19: not defined.
Thus, “a probability being greater than a threshold for a defined significance level” is a probability, that is compared to a threshold, either of which can be zero, a fraction or a negative number. This definition is used for purposes of searching for prior art, but cannot be incorporated into the claims.
Should applicant wish different definitions, Applicant should point to the portions of the specification that clearly show a different definition.
1st Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-5, 9-13 and 17-19 (all claims except 6-8, 14-16 and 20) are rejected under 35 U.S.C. 103 as obvious over US Patent Publication 2018 0300865 A1, (Weiss et al.) in view of Canadian Patent Publication 3 174 896 A1, (Published 23 December 2023) (Beharie et al.). The references are listed in a PTO-892 from the Office Action in which they are first used.
Claim 1
[AltContent: textbox (Weiss et al. Showing an inspection system.)]
PNG
media_image1.png
615
449
media_image1.png
Greyscale
Regarding Claim 1, Weiss et al. teach a computerized method ("a new and useful method for predicting defects in assembly units in the field of optical inspection," paragraph [0002])comprising:
extracting one or more features from a plurality of images ("detecting a set of features in the inspection image in Block S120 and generating a vector, in a set of vectors," paragraph [0010]);
classifying the plurality of images based on the extracted one or more features to form one or more clusters of images ("identify a first cluster of vectors including a first vector associated with the first assembly unit-representing assembly units likely to exhibit the particular defect," paragraph [0049]);
performing hypothesis testing on the one or more clusters of images based on one or more production factors ("the system can generate ( or append) vectors based on features extracted from focused regions of interest in inspection images of like assembly units, thereby necessitating less time and computing power to generate higher-resolution representations of key regions of assembly units for comparison in Block S130, which may improve accuracy and resolution of subsequent defect, anomaly, and production drift detection," paragraph [0050]), wherein the hypothesis testing uses a null hypothesis to identify variations in the images of the one or more clusters ("Finally, a NULL HYPOTHESIS may exist having 0 impressionability with 0 Cl width," paragraph [0201]);
identifying variations in the one or more features resulting from the hypothesis testing ("Block S130, the system implements structured data analysis techniques ( e.g., linear regression analysis, cluster analysis, k-means clustering, and/or other statistical analysis and machine learning techniques) to partition the set of vectors-each uniquely representing multiple features of one assembly unit-into multiple groups or "clusters" of vectors representing similar combinations of features and/or similar feature ranges in one or more dimensions in the multi-dimensional feature space," paragraph [0058] where structured data analysis teaches identifying variations);
determining whether an observed probability of the identified variations in the one or more features is greater than a threshold for a defined significance level ("detecting a second set of features in the second inspection image; generating a second vector representing the second set of features in the multi-dimensional feature space; and, in response to the second vector deviating from the set of vector groups by more than a threshold difference, flagging the second assembly unit in Block S150," paragraph [0016]); and
in response to the observed probability being greater than the threshold for the defined significance level, determining one or more production metrics based on the identified variations ("The system can therefore predict defects in certain past assembly units by identifying vectors-representing these assembly units-that are sufficiently near a particular vector representing a defective assembly unit across multiple (e.g., "n") dimensions," paragraph [0070] where the multiple dimensions are production metrics).
Weiss et al. is not relied upon to explicitly teach all of unsupervised machine learning.
[AltContent: textbox (Beharie et al. Fig. 18, showing a prediction model.)]
PNG
media_image2.png
208
355
media_image2.png
Greyscale
However, Beharie et al. teach the classifying performed based on unsupervised machine learning ("one or more lookalike segmentation processes 1526 which may generate one or more lookalike segments 1528 which may be stored in object storage service 1518, and a user segmentation process 1530 having unsupervised segmentation process 1532, odds ratio process 1534 and post-binning process 1536," paragraph [0351]).
Therefore, taking the teachings of Weiss et al. and Beharie et al. as a whole, it would have been obvious to a person having ordinary skill in the art before the time of the effective filing date of the claimed invention of the instant application to modify “Method for Predicting Defects in Assembly Units” as taught by Weiss et al. to use “Systems and methods for Generating Explainable Predictions” as taught by Beharie et al. The suggestion/motivation for doing so would have been that, “The described embodiments relate generally to systems and methods for generating explainable predictions for customer relationship management, and specifically to generating explainable predictions that include attribution data associated with each prediction.” as noted by the Beharie et al. disclosure in paragraph [0001], which also motivates combination because the combination would predictably have a better explainability as there is a reasonable expectation that there is a source for errors and that source is better to be known; and/or because doing so merely combines prior art elements according to known methods to yield predictable results.
The rejection of method claim 1 above applies mutatis mutandis to the corresponding limitations of system claim 10 and apparatus claim 18 while noting that the rejection above cites to both device and method disclosures. Claims 10 and 18 are mapped below for clarity of the record and to specify any new limitations not included in claim 1.
Claim 2
Regarding claim 2, Weiss et al. teach the computerized method of claim 1, wherein the plurality of images comprises current images of a product along a production line and past images of a similar product along the production line ("to scan and identify other assembly units that may exhibit the same defect (exclusively) from historical optical data recorded during production of these assembly units," paragraph [0069]).
Claim 3
Regarding claim 3, Weiss et al. teach the computerized method of claim 1, wherein each image of the plurality of images is classified into one of two clusters and the hypothesis testing uses the null hypothesis to identify variations in the images of the two clusters ("infer soundness, aesthetic defects, and/or functional defects of other assembly units represented by vectors in this cluster based on these limited test and/or inspection data; and/or isolate features indicative of such aesthetic and/or functional defects, such as by comparing features represented in different clusters," paragraph [0065]).
Claim 4
Regarding claim 4, Weiss et al. teach the computerized method of claim 3, further comprising rejecting the null hypothesis in response to the observed probability being greater than the threshold for the defined significance level ("infer soundness, aesthetic defects, and/or functional defects of other assembly units represented by vectors in this cluster based on these limited test and/or inspection data; and/or isolate features indicative of such aesthetic and/or functional defects, such as by comparing features represented in different clusters," paragraph [0065]).
Claim 5
Regarding claim 5, Weiss et al. teach the computerized method of claim 1, wherein the plurality of images comprises images of a product along an assembly line and further comprising monitoring one or more production processes for the product using the one or more production metrics ("predict presence of this particular defect in other assembly units associated with the other unlabeled vectors in the first cluster; and serve a prompt to a user ( e.g., a manufacturing engineer associated with the assembly line, a technician on the assembly line) to inspect these other assembly units for the particular defect, such as in real-time as these other assembly units are assembled or asynchronously by retrieving these assembly units from a stock room. Similarly, the system can: define a second cluster containing hundreds of vectors, including tens of vectors associated with assembly units confirmed to exclude the particular defect and labeled as non-defective; predict absence of the defect in assembly units associated with unlabeled vectors in the second cluster; and generate a list of serial numbers of these assembly units to exclude from inspection for this particular defect," paragraph [0065]).
Claim 9
Regarding claim 9, Weiss et al. teach the computerized method of claim 1, further comprising preprocessing the plurality of images, wherein the preprocessing comprises centering and cropping each image of the plurality of images on a region of interest and masking out other regions of each of the images corresponding to noise ("highlight or crop regions of these inspection images containing features corresponding to this subset of feature dimensions," paragraph [0109]).
Claim 10
Regarding claim 10, Weiss et al. teach a system ("a new and useful method for predicting defects in assembly units in the field of optical inspection," paragraph [0002]) comprising:
a plurality of cameras ("An optical inspection station can additionally or alternatively include multiple visible light cameras," paragraph [0036]) configured to acquire a plurality of images of products along a production line ("The system can thus aggregate a set of ( e.g., 100, 1 k, or 100 k) inspection images (e.g., digital color photographic image) recorded over a period of operation of an assembly line in Block Sll0, wherein each inspection image records visual characteristics of a unique assembly unit at a particular production stage," paragraph [0039]); and
a monitoring system receiving the plurality of images ("optical inspection station ( or a local or remote computer system interfacing with the remote database) can implement machine vision techniques to identify these fiducials in a color image captured by the visible light camera and to transform sizes, geometries ( e.g., distortions from known geometries), and/or positions of these fiducials within the color image into a depth map, into a three-dimensional color image, or into a three-dimensional measurement space ( described below) for the color image, such as by passing the color image into a neural network," paragraph [0037]) and configured to:
extract one or more features from the plurality of images ("detecting a set of features in the inspection image in Block S120 and generating a vector, in a set of vectors," paragraph [0010]);
classify the plurality of images based on the extracted one or more features to form one or more clusters of images ("identify a first cluster of vectors including a first vector associated with the first assembly unit-representing assembly units likely to exhibit the particular defect," paragraph [0049]);
perform hypothesis testing on the one or more clusters of images based on one or more production factors ("the system can generate ( or append) vectors based on features extracted from focused regions of interest in inspection images of like assembly units, thereby necessitating less time and computing power to generate higher-resolution representations of key regions of assembly units for comparison in Block S130, which may improve accuracy and resolution of subsequent defect, anomaly, and production drift detection," paragraph [0050]), wherein the hypothesis testing uses a null hypothesis to identify variations in the images of the one or more clusters ("Finally, a NULL HYPOTHESIS may exist having 0 impressionability with 0 Cl width," paragraph [0201]);
identify variations in the one or more features resulting from the hypothesis testing ("Block S130, the system implements structured data analysis techniques ( e.g., linear regression analysis, cluster analysis, k-means clustering, and/or other statistical analysis and machine learning techniques) to partition the set of vectors-each uniquely representing multiple features of one assembly unit-into multiple groups or "clusters" of vectors representing similar combinations of features and/or similar feature ranges in one or more dimensions in the multi-dimensional feature space," paragraph [0058] where structured data analysis teaches identifying variations);
determine whether an observed probability of the identified variations in the one or more features is greater than a threshold for a defined significance level ("detecting a second set of features in the second inspection image; generating a second vector representing the second set of features in the multi-dimensional feature space; and, in response to the second vector deviating from the set of vector groups by more than a threshold difference, flagging the second assembly unit in Block S150," paragraph [0016]); and
in response to the observed probability being greater than the threshold for the defined significance level, determine one or more production metrics based on the identified variations to thereby monitor a production of the products ("The system can therefore predict defects in certain past assembly units by identifying vectors-representing these assembly units-that are sufficiently near a particular vector representing a defective assembly unit across multiple (e.g., "n") dimensions," paragraph [0070] where the multiple dimensions are production metrics).
Weiss et al. is not relied upon to explicitly teach all of unsupervised machine learning.
However, Beharie et al. teach the classifying performed based on unsupervised machine learning ("one or more lookalike segmentation processes 1526 which may generate one or more lookalike segments 1528 which may be stored in object storage service 1518, and a user segmentation process 1530 having unsupervised segmentation process 1532, odds ratio process 1534 and post-binning process 1536," paragraph [0351]).
Weiss et al. and Beharie et al. are combined as per claim 1.
Claim 11
Regarding claim 11, Weiss et al. teach the system of claim 10, wherein the plurality of images comprises current images of the products along the production line and past images of a similar product along the production line ("to scan and identify other assembly units that may exhibit the same defect (exclusively) from historical optical data recorded during production of these assembly units," paragraph [0069]).
Claim 12
Regarding claim 12, Weiss et al. teach the system of claim 10, wherein each image of the plurality of images is classified into one of two clusters and the hypothesis testing uses the null hypothesis to identify variations in the images of the two clusters ("infer soundness, aesthetic defects, and/or functional defects of other assembly units represented by vectors in this cluster based on these limited test and/or inspection data; and/or isolate features indicative of such aesthetic and/or functional defects, such as by comparing features represented in different clusters," paragraph [0065]).
Claim 13
Regarding claim 13, Weiss et al. teach the system of claim 12, wherein the monitoring system is further configured to reject the null hypothesis in response to the observed probability being greater than the threshold for the defined significance level ("infer soundness, aesthetic defects, and/or functional defects of other assembly units represented by vectors in this cluster based on these limited test and/or inspection data; and/or isolate features indicative of such aesthetic and/or functional defects, such as by comparing features represented in different clusters," paragraph [0065]).
Claim 17
Regarding claim 17, Weiss et al. teach the system of claim 10, wherein the monitoring system is further configured to preprocess the plurality of images, wherein the preprocessing comprises centering and cropping each image of the plurality of images on a region of interest and masking out other regions of each of the images corresponding to noise "highlight or crop regions of these inspection images containing features corresponding to this subset of feature dimensions," paragraph [0109]).
Claim 18
Regarding claim 18, Weiss et al. teach one or more non-transitory computer-readable media storing processor-executable instructions that ("optical inspection station ( or a local or remote computer system interfacing with the remote database) can implement machine vision techniques to identify these fiducials in a color image captured by the visible light camera and to transform sizes, geometries ( e.g., distortions from known geometries), and/or positions of these fiducials within the color image into a depth map, into a three-dimensional color image, or into a three-dimensional measurement space ( described below) for the color image, such as by passing the color image into a neural network," paragraph [0037]), when executed by at least one processor, cause the at least one processor to:
extract one or more features from a plurality of images ("detecting a set of features in the inspection image in Block S120 and generating a vector, in a set of vectors," paragraph [0010]);
classify the plurality of images based on the extracted one or more features to form one or more clusters of images ("identify a first cluster of vectors including a first vector associated with the first assembly unit-representing assembly units likely to exhibit the particular defect," paragraph [0049]);
perform hypothesis testing on the one or more clusters of images based on one or more production factors ("the system can generate ( or append) vectors based on features extracted from focused regions of interest in inspection images of like assembly units, thereby necessitating less time and computing power to generate higher-resolution representations of key regions of assembly units for comparison in Block S130, which may improve accuracy and resolution of subsequent defect, anomaly, and production drift detection," paragraph [0050]), wherein the hypothesis testing uses a null hypothesis to identify variations in the images of the one or more clusters("Finally, a NULL HYPOTHESIS may exist having 0 impressionability with 0 Cl width," paragraph [0201]);
identify variations in the one or more features resulting from the hypothesis testing ("Block S130, the system implements structured data analysis techniques ( e.g., linear regression analysis, cluster analysis, k-means clustering, and/or other statistical analysis and machine learning techniques) to partition the set of vectors-each uniquely representing multiple features of one assembly unit-into multiple groups or "clusters" of vectors representing similar combinations of features and/or similar feature ranges in one or more dimensions in the multi-dimensional feature space," paragraph [0058] where structured data analysis teaches identifying variations);
determine whether an observed probability of the identified variations in the one or more features is greater than a threshold for a defined significance level ("detecting a second set of features in the second inspection image; generating a second vector representing the second set of features in the multi-dimensional feature space; and, in response to the second vector deviating from the set of vector groups by more than a threshold difference, flagging the second assembly unit in Block S150," paragraph [0016]); and
in response to the observed probability being greater than the threshold for the defined significance level, determine one or more production metrics based on the identified variations ("The system can therefore predict defects in certain past assembly units by identifying vectors-representing these assembly units-that are sufficiently near a particular vector representing a defective assembly unit across multiple (e.g., "n") dimensions," paragraph [0070] where the multiple dimensions are production metrics).
Weiss et al. is not relied upon to explicitly teach all of unsupervised machine learning.
However, Beharie et al. teach the classifying performed based on unsupervised machine learning ("one or more lookalike segmentation processes 1526 which may generate one or more lookalike segments 1528 which may be stored in object storage service 1518, and a user segmentation process 1530 having unsupervised segmentation process 1532, odds ratio process 1534 and post-binning process 1536," paragraph [0351]).
Weiss et al. and Beharie et al. are combined as per claim 1.
Claim 19
Regarding claim 19, Weiss et al. teach the one or more non-transitory computer-readable media of claim 18, wherein each image of the plurality of images is classified into one of two clusters and the hypothesis testing uses the null hypothesis to identify variations in the image of the two clusters ("infer soundness, aesthetic defects, and/or functional defects of other assembly units represented by vectors in this cluster based on these limited test and/or inspection data; and/or isolate features indicative of such aesthetic and/or functional defects, such as by comparing features represented in different clusters," paragraph [0065]), and wherein the at least one processor is further caused to:
reject the null hypothesis in response to the observed probability being greater than the threshold for the defined significance level ("infer soundness, aesthetic defects, and/or functional defects of other assembly units represented by vectors in this cluster based on these limited test and/or inspection data; and/or isolate features indicative of such aesthetic and/or functional defects, such as by comparing features represented in different clusters," paragraph [0065]).
2nd Claim Rejections - 35 USC § 103
Claims 6-8, 14-16 and 20 (all remaining claims) are rejected under 35 U.S.C. 103 as obvious over US Patent Publication 2018 0300865 A1, (Weiss et al.) and Canadian Patent Publication 3 174 896 A1, (Published 23 December 2023) (Beharie et al.) in view of Non Patent Publication “Automated Battery Making Fault Classification Using Over-Sampled Image Data CNN Features”, (Din et al.). The references are listed in a PTO-892 from the Office Action in which they are first used.
Claim 6
Regarding Claim 6, Weiss et al. and Beharie et al. teach the computerized method of claim 5, as noted above.
Weiss et al. and Beharie et al. are not relied upon to explicitly teach all of the one or more production factors comprise noise.
[AltContent: textbox (Din et al. Fig. 2, showing battery fault images.)]
PNG
media_image3.png
346
584
media_image3.png
Greyscale
However, Din et al. teach wherein the one or more production factors comprise one or more of inputs, noise, process changes, or a combination thereof ("The Empirical Mode Decomposition (EMD) approach was initially used to extract features from batteries by decomposing the battery voltage signals and reducing noise during this process. The collected features were then utilized to calculate the sample entropy values for fault detection [26]," Section 2, paragraph 4).
Therefore, taking the teachings of Weiss et al., Beharie et al. and Din et al. as a whole, it would have been obvious to a person having ordinary skill in the art before the time of the effective filing date of the claimed invention of the instant application to modify “Method for Predicting Defects in Assembly Units” as taught by Weiss et al. and “Systems and methods for Generating Explainable Predictions” as taught by Beharie et al. to use “Automated Battery Making Fault Classification Using Over-Sampled Image Data CNN Features” as taught by Din et al. The suggestion/motivation for doing so would have been that, “The battery faults and warning signs were detected by Xiong et al. [12] using a rule based and probabilistic-based method. Errors in the real-time monitoring system, both at room and high temperatures, were predicted by their analysis.” as noted by the Din et al. disclosure in Section 1, paragraph 3, which also motivates combination because the combination would predictably have a better explainability as there is a reasonable expectation that there is a source for errors and that source is better to be known; and/or because doing so merely combines prior art elements according to known methods to yield predictable results.
Claim 7
Regarding claim 7, Weiss et al. teach the computerized method of claim 6, wherein the process changes comprise a change to at least one of a date and time of production, an operator, a tool, a production, or a combination thereof ("By also identifying a set of features common to a first set of assembly units exhibiting a defect but not common to (e.g., excluded from) a second set of assembly units not exhibiting this defect, the system can filter a relatively large feature set down to a compressed feature set exhibiting a greater likelihood of producing the defect, as shown in FIG. 2. By scanning inspection images of other assembly units----of the same or different assembly type-for similarity to this compressed feature set, the system can detect or predict similar defects in these other assembly units even if the source of the defect is not immediately known to an engineer," paragraph [0026] where the compressed feature set is the process changes).
Claim 8
Regarding claim 8, Weiss et al. teach the computerized method of claim 5, as noted above.
Weiss et al. and Beharie are not relied upon to explicitly teach all of features relate to cell tab welds.
However, Din et al. teach wherein the product comprises a vehicle high-voltage battery pack ("using image processing and machine learning techniques to automatically detect faults in the battery manufacturing process," abstract) and the one or more features relate to cell tab welds for cells within the vehicle high-voltage battery pack ("The important faults in the battery making process are burning the positive or negative terminals, welding too high, the wrong welding, welding holes, a lack of welding, the wrong cover, continuous holes, and shifting the terminals," Section 1, paragraph 1).
Weiss et al., Beharie et al. and Din et al. are combined as per claim 6.
Claim 14
Regarding claim 14, Weiss et al. teach the system of claim 10, as noted above.
Weiss et al. and Beharie are not relied upon to explicitly teach all of production factors comprising noise.
However, Din et al. teach wherein the one or more production factors comprises one or more of inputs, noise, process changes, or a combination thereof ("The Empirical Mode Decomposition (EMD) approach was initially used to extract features from batteries by decomposing the battery voltage signals and reducing noise during this process. The collected features were then utilized to calculate the sample entropy values for fault detection [26]," Section 2, paragraph 4).
Weiss et al., Beharie et al. and Din et al. are combined as per claim 6.
Claim 15
Regarding claim 15, Weiss et al. teach the system of claim 14, as noted above.
Weiss et al. and Beharie are not relied upon to explicitly teach all of process changes.
However, Din et al. teach wherein the process changes comprise a change to at least one of a date and time of production, an operator, a tool, a production, or a combination thereof ("By also identifying a set of features common to a first set of assembly units exhibiting a defect but not common to (e.g., excluded from) a second set of assembly units not exhibiting this defect, the system can filter a relatively large feature set down to a compressed feature set exhibiting a greater likelihood of producing the defect, as shown in FIG. 2. By scanning inspection images of other assembly units----of the same or different assembly type-for similarity to this compressed feature set, the system can detect or predict similar defects in these other assembly units even if the source of the defect is not immediately known to an engineer," paragraph [0026] where the compressed feature set is the process changes).
Weiss et al., Beharie et al. and Din et al. are combined as per claim 6.
Claim 16
Regarding claim 16, Weiss et al. teach the system of claim 10, as noted above.
Weiss et al. and Beharie are not relied upon to explicitly teach all of cell tab welds.
However, Din et al. teach wherein the products comprise a vehicle high-voltage battery pack ("using image processing and machine learning techniques to automatically detect faults in the battery manufacturing process," abstract) and the one or more features relate to cell tab welds for cells within the vehicle high-voltage battery pack ("The important faults in the battery making process are burning the positive or negative terminals, welding too high, the wrong welding, welding holes, a lack of welding, the wrong cover, continuous holes, and shifting the terminals," Section 1, paragraph 1).
Weiss et al., Beharie et al. and Din et al. are combined as per claim 6.
Claim 20
Regarding claim 20, Weiss et al. teach the one or more non-transitory computer-readable media of claim 18, preprocess the plurality of images, wherein the preprocessing comprises centering and cropping each image of the plurality of images on a region of interest and masking out other regions of each of the images corresponding to noise ("highlight or crop regions of these inspection images containing features corresponding to this subset of feature dimensions," paragraph [0109]) as noted above.
Weiss et al. and Beharie are not relied upon to explicitly teach all of cell tab welds.
However, Din et al. teach wherein the products comprise a vehicle high-voltage battery pack ("using image processing and machine learning techniques to automatically detect faults in the battery manufacturing process," abstract) and the one or more features relate to cell tab welds for cells within the vehicle high-voltage battery pack ("The important faults in the battery making process are burning the positive or negative terminals, welding too high, the wrong welding, welding holes, a lack of welding, the wrong cover, continuous holes, and shifting the terminals," Section 1, paragraph 1).
Weiss et al., Beharie et al. and Din et al. are combined as per claim 6.
Reference Cited
The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure.
US Patent Publication 2023 0281959 A1 to Hoshen et al. discloses receiving, as input, a target image; extracting (i) a set of feature representations from a plurality of image locations within each of the training images, and (ii) target feature representations from a plurality of target image locations within the target image; calculating, with respect to a target image location of the plurality of target image locations in the target image, a distance between (iii) the target feature representation of the target image location, and (iv) a subset from the set of feature representations comprising the k nearest the feature representations to the target feature representation; and determining that the target image location is anomalous, when the calculated distance exceeds a predetermined threshold.
US Patent Publication 2020 0005422 A1 to Subramanian et al. discloses using images for automatic visual inspection with machine learning are disclosed. A particular embodiment includes an inspection system to: train a machine learning system to detect defects in an object based on training with a set of training images including images of defective and non-defective objects; enable a user to use a camera to capture a plurality of images of an object being inspected at different poses of the object; and detect defects in the object.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HEATH E WELLS whose telephone number is (703)756-4696. The examiner can normally be reached Monday-Friday 8:00-4:00.
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, Ms. Jennifer Mehmood can be reached on 571-272-2976. 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.
/H.E.W/Examiner, Art Unit 2664
Date: 8 April 2026
/JENNIFER MEHMOOD/Supervisory Patent Examiner, Art Unit 2664
Prosecution Insights