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 .
DETAILED ACTION
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 3/16/2026 has been entered.
Response to Amendment
Applicant’s amendment filed on 3/16/2026 has been entered. Claims 1-20 are still pending in this application.
Response to Arguments
2. Applicant’s amendment filed on 3/16/2026 overcome the all rejections and objections set forth in the previous Office Action.
Applicant’s arguments, filed on 3/16/2026 have been fully considered and are persuasive.
Allowable Subject Matter
3. Claims 1-13 and 20 are allowed over the prior art of record.
The following is an examiner’s statement of reasons for allowance:
The prior art fails to teach Claim 8, alone or in reasonable combination, which specifically comprise the following limitations (in consideration of the claim as a whole):
-wherein executing the training of the defect detection model further comprises: generating a quality score of defect image data that is output from the trained defect detection model; determining whether to continue the training of the defect detection model by determining a degree of the training for each label with the quality score, wherein the determining whether to continue the training comprises: continuing to train on a label where the quality score does not reach a second threshold value, and ending training on a label where the quality score reaches the second threshold value.
The closest prior art, Bachiraju (US 20220334567) reveals a similar system, but fails to anticipate or render obvious, either singularly or in combination with the other cited references, the above limitations (as combined with the other claimed limitations).
The claim 1 is the method claim, corresponding to the apparatus claim 8 and is thus allowed for the same reasons as for the claim 1.
The claims 2-7 and 20 depend on the claim 1 and are thus allowed for the same reasons as for the claim 1.
The claims 9-13 depend on the claim 8 and are thus allowed for the same reasons as for the claim 8.
Any comments considered necessary by applicant must be submitted no later than the payment of the issue fee and, to avoid processing delays, should preferably accompany the issue fee. Such submissions should be clearly labeled “Comments on Statement of Reasons for Allowance.”
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 14 and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Bachiraju (US 20220334567) in view of Leung et al. (US 8370282) and Verma et al. (US 20230281518)
Regarding claim 14, (Currently Amended) Bachiraju teaches a processor-implemented method, the method comprising: randomly assigning a defect label to a determined unknown detected defect type not among defect types in a training data set(p0042: defect patterns and p0044: a pattern library may be built based on the recognized patterns…the new patterns for the fingerprint library may be identified automatically based on the WIP data and inspection data, );
Bachiraju does not teach generating an importance score for the unknown detected defect type; selectively training a machine learning model using the unknown detected defect type when the importance score meets a first threshold value; and deleting the unknown detected defect type from the training data set when the importance score fails to meet the first threshold value
Verma teaches deleting the unknown detected defect type from the training data set when the importance score fails to meet the first threshold value(p0048:Based on the scores associated with the second machine learning models, at least one hardware processor 402 may determine whether the first data set is to be discarded or kept for training the first machine learning model…not meet a threshold quality (e.g., according to an agreement with other models) can be discarded.).
Bachiraju and Verma combinable because they both deal with data training. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the application to combine the teachings of Bachiraju with the teaching of Verna to be able to select only components of data deemed to be good and reliable, for use in federated learning (p0002).
Regarding claim 19, Bachiraju teaches the method of claim 14, further comprising using the trained model to detect another defect that is determined to be a known defect type (p0011: machine learning model, generating an indication of a type of defect represented in the wafer map).
Claim 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Bachiraju in view of Verna as applied to claim 14 above, and further in view of Johnson et al. (US 20210178752)
Regarding claim 15, Bachiraju in view of Verna does not teach the apparatus of claim 8, wherein the generating of the importance score is based on one of a determined predefined frequency of occurrence of the defect data and a determined distribution of each pattern of a data set related to the defect data.
Johnson teaches wherein the generating of the importance score is based on one of a determined predefined frequency of occurrence of the defect data and a determined distribution of each pattern of a data set related to the defect data (p0040: calculate a persistency score based on the recency (e.g., time from the historical data) and the frequency of occurrence (sometimes referred to as frecency) to determine whether the defect is persistent).
Bachiraju in view of Verma and Johnson are combinable because they both deal with AI model training. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the application to combine the teachings of Bachiraju in view of Verma with the teaching of Johnson for purpose of providing a maintenance system of a printer automatically determines the next cleaning action.
Claim 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Bachiraju in view of Verma as applied to claim 14 above, and further in view of Hirai et al. (US 20220292317).
Regarding claim 16, Bachiraju in view of Verma does not teach the method of claim 14, wherein the method further comprises performing a knowledge distillation of a corresponding pattern of the unknown detected defect type to add the corresponding pattern to the training data set when the importance score meets the first threshold.
Hirai teaches wherein the method further comprises performing a knowledge distillation of a corresponding pattern of the unknown detected defect type to add the corresponding pattern to the training data set when the importance score meets the first threshold (p0082: is the threshold or more, the first real image, the reference image and the reliability, which are input to the trained model, may be added as training data, and may be applied to the training of the machine learning model.)
Bachiraju in view of Verma and Hirai are combinable because they both deal with training data set. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the application to combine the teachings of Bachiraju in view of Verma with the teaching of Hirai for purpose to training a neural network to detect defects.
Claims 17 and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Bachiraju in view of Verma applied to claim 14 above, and further in view of Lester et al. (US 20240202605).
Regarding claim 17, Bachiraju in view of Verma does not teach the apparatus of claim 8, wherein the assigning of the label includes: performing a clustering algorithm and a k-nearest neighbors (k-NN) algorithm; and assigning a random label to the detected defect pattern dependent on result of the clustering algorithm and the k-nearest neighbors (k-NN) algorithm.
Lester teaches performing a clustering algorithm and a k-nearest neighbors (k-NN) algorithm; and assigning a random label to the detected defect pattern dependent on result of the clustering algorithm and the k-nearest neighbors (k-NN) algorithm (p0043). clustering the plurality of defects based on respective similarity values (Lester: p0044: clustering module 206 may determine a similarity metric between each unlabeled training example and each labeled training example based on the feature values associated with the training examples (e.g., using least-squared error).
Bachiraju in view of Verma and Lester are combinable because they both deal with AI training data set . Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the application to combine the teachings of Bachiraju in view of Verma with the teaching of Lester for purpose of maintaining accurate physician taxonomy data (p0005).
Regarding claim 18, Bachiraju in view of Verma and Lester teaches the method of claim 17, wherein the random assigning of the defect label is based on a respective similarity value between the unknown detected defect types and a respective defect type of the plurality of defect types having a similar similarity value (Lester: p0044).
Response to Arguments
Applicant's arguments with respect to claims have been considered.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HELEN Q ZONG whose telephone number is (571)270-1600. The examiner can normally be reached Mon-Fri 9-6.
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, Abderrahim Merouan can be reached at 5712705254. 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.
HELEN ZONG
Primary Examiner
Art Unit 2683
/HELEN ZONG/ Primary Examiner, Art Unit 2683