Prosecution Insights
Last updated: April 19, 2026
Application No. 18/268,924

DATA-DRIVEN PREDICTION AND IDENTIFICATION OF FAILURE MODES BASED ON WAFER-LEVEL ANALYSIS AND ROOT CAUSE ANALYSIS FOR SEMICONDUCTOR PROCESSING

Non-Final OA §103
Filed
Jun 21, 2023
Examiner
SAFAIPOUR, BOBBAK
Art Unit
2665
Tech Center
2600 — Communications
Assignee
ASML Netherlands B.V.
OA Round
3 (Non-Final)
86%
Grant Probability
Favorable
3-4
OA Rounds
2y 8m
To Grant
97%
With Interview

Examiner Intelligence

Grants 86% — above average
86%
Career Allow Rate
933 granted / 1085 resolved
+24.0% vs TC avg
Moderate +11% lift
Without
With
+10.7%
Interview Lift
resolved cases with interview
Typical timeline
2y 8m
Avg Prosecution
30 currently pending
Career history
1115
Total Applications
across all art units

Statute-Specific Performance

§101
8.7%
-31.3% vs TC avg
§103
43.6%
+3.6% vs TC avg
§102
26.6%
-13.4% vs TC avg
§112
6.6%
-33.4% vs TC avg
Black line = Tech Center average estimate • Based on career data from 1085 resolved cases

Office Action

§103
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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 03/02/2026 has been entered. 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 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. 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. 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 set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied 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. Claims 1, 3-5, 7-9, 12-14, 16 and 18-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Pandev (US 2019/0214285 A1) in view of Boughorbel (US 2011/0266440 A1) and in further view of Brauer (US 2020/0193588 A1). Regarding claims 1 and 16, Pandev discloses an apparatus [claim 16: non-transitory computer readable medium that stores a set of instructions that is executable by at least one processor of a computing device to cause the computing device to: (paragraph 47)] for analyzing an input electron microscope image of a first area on a first wafer, comprising: (paragraphs 17-19, 26 and 34: Pandev discloses obtaining a first plurality of electron-microscope images of a semiconductor structure on a semiconductor wafer, where the structure can be a test structure or part of a device and is formed on a wafer during fabrication. A second plurality of images is college for respective instances of the semiconductor structure on one or more semiconductor wafers.) a memory storing a set of instructions; and (figure 7: memory 710) at least one processor configured to execute the set of instructions to cause the apparatus to perform: (figure 7: processor 702) evaluating the plurality of mode images; (paragraphs 25, 27, 31-33 and 35: the model-training module trains a model specifying a relationship between EM images and semiconductor-fabrication parameters, and the value-prediction module applies the model to predict values for new images. The defect-classification module predicts defect classes from EM images.) predicting one or more characteristics in the first area on the first wafer based on the determined contributions; and (paragraphs 18, 25 and 27: Training a model that maps electron-microscope images to semiconductor-fabrication parameters, which include geometric and non-geometric parameters. Paragraph 27: Values of the one or more semiconductor-fabrication parameters for the second plurality of electron-microscope images are predicted using the model. Paragraphs 31-33 and 35: Training a model mapping EM images to defect classes and predicting one or more defect classes for wafer images.) Predicting these fabrication parameters and/or defect classes for instances of the structure on the wafers is predicting one or more characteristics in the first area on the first wafer. In the combination with Boughorbel, the model uses mode-contribution features as input, so the prediction is based on the determined contributions. generating an output result to inform an adjustment of one or more parameters of a lithographic apparatus or an electron microscope based on the determined contributions and the predicted one or more characteristics. (Paragraphs 28 and 36: A fabrication process used to fabricate the one or more semiconductor wafers is adjusted based at least in part on the predicted values of the semiconductor-fabrication parameters. If predicted values differ from targets by more than a threshold, the process is adjusted so future wafers move towards target.) Since the semiconductor-fabrication parameters include lithographic focus and dose for photolithography steps, these are parameters of a lithographic apparatus. The process-adjustment module generates an output to adjust those lithography parameters based on the predicted characteristics. Pandev fails to specifically disclose obtaining a plurality of mode images corresponding to a plurality of interpretable modes, wherein a respective interpretable mode of the plurality of interpretable modes is associated with a category of defects and determining, based on evaluation results, contributions from the plurality of interpretable modes. In related art, Boughorbel discloses obtaining a plurality of mode images corresponding to a plurality of interpretable modes and (paragraph 10: A statistical Blind Source Separation (BSS) technique is employed to automatically process the data set (D) and spatially resolve it into a result set (R) of imaging pairs (Q, L), in which an imaging quantity (Q) having value Q is associated with a discrete depth level L referenced to the surface S. Paragraph 11: A suitable BSS technique is PCA which allows high-resolution 3D volume reconstruction and effective separation of different depth layers in a sample from a sequence of SEM images.) Thus, Boughorbel teaches taking multiple SEM images and producing a set of decorrelated component images Qk, each associated with a physical depth level Lk. These Qk images are mode images; the corresponding Lk depth makes them interpretable modes. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate the teachings of Boughorbel into the teachings of Pandev to effectively improve robustness and interpretability of downstream ML models to obtain more reliable predictions for adjusting lithographic parameters. Although Boughorbel discloses obtaining a plurality of mode images corresponding to a plurality of interpretable modes, Boughorbel fails to disclose they are associated with a category of defects. Furthermore, in related art, Brauer discloses obtaining a plurality of modes images corresponding to a plurality of interpretable modes, (paragraphs 14-15 and 34: Brauer teaches imaging defects using a plurality of optical modes, each mode having different optical characteristics. Brauer also teaches a reference image is subtracted to produce a difference image that reveals defects. Therefore, Brauer teaches obtaining a plurality of mode images corresponding to multiple modes.) wherein a respective interpretable mode of the plurality of interpretable modes is associated with a category of defects (paragraph 32: Brauer teaches defect categories as first class defects such as defects of interest and second defects such as nuisance defects.) and determining, based on evaluation results, contributions from the plurality of interpretable modes. (paragraphs 25 and 51-54: Brauer teaches each mode’s signal contributes to the discrimination score via weights and the model chooses pixels from two optical modes as the optimal set.) Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate the teachings of Brauer into the teachings of Pandev and Boughorbel for an effective classification of semiconductor defects. Regarding claims 3 and 18, Pandev, as modified by Boughorbel and Brauer, discloses the claimed invention wherein decomposing the input electron microscope image into the plurality of mode images. (Boughorbel: paragraphs 27-29, 59-61 and 72-78) Regarding claims 4 and 19, Pandev, as modified by Boughorbel and Brauer, discloses the claimed invention wherein obtaining coefficients associated with the plurality of interpretable modes respectively corresponding to the input electron microscope image. (Boughorbel: paragraphs 28 and 72-78) Regarding claims 5 and 20, Pandev, as modified by Boughorbel and Brauer, discloses the claimed invention wherein the one or more characteristics correspond to one or more categories of defects respectively. (Pandev: paragraphs 31-35) Regarding claim 7, Pandev, as modified by Boughorbel and Brauer, discloses the claimed invention wherein applying a classifier model to the coefficients associated with the plurality of interpretable modes respectively to obtain output including the evaluation results. (Pandev: figure 7; paragraphs 35 and 47) Regarding claim 8, Pandev, as modified by Boughorbel and Brauer, discloses the claimed invention wherein the classifier model is a logistic regression, a support vector machine, or a neural network model. (Pandev: paragraph 25) Regarding claim 9, Pandev, as modified by Boughorbel and Brauer, discloses the claimed invention wherein obtaining the evaluation results each of which indicates a likelihood of existence of corresponding interpretable modes. (Pandev: paragraphs 25, 27, 31-33 and 35) Regarding claim 12, Pandev, as modified by Boughorbel and Brauer, discloses the claimed invention wherein determining the contributions from the plurality of interpretable modes to the input electron microscope image comprises: determining, from a linear approximation using the linear model, weights associated with respective ones of the interpretable modes. (Boughorbel: paragraphs 72-78) Regarding claim 13, Pandev, as modified by Boughorbel and Brauer, discloses the claimed invention wherein generating a visualization representing the contributions from the plurality of interpretable modes to the input electron microscope image. (Boughorbel: paragraphs 69-72) Regarding claim 14, Pandev, as modified by Boughorbel and Brauer, discloses the claimed invention wherein adjusting one or more processing parameters in accordance with the one or more characteristics in the area on the wafer. (Pandev: paragraphs 18, 28 and 36) Claim(s) 6 is/are rejected under 35 U.S.C. 103 as being unpatentable over Pandev in view of Boughorbel and Brauer and in further view of Huang (US 2020/0174380 A1). Regarding claim 6, Pandev, as modified by Boughorbel and Brauer, discloses the claimed invention except for wherein the one or more categories of defects comprise small critical dimension (CD), shift along a certain direction, ellipticity, blurry edges, printed contact hole, missing contact hole, or bridging contact hole. In related art, Huang discloses categories of defects comprise small critical dimension (CD), shift along a certain direction, ellipticity, blurry edges, printed contact hole, missing contact hole, or bridging contact hole. (paragraph 30 and figure 3) Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate the teachings of Huang into the teachings of Pandev, Boughorbel and Brauer to effectively enhance a lithographic mask. Claim(s) 10-11 is/are rejected under 35 U.S.C. 103 as being unpatentable over Pandev in view of Boughorbel and Brauer and in further view of Wang (US 2020/0371046 A1). Regarding claim 10, Pandev, as modified by Boughorbel and Brauer, discloses the claimed invention except for wherein approximating the classifier model using a polynomial regression model. In related art, Wang discloses approximating the classifier model using a polynomial regression model. (paragraph 62) Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate the teachings of Wang into the teachings of Pandev, Boughorbel and Bauer to effectively detect defects in a wafer bond. Regarding claim 11, Pandev, as modified by Boughorbel, Brauer and Wang, discloses the claimed invention wherein the polynomial regression model includes a linear model. (paragraph 62) Claim(s) 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Pandev in view of Boughorbel and Brauer and in further view of Wu (US 2011/0243424 A1). Regarding claim 15, Pandev, as modified by Boughorbel and Brauer, discloses the claimed invention except for wherein determining defect causes based on the determined contributions from the plurality of interpretable modes. In related art, Wu discloses determining defect causes based on the determined contributions from the plurality of interpretable modes. (paragraph 21) Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate the teachings of Wu into the teachings of Pandev, Boughorbel and Brauer to effectively determine the root cause of the defect. Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to BOBBAK SAFAIPOUR whose telephone number is (571)270-1092. The examiner can normally be reached Monday - Friday, 8:00am - 5:00pm. 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, Stephen Koziol can be reached at (408) 918-7630. 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. /BOBBAK SAFAIPOUR/Primary Examiner, Art Unit 2665
Read full office action

Prosecution Timeline

Jun 21, 2023
Application Filed
Jun 20, 2025
Non-Final Rejection — §103
Sep 22, 2025
Response Filed
Nov 29, 2025
Final Rejection — §103
Feb 02, 2026
Response after Non-Final Action
Mar 02, 2026
Request for Continued Examination
Mar 04, 2026
Response after Non-Final Action
Mar 07, 2026
Non-Final Rejection — §103 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12597155
TRACKING THREE-DIMENSIONAL GEOMETRIC SHAPES
2y 5m to grant Granted Apr 07, 2026
Patent 12597113
FABRIC DEFECT DETECTION METHOD
2y 5m to grant Granted Apr 07, 2026
Patent 12591987
System and Method for Simultaneously Registering Multiple Lung CT Scans for Quantitative Lung Analysis
2y 5m to grant Granted Mar 31, 2026
Patent 12586140
Automated Property Inspections
2y 5m to grant Granted Mar 24, 2026
Patent 12586240
IMAGE PROCESSING APPARATUS AND CONTROL METHOD FOR SAME
2y 5m to grant Granted Mar 24, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

AI Strategy Recommendation

Get an AI-powered prosecution strategy using examiner precedents, rejection analysis, and claim mapping.
Powered by AI — typically takes 5-10 seconds

Prosecution Projections

3-4
Expected OA Rounds
86%
Grant Probability
97%
With Interview (+10.7%)
2y 8m
Median Time to Grant
High
PTA Risk
Based on 1085 resolved cases by this examiner. Grant probability derived from career allow rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month