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 .
Election/Restrictions
Applicant’s election without traverse of claims 1-12, 17, 20-21 in the reply filed on 03/05/2026 and 06/08/2026 is acknowledged.
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) 1-12, 17, 20-21 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhang et al. (US2022/0404712) in view of Ha et al. (US2018/0330511).
To claim 1, Zhang teach a system configured to determine an offset for use in a process performed on a specimen, comprising:
one or more computer subsystems; and one or more components executed by the one or more computer subsystems, wherein the one or more components comprise a deep learning model (paragraph 0169, deep CNN); and
wherein the one or more computer subsystems are configured for:
transforming design information for an alignment target on a specimen to a predicted image of the alignment target by inputting the design information into the deep learning model (925 of Fig. 9, paragraphs 0156-0157, image generator/machine learning model for predicting a measured image from design pattern);
aligning the predicted image to an image of the alignment target on the specimen generated by an imaging subsystem (320 of Fig. 3, paragraph 0125, printed pattern can be imaged by an image capture device to generate measured image);
determining an offset between the predicted image and the image generated by the imaging subsystem based on results of said aligning (1010 of Fig. 10, paragraphs 0159-0160); and
storing the determined offset as an align-to-design offset for use in a process performed on the specimen with the imaging subsystem (730 of Fig. 7, paragraphs 0140-0143, calibrating the process model to reduce a difference, computed based on determined offset, between simulated contour and measured contour).
But, Zhang do not expressly disclose wherein the deep learning model is configured as variational encoder.
Ha teach using deep learning model for aligning images for a specimen acquired with different modalities are provided (abstract), wherein alignment results may include any suitable alignment results known in the art such as alignment offsets, a combination of translation offsets, scales, rotation angles, slant, etc. (paragraphs 0087), wherein the deep learning model is configured as variational encoder (paragraphs 0100-0102).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate teaching of Ha into the system of Zhang, in order to implement deep learning by design preference.
To claim 20, Zhang and Ha teach a non-transitory computer-readable medium, storing program instructions executable on one or more computer systems for performing a computer-implemented method for determining an offset for use in a process performed on a specimen (as explained in response to claim 1 above).
To claim 21, Zhang and Ha teach a computer-implemented method for determining an offset for use in a process performed on a specimen (as explained in response to claim 1 above).
To claim 17, Zhang and Ha teach claim 1.
Zhang teach wherein the process is an inspection process (paragraph 0125).
To claim 3, Zhang and Ha teach claim 1.
Zhang and Ha teach wherein the one or more computer subsystems are further configured for converting a binary design image for the alignment target into a grayscale design image, and wherein the design information comprises the grayscale design image and not the binary design image (Zhang, paragraph 0106, wherein conversion between binary image and grayscale image is well-known practice in the art, which would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate by design preference, hence Official Notice is taken).
To claim 4, Zhang and Ha teach claim 3.
Zhang and Ha teach wherein the deep learning model is further configured for transforming the grayscale design image into a predicted grayscale design image (obvious as deep learning model fundamentally comprises transformation process, and output of deep learning model is prediction).
To claim 5, Zhang and Ha teach claim 1.
Zhang and Ha teach wherein the design information comprises information for multiple layers of a design for the specimen (Zhang, paragraphs 0004-0005; Ha, paragraph 0031, 0075).
To claim 6, Zhang and Ha teach claim 5.
Zhang and Ha teach wherein the deep learning model is further configured to have different weights for at least two of the multiple layers that are separately determined during training of the deep learning model (Zhang, paragraph 0171; Ha, paragraph 0111).
To claim 7, Zhang and Ha teach claim 1.
Zhang and Ha teach wherein the one or more computer subsystems are further configured for re-training the deep learning model for a different specimen by performing iterative training of the deep learning model (Zhang, paragraphs 0011, 0037, 0047, 0053, 0167, 0193, 0289, 0316, 0370, 0390, 0429, 0464, 0488, iterative training; Ha, paragraphs 0129-0130, iterative training).
To claims 8, Zhang and Ha teach claim 7.
Zhang and Ha teach wherein the one or more computer subsystems are further configured for performing the re-training during runtime of the process performed on the different specimen (Zhang, paragraphs 0011, 0037, 0047, 0053, 0167, 0193, 0289, 0316, 0370, 0390, 0429, 0464, 0488, iterative training; Ha, paragraphs 0059-0061, processing multiple specimens, paragraphs 0129-0130, iterative training).
To claim 9, Zhang and Ha teach claim 1.
Zhang and Ha teach wherein the one or more computer subsystems are further configured for performing the inputting, aligning, determining, and storing for a first portion of the specimen and re-training the deep learning model by performing iterative training of the deep learning model for a second portion of the specimen (Zhang, paragraphs 0003, 0111, multiple portions of specimen are analyzed and processed, paragraphs 0011, 0037, 0047, 0053, 0167, 0193, 0289, 0316, 0370, 0390, 0429, 0464, 0488, iterative training, wherein obvious as iteratively training multiple portions of specimen).
To claim 10, Zhang and Ha teach claim 9.
Zhang and Ha teach wherein the one or more computer subsystems are further configured for performing the inputting, aligning, determining, and storing for the first portion of the specimen and the re-training during runtime of the process performed on the specimen (as explained in response to claim 9 above).
To claim 11, Zhang and Ha teach claim 1.
Zhang and Ha teach wherein the one or more computer subsystems are further configured for performing the inputting, aligning, determining, and storing during runtime of the process performed on the specimen and during runtime of the process performed on one or more other specimens (Zhang, obvious in paragraphs 0202-0206, storing temporary variables or other intermediate information during execution of instructions to be executed; Ha, paragraph 0049, parallel processing, paragraphs 0059-0061, processing multiple specimens).
To claim 12, Zhang and Ha teach claim 1.
Zhang and Ha teach wherein the one or more computer subsystems are further configured for performing the process on the specimen with the imaging subsystem, and wherein the process comprises aligning a target image of an inspection area on the specimen to a design for the specimen based on the align-to-design offset (as explained in response to claim 1 above), transforming design information for the inspection area to a predicted target image of the inspection area by inputting the design information for the inspection area into the deep learning model (paragraphs 0032, 0147-0160, 0184, 0276-0277), subtracting the predicted target image from the aligned target image, and applying a defect detection method to results of the subtracting (despite lack of disclosure, applying defect detection method to results of subtracting is well-known technique in the art, which would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate, hence Official Notice is taken).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ZHIYU LU whose telephone number is (571)272-2837. The examiner can normally be reached Weekdays: 8:30AM - 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 R 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.
ZHIYU . LU
Primary Examiner
Art Unit 2669
/ZHIYU LU/Primary Examiner, Art Unit 2665 June 21, 2026
Prosecution Insights