DETAILED ACTION
Final Rejection
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 Amendment
Applicant’s amendments, filed 09/09/2025 to claims are accepted. In this amendment, claims 1, 10 and 14 has been amended, Claims 16-20: added and claim 15: cancelled.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-14 and 16-20 are rejected under 35 U.S.C. § 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1
Each of claims1-14 and 16-20 falls within one of the four statutory categories. See MPEP § 2106.03. For example, each of claims 1-14 and 16-20 fall within category of process.
Regarding Claims 1-9
Step 2A – Prong 1
Exemplary claim 1 is directed to an abstract idea of identifying a flaw.
The abstract idea is set forth or described by the following italicized limitations:
1. A computerized method of automatically identifying a flaw in a material during an inspection using a trained machine learning model, the method comprising:
obtaining flaw detection information acquired at least in part by applying at least one non-destructive testing (NDT) modality to the material;
applying the flaw detection information to the trained machine learning model to automatically associate the flaw with a cluster of similar flaws, wherein the machine learning model was trained by first performing clustering on the flaw detection information before receiving a tag that assigns a name to the cluster; and
generating a flaw identification output based on the association, and
configuring at least one production parameter in response to the flaw identification output.
The italicized limitations above represent mental steps (i.e., a process that can be performed by can be performed mentally and/or with pen and paper). Therefore, the italicized limitations fall within the subject matter groupings of abstract ideas enumerated in Section I of the 2019 Revised Patent Subject Matter Eligibility Guidance.
For example, the limitations “generating a flaw identification output based on the association; configuring at least one production parameter in response to the flaw identification output” is mental step (i.e., a process that can be performed by can be performed mentally and/or with pen and paper or a mental judgment), see 2106.04(a)(2).
Step 2A – Prong 2
Claims 1 does not include additional elements (when considered individually, as an ordered combination, and/or within the claim as a whole) that are sufficient to integrate the abstract idea into a practical application.
For example, additional first element is “obtaining flaw detection information acquired at least in part by applying at least one non-destructive testing (NDT) modality to the material” to be performed, at least in-part, these additional elements appear to only add insignificant extra-solution activity (e.g., data gathering) and only generally link the abstract idea to a particular field. Therefore, this element individually or as a whole does not provide a practical application. See MPEP 2106.05(g).
The 2nd additional element is “applying the flaw detection information to the trained machine learning model to automatically associate the flaw with a cluster of similar flaws, wherein the machine learning model was trained by first performing clustering on the flaw detection information before receiving a tag that assigns a name to the cluster” to be performed, at least in-part, these additional elements appear to only add insignificant extra-solution activity (e.g., data gathering) and only generally link the abstract idea to a particular field. Therefore, this element individually or as a whole does not provide a practical application. See MPEP 2106.05(g).
The 3rd additional element is “A computerized method of automatically identifying a flaw in a material during an inspection using a trained machine learning model”. This element amounts to mere use of a generic computer system with high level of generality, which is well understood routine and conventional (see background of current discloser and IDS and PTO 892) and this element individually does not provide a practical application. In view of the above, the “additional element” individually or combine does not provide a practical application of the abstract idea. see MPEP 2106.05(d).
In view of the above, the three “additional elements” individually do not provide a practical application of the abstract idea. Furthermore, the “additional elements” in combination amount to a plurality of generic devices with software, where such computers and software amount to mere instructions to implement the abstract idea on a computer(s) and/or mere use of a generic computer component(s) as a tool to perform the abstract idea. Therefore, these elements in combination do not provide a practical application. The combination of additional elements does no more than generally link the use of the abstract idea to a particular technological environment, and for this additional reason, the combination of additional elements does not provide a practical application of the abstract idea.
Step 2B
Claims1 does not include additional elements, when considered individually and as an ordered combination, that are sufficient to amount to significantly more than the abstract idea. For example, the limitation of Claim 1 is an additional element that is, i.e. “ non-destructive testing (NDT) modality to the material”, generic device, which is well understood, routine and convention (see background of current discloser and IDS and PTO 892) and MPEP 2106.05(d)).
The reasons for reaching this conclusion are substantially the same as the reasons given above in § Step 2A – Prong 2. For brevity only, those reasons are not repeated in this section. See MPEP §§ 2106.05(g) and MPEP §§2106.05(II).
.
Dependent Claims 2-9
Dependent claims 2-9 fails to cure this deficiency of independent claim 1 (set forth above) and are rejected accordingly. Particularly, claims 2-9 recite limitations that represent (in addition to the limitations already noted above) either the abstract idea or generic data collection device or an additional element that is merely extra-solution activity, mere use of instructions and/or generic computer component(s) as a tool to implement the abstract idea, and/or merely limits the abstract idea to a particular technological environment.
For example, the limitations of Claims 2-9 are insignificant extra-solution activity (e.g., data gathering) with generic sensor components.
.
Regarding Claims 10-14 and 16-20
Step 2A – Prong 1
Exemplary claim 10 is directed to an abstract idea of identifying a flaw.
The abstract idea is set forth or described by the following italicized limitations:
10. A computerized method of training processing circuitry using machine learning to identify a flaw in a material during an inspection, the method comprising:
training a machine learning model by first performing clustering on flaw detection information acquired at least in part by applying at least one non-destructive testing (NDT) modality to the material to group together similar flaws into clusters;
receiving tags for the clusters after the clusters are formed;
associating the received tags with corresponding clusters to generate classification rules for flaw identification; and
configuring the classification rules to enable automatic adjustment of at least one production parameter in response to flaw identification during subsequent inspections.
The italicized limitations above represent mental steps (i.e., a process that can be performed by can be performed mentally and/or with pen and paper). Therefore, the italicized limitations fall within the subject matter groupings of abstract ideas enumerated in Section I of the 2019 Revised Patent Subject Matter Eligibility Guidance.
For example, the limitations “to perform clustering on flaw detection information; configuring the classification rules” is mental step (i.e., a process that can be performed by can be performed mentally and/or with pen and paper or a mental judgment), see 2106.04(a)(2).
Step 2A – Prong 2
Claims 10 does not include additional elements (when considered individually, as an ordered combination, and/or within the claim as a whole) that are sufficient to integrate the abstract idea into a practical application.
For example, additional first element is “training a machine learning model by first performing clustering on flaw detection information acquired at least in part by applying at least one non-destructive testing (NDT) modality to the material to group together similar flaws into clusters; receiving tags for the clusters after the clusters are formed; associating the received tags with corresponding clusters to generate classification rules for flaw identification” to be performed, at least in-part, these additional elements appear to only add insignificant extra-solution activity (e.g., data gathering) and only generally link the abstract idea to a particular field. Therefore, this element individually or as a whole does not provide a practical application. See MPEP 2106.05(g).
The 2nd additional element is “a computerized method of training processing circuitry using machine learning to identify a flaw in a material during an inspection”. This element amounts to mere use of a generic computer system with high level of generality, which is well understood routine and conventional (see background of current discloser and IDS and PTO 892) and this element individually does not provide a practical application. In view of the above, the “additional element” individually or combine does not provide a practical application of the abstract idea. see MPEP 2106.05(d).
In view of the above, the two “additional elements” individually do not provide a practical application of the abstract idea. Furthermore, the “additional elements” in combination amount to a plurality of generic devices with software, where such computers and software amount to mere instructions to implement the abstract idea on a computer(s) and/or mere use of a generic computer component(s) as a tool to perform the abstract idea. Therefore, these elements in combination do not provide a practical application. The combination of additional elements does no more than generally link the use of the abstract idea to a particular technological environment, and for this additional reason, the combination of additional elements does not provide a practical application of the abstract idea.
.
Step 2B
Claims10 does not include additional elements, when considered individually and as an ordered combination, that are sufficient to amount to significantly more than the abstract idea. For example, the limitation of Claim 1 is an additional element that is, i.e. “ non-destructive testing (NDT) modality to the material”, generic device, which is well understood, routine and convention (see background of current discloser and IDS and PTO 892) and MPEP 2106.05(d)).
The reasons for reaching this conclusion are substantially the same as the reasons given above in § Step 2A – Prong 2. For brevity only, those reasons are not repeated in this section. See MPEP §§ 2106.05(g) and MPEP §§2106.05(II).
.
Dependent Claims 11-14 and 16-20
Dependent claims 11-14 and 16-20 fails to cure this deficiency of independent claim 1 (set forth above) and are rejected accordingly. Particularly, claims 11-14 and 16-20 recite limitations that represent (in addition to the limitations already noted above) either the abstract idea or generic data collection device or an additional element that is merely extra-solution activity, mere use of instructions and/or generic computer component(s) as a tool to implement the abstract idea, and/or merely limits the abstract idea to a particular technological environment.
For example, the limitations of Claims 11-14 and 16-20 are insignificant extra-solution activity (e.g., data gathering).
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)(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.
Claim(s) 1, 5-10, 16-17 and 20 is/are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Hasanian et al. (US 2021/0365016).
Regarding Claim 1. Hasanian teaches a computerized method of automatically identifying (307: fig. 3) a flaw in a material during an inspection using a trained machine learning model(figs. 1, 3; [0040], Machine learning models and processes may be trained using the features: [0050]),
the method comprising: obtaining flaw detection information acquired at least in part by applying at least one non-destructive testing (NDT) modality(105-106: fig.1) to the material(the NDT tools 106, such as laser ultrasonic testing, may be initiated to start a thorough inspection of the latest layers to look for possible flaws which could be associated with the received acoustic emissions: [0040]);
applying the flaw detection information to the trained machine learning model to automatically associate the flaw with a cluster of similar flaws(118: fig. 1; AE sensor data only or may be a combination of different types of sensor data, and may utilize a classifier to classify the patterns as being indicative of normal printing operations (i.e., no defect or anomaly detected) or as being indicative of a defect; . Classifiers utilized by the machine learning processes of embodiments may include experience-based classifiers, statistical classifiers, both experience-based and statistical classifiers, or other types/combinations of classifiers: [0031]; providing valuable data for the machine learning data clustering toolbox:[0034], [0040]), wherein the machine learning model was trained by first performing clustering on the flaw detection information before receiving a tag that assigns a name to the cluster(which enables the control system 102 to spot anomalies, and detected anomalies may be marked as different flaws or defects by classification and clustering data analysis. One of the outputs of the decision-making logic 118 may be a classified dataset where data is marked with different pre-known phenomena, conditions, or marked as an unknown cluster. After analyzing the data, decision-making unit 118 can determine a proper response (e.g., change a temperature of the AM process, a material deposition rate, halt/pause the AM process, cancel the AM process, etc.), which may be applied to the AM system 101 via the printer-controller 119. At some points, user device 103 may be asked to assist the control system 102 to mark the best class for a detected anomaly: [0034]);
generating a flaw identification output based on the association (detected anomalies may be marked as different flaws or defects by classification and clustering data analysis. One of the outputs of the decision-making logic 118 may be a classified dataset where data is marked with different pre-known phenomena, conditions, or marked as an unknown cluster: [0034]; NDT tools 106, such as laser ultrasonic testing, may be initiated to start a thorough inspection of the latest layers to look for possible flaws which could be associated with the received acoustic emissions. This can lead to evaluating the severity of the occurred flaws and providing valuable data for the machine learning data clustering toolbox: [0040], [0050]); and
configuring at least one production parameter in response to the flaw identification output([0008], [0035]).
Regarding Claim 5. Hasanian further teaches the flaw identification output includes a type of flaw (control system 102 to spot anomalies, and detected anomalies may be marked as different flaws or defects by classification and clustering data analysis: [0034]).
Regarding Claim 6. Hasanian further teaches the type of flaw includes at least one of a crack, a porosity, or no flaw (a classifier to classify the patterns as being indicative of normal printing operations (i.e., no defect or anomaly detected) or as being indicative of a defect: [0031],[0034] [0037]).
Regarding Claim 7. Hasanian further teaches the flaw identification output includes a probability of the identified flaw (a probability of defect or anomaly formation may be calculated, and the detected anomaly/defect may be compared to one or more defined thresholds:[0043], [0046]).
Regarding Claim 8. Hasanian further teaches storing data related to the flaw detection information in a database(117: fig. 1; [0032], [0038]).
Regarding Claim 9. Hasanian further teaches storing data related to the flaw detection information in a database includes: storing data related to the flaw detection information in the database when a condition is satisfied (, the one or more database 117 may include sensor data that may be used to detect or predict the occurrence of defects during a manufacturing process: [0032]-[0033]).
Regarding Claim 10. Hasanian teaches a computerized method of training processing circuitry using machine learning to identify a flaw in a material during an inspection, the method comprising (figs. 1, 3-4; [0030],[0040],[0050])
training a machine learning model ([0030]) by first performing clustering on flaw detection information acquired at least in part by applying at least one non-destructive testing (NDT) modality (101: fig. 1) to the material to group together similar flaws into clusters(classification and clustering data analysis:[0034]);
receiving tags for the clusters after the clusters are formed (marked as an unknown cluster((classification and clustering data analysis, unknown cluster, the control system 102 to mark the best class for a detected anomaly::[0034]);
associating the received tags with corresponding clusters to generate classification rules for flaw identification (which enables the control system 102 to spot anomalies, and detected anomalies may be marked as different flaws or defects by classification and clustering data analysis. One of the outputs of the decision-making logic 118 may be a classified dataset where data is marked with different pre-known phenomena, conditions, or marked as an unknown cluster. After analyzing the data, decision-making unit 118 can determine a proper response (e.g., change a temperature of the AM process, a material deposition rate, halt/pause the AM process, cancel the AM process, etc.), which may be applied to the AM system 101 via the printer-controller 119. At some points, user device 103 may be asked to assist the control system 102 to mark the best class for a detected anomaly: [0034]; detected anomalies may be marked as different flaws or defects by classification and clustering data analysis. One of the outputs of the decision-making logic 118 may be a classified dataset where data is marked with different pre-known phenomena, conditions, or marked as an unknown cluster: [0034]; NDT tools 106, such as laser ultrasonic testing, may be initiated to start a thorough inspection of the latest layers to look for possible flaws which could be associated with the received acoustic emissions. This can lead to evaluating the severity of the occurred flaws and providing valuable data for the machine learning data clustering toolbox: [0040], [0050]); and
configuring the classification rules to enable automatic adjustment of at least one production parameter in response to flaw identification during subsequent inspections ([0008], [0035]).
Regarding Claim 16: Hasanian further teaches setting detection thresholds for the at least one NDT modality during acquisition of the flaw detection information (the NDT tools 106, such as laser ultrasonic testing, may be initiated to start a thorough inspection of the latest layers to look for possible flaws which could be associated with the received acoustic emissions: [0039]; acoustic emission data acquisition methods are hit based (e.g., when a waveform is higher than a threshold), and/or different time interval-period casting strategies: [0029]).
Regarding Claim 17: Hasanian further teaches the flaw detection information is acquired from multiple NDT modalities, and wherein the training further comprises:
performing position-based agglomeration to merge flaw detection information from multiple NDT modalities based on spatial relationships of detected flaws in the material (Machine learning models and processes may be trained using the features extracted during the controlled print and used to analyze production or non-test runs of AM processes. The features corresponding to the defect may be saved as a signature that may be used to detect defects during production of structures via AM manufacturing processes:[0048],[0050]; Upon determining the desired features, coefficients and optimized weights can be calculated by exposing and training the models to generate data of multiple experiments (e.g., multiple controlled prints under the same operating parameters and conditions). As signatures and features of importance are identified, the method 400 may include updating data processing parameters, at step 408. This may include updating the designed toolboxes and related coefficients used to monitor AM processes (e.g., for deployment in non-test run scenarios). Where no important features/signatures are detected, the AM process may proceed to block 407 and the training may continue (e.g., if the training AM process is not complete) or may end.[0053]) ).
Regarding Claim 20: Hasanian further teaches generating classification rules for automatically adjusting at least one production parameter based on the flaw identification ([0008], [0035]).
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) 2 and 11 is/are rejected under 35 U.S.C. 103 as being unpatentable over Hasanian et al. (US 2021/0365016) in view of Smet et al. (US 2012/0074932).
Regarding Claims 2 and 11. Hasanian further teaches a sensor system with other types of sensors ([0017]).
Hasanian silent about the at least one NDT modality includes Eddy current testing.
However, Smet the at least one NDT modality includes Eddy current testing(abstract)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to the invention of Hasanian, Hasanian’s one of the other sensors modified by Eddy current, as taught by Smet, so as to enables the detection of the defects in non accessible or difficult accessible zone of the metallic structure of the aircraft in automatic, rapid, robust and rapid manner..
Claim(s) 3 and 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Hasanian et al. (US 2021/0365016) in view of St-laurent et al. (US 2018/0113100)
Regarding Claims 3 and 12. Hasanian further teaches a sensor system with other types of sensors ([0017])
Hasanian silent about the at least one NDT modality includes phased array ultrasonic testing.
However, St-laurent teaches the at least one NDT modality includes phased array ultrasonic testing([0001]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to the invention of Hasanian, Hasanian’s one of the other sensors modified by phased array ultrasonic, as taught by St-laurent, so as to enables the ultrasonic inspection system, which is simple, convenient and reliable, and has no loss of precision or safety..
Claim(s) 4 and 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Hasanian et al. (US 2021/0365016) in view of Bourgelas (US 2015/0049108)
Regarding Claims 4 and 13. Hasanian further teaches a sensor system with other types of sensors ([0017]).
Hasanian silent about the at least one NDT modality includes Eddy current testing and phased array ultrasonic testing.
However, Bourgelas teaches the at least one NDT modality includes Eddy current testing and phased array ultrasonic testing([0003]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to the invention of Hasanian, Hasanian’s one of the other sensors modified by phased array ultrasonic and eddy current detection system, as taught by Bourgelas, so as to enables the detection of the defects in automatic, rapid, robust and rapid manner.
Claim(s) 14 and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Hasanian et al. (US 2021/0365016) in view of Hall et al. (US 20170234837).
Regarding Claim 14. Hasanian silent about the training includes: performing a dimensionality reduction technique to group together the similar flaws into cluster.
However, Hall teaches the training includes: performing a dimensionality reduction technique to group together the similar flaws into cluster ([0109],[0111], fig. 12(b)).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to the invention of Hasanian, the training includes: performing a dimensionality reduction technique to group together the similar flaws into cluster, as taught by Hall, so as to facilitate more accurate fault location within any subsequent online AE condition monitoring system, during scheduled NDT maintenance during the parts lifecycle (e.g. by comparisons with the TDOA data during manufacture), or for more accurate diagnosis of fault conditions.
Regarding Claim 19. Hasanian silent about performing clustering comprises: applying principal component analysis (PCA) to reduce a dimensionality of the flaw detection information before grouping the similar flaws into clusters.
However, Hall teaches performing clustering comprises: applying principal component analysis (PCA) to reduce a dimensionality of the flaw detection information before grouping the similar flaws into clusters([0109]-[0111]; fig. 12(a)).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to the invention of Hasanian, performing clustering comprises: applying principal component analysis (PCA) to reduce a dimensionality of the flaw detection information before grouping the similar flaws into clusters, as taught by Hall, so as to facilitate more accurate fault location within any subsequent online AE condition monitoring system, during scheduled NDT maintenance during the parts lifecycle (e.g. by comparisons with the TDOA data during manufacture), or for more accurate diagnosis of fault conditions.
Examiner Notes
Regarding claim 18, There is no prior art rejection over claims, however there is 101 rejections (specifically, the limitation is “sampling the flaw detection information in a database when a confidence level for flaw classification is above a threshold”),
Response to Argument
Applicant’s arguments with respect 101 rejection, specially claim 1, the applicant did not agree with it., see pages 5-6.
The Applicant argus that “the claims are patent-eligible under 35 U.S.C. § 101 because they are directed to a practical application that improves the functioning of manufacturing equipment and the quality of produced materials, rather than to an abstract idea alone”.
In response, the Examiner respectfully disagree because the claims (specifically 1 and 10) limitations represent mental steps (i.e., a process that can be performed by can be performed mentally and/or with pen and paper). Therefore, the italicized limitations fall within the subject matter groupings of abstract ideas enumerated in Section I of the 2019 Revised Patent Subject Matter Eligibility Guidance. Step 2A – Prong 2: Claims do not include additional elements (when considered individually, as an ordered combination, and/or within the claim as a whole) that are sufficient to integrate the abstract idea into a practical application. For example, additional first element is “obtaining flaw detection information acquired at least in part by applying at least one non-destructive testing (NDT) modality to the material” to be performed, at least in-part, these additional elements appear to only add insignificant extra-solution activity (e.g., data gathering) and only generally link the abstract idea to a particular field. Therefore, this element individually or as a whole does not provide a practical application. See MPEP 2106.05(g). The 2nd additional element is “applying the flaw detection information to the trained machine learning model to automatically associate the flaw with a cluster of similar flaws, wherein the machine learning model was trained by first performing clustering on the flaw detection information before receiving a tag that assigns a name to the cluster” to be performed, at least in-part, these additional elements appear to only add insignificant extra-solution activity (e.g., data gathering) and only generally link the abstract idea to a particular field. Therefore, this element individually or as a whole does not provide a practical application. See MPEP 2106.05(g). The 3rd additional element is “A computerized method of automatically identifying a flaw in a material during an inspection using a trained machine learning model”. This element amounts to mere use of a generic computer system with high level of generality, which is well understood routine and conventional (see background of current discloser and IDS and PTO 892) and this element individually does not provide a practical application. In view of the above, the “additional element” individually or combine does not provide a practical application of the abstract idea. see MPEP 2106.05(d). In view of the above, the three “additional elements” individually do not provide a practical application of the abstract idea. Furthermore, the “additional elements” in combination amount to a plurality of generic devices with software, where such computers and software amount to mere instructions to implement the abstract idea on a computer(s) and/or mere use of a generic computer component(s) as a tool to perform the abstract idea. Therefore, these elements in combination do not provide a practical application. The combination of additional elements does no more than generally link the use of the abstract idea to a particular technological environment, and for this additional reason, the combination of additional elements does not provide a practical application of the abstract idea. Step 2B:Claims1 does not include additional elements, when considered individually and as an ordered combination, that are sufficient to amount to significantly more than the abstract idea. For example, the limitation of Claim 1 is an additional element that is, i.e. “ non-destructive testing (NDT) modality to the material”, generic device, which is well understood, routine and convention (see background of current discloser and IDS and PTO 892) and MPEP 2106.05(d)). The reasons for reaching this conclusion are substantially the same as the reasons given above in § Step 2A – Prong 2. For brevity only, those reasons are not repeated in this section. See MPEP §§ 2106.05(g) and MPEP §§2106.05(II). As such 101 rejection is maintained.
Applicant’s arguments with respect 102 rejection, specially claim 1, the applicant did not agree with it., see pages 6-9.
The Applicant argus that Hasanian relies on "pre-known phenomena" and "conditions" that are already tagged before the clustering analysis occurs. This is a hallmark of conventional machine learning techniques, where classification/tagging precedes clustering, which is the opposite of the sequence in claim 1.”.
In response, the Examiner respectfully disagree because Hasanian teaches AE sensor data only or may be a combination of different types of sensor data, and may utilize a classifier to classify the patterns as being indicative of normal printing operations (i.e., no defect or anomaly detected) or as being indicative of a defect; . Classifiers utilized by the machine learning processes of embodiments may include experience-based classifiers, statistical classifiers, both experience-based and statistical classifiers, or other types/combinations of classifiers: [0031]; providing valuable data for the machine learning data clustering toolbox:[0034], [0040]), One of the outputs of the decision-making logic 118 may be a classified dataset where data is marked as an unknown cluster. control system 102 to spot anomalies, and detected anomalies may be marked as different flaws or defects by classification and clustering data analysis: [0034]). The Examiner considered “unknown cluster” to be unmarked cluster and after that marked as different flaws. As such 102 rejection is maintained.
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.
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
a) Asbag et al. (US 2019/0333208) disclose there are provided system and method of classifying defects in a specimen. The method includes: obtaining one or more defect clusters detected on a defect map of the specimen, each cluster characterized by a set of cluster attributes comprising spatial attributes including spatial density indicative of density of defects in one or more regions accommodating the cluster, each given defect cluster being detected at least based on the spatial density thereof meeting a criterion; for each cluster, applying a cluster classifier to a respective set of cluster attributes thereof to associate the cluster with one or more labels of a predefined set of labels, wherein the cluster classifier is trained using cluster training data; and identifying DOI in each cluster by performing a defect filtration for each cluster using one or more filtering parameters specified in accordance with the label of the cluster.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MOHAMMAD K ISLAM whose telephone number is (571)270-0328. The examiner can normally be reached M-F 9:00 a.m. - 5:00 p.m..
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Shelby A Turner can be reached at 571-272-6334. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/MOHAMMAD K ISLAM/Primary Examiner, Art Unit 2857