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
The amendment filed on June 15th, 2026 has been entered. Claims 1-20 remain pending in the application.
Response to Arguments/Remarks re. 35 U.S.C. § 102/103 Rejections
Applicant’s arguments with respect to the non-final rejection of claims under 35 U.S.C 102/103 have been considered but are moot because the new grounds of rejection, as necessitated by the amended claims, do not rely solely on the references applied in the prior rejection of record.
As a note, Applicant has effectively argued that Maggipinto as cited does not teach “wherein output of a final layer of the deep learning model is not input to the additional component”. In doing so, the Applicant seems to be attempting to frame the end of the encoder as the last layer of the deep learning model. This is a mischaracterization. Autoencoders possess both an encoder and decoder portion, with their own respective layers. The final layer of an encoder is not the final layer of the autoencoder, the final layer of an autoencoder is the output layer of the decoder. Accordingly, the argument is not persuasive.
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 1, 19 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Maggipinto et. al A Deep Convolutional Autoencoder-Based Approach for Anomaly Detection With Industrial, Non-Images, 2-Dimensional Data: A Semiconductor Manufacturing Case Study (Hereinafter, “Maggipinto”) in view of Zhang et. al (US 11580398 B2) (Hereinafter, “Zhang”)
With respect to claim 1, Maggipinto teaches:
A system configured for determining information for a specimen, comprising:
a computer system ([8]) configured for acquiring output generated for a specimen by one or more detectors of an output generation subsystem ([8] “The autoencoder itself is instead very flexible and can be trained on any dataset that present 2d input data”; [Abstract] “We test our approach on real world Optical Emission Spectroscopy data that are typical of semiconductor manufacturing”)
one or more components executed by the computer system, wherein the one or more components comprise
a deep learning model (Fig. 4, “Scheme of the proposed deep learning-based anomaly detection (AD) scheme”) configured for determining information for the specimen from the output generated by at least one of the one or more detectors, model comprises hidden layers configured for generating hidden layer output ([5]; Fig. 3 “layers of the encoder”. Read in line with page 22 lines 8-10 of the specification, “Layers other than the input and output layers of a DL model are considered hidden layers or intermediate layers”; Page 21 lines 24-25 “DL NNs typically include several hidden layers such as convolution or fully connected layers”)
an additional component ([4A]) configured for determining additional information for the specimen from the hidden layer output generated by at least one of the hidden layers in combination with input specific to the specimen (Fig. 2, “Anomaly Detection” block; Fig. 3; [5] “Since we do not know at what level of the network the most valuable features are extracted, we concatenate the features obtained from different pooling layers of the encoder…The reduced version of the feature vector is well-suited to be processed by shallow anomaly detection methods…”), wherein output of a final layer of the deep learning model is not input to the additional component ([2] “The decoder network is not used during the detection process which reduces by half the complexity of the neural part of the algorithm”; [7] “It is important to remark that the feature extraction does not require the decoder part of the network at evaluation time, hence it has half the number of parameters”; Fig. 2)
Maggipinto does not explicitly teach:
wherein the output from which the information is determined comprises images of the specimen
However, Zhang, in the same field of endeavor of semiconductor analysis, teaches:
A system configured for determining information for a specimen, comprising:
a computer system ([Abstract]) configured for acquiring output generated for a specimen by one or more detectors of an output generation subsystem (Col. 6, lines 45-61; Col. 11, lines 19-35; Col. 11, lines 39-41 “The deep learning model is configured for determining information from an image generated for a specimen by an imaging tool”)
one or more components executed by the computer system, wherein the one or more components comprise
a deep learning model configured for determining information for the specimen from the output generated by at least one of the one or more detectors, wherein the output from which the information is determined comprises images of the specimen (Fig. 4; Col. 2, lines 23-35 “The one or more components also include a diagnostic component configured for determining one or more causal portions of the image that resulted in the information being determined and for performing one or more functions based on the determined one or more causal portions of the image”; Col. 11) and wherein the deep learning model comprises hidden layers configured for generating hidden layer output (Fig. 4; Col. 18-19)
an additional component configured for determining additional information for the specimen from the hidden layer output generated by at least one of the hidden layers in combination with input specific to the specimenFig. 4; Col. 18-19)
It would have been obvious to one of ordinary skill in the art as of the effective filing date of the claimed invention, to modify Maggipinto to include the limitations of image input, as taught by Zhang. Doing so would have the advantage of providing additional spatial context within the analysis. One of ordinary skill in the art would understand that neural networks can process a variety of inputs using similar architecture, and accordingly the systems readily integrate.
With respect to claim 19, it largely restates the functional language of claim 1, but as a non-transitory computer-readable medium storing executable instructions. Maggipinto/Zhang provides for the same (Zhang, Col. 27). Accordingly, claim 19 is rejected.
With respect to claim 20, it largely restates the functional language of claim 1, but as a computer-implemented method. Maggipinto/Zhang provides for the same (Zhang, Col. 27). Accordingly, claim 20 is rejected.
Claims 2-18 as original claims are rejected in line with the Non-Final Rejection mailed 3/24/2026. The addition of Zhang as applied does not further render any claim depending from claim 1 non-obvious, as the teaching of Zhang represents a minor distinction which otherwise readily integrates into the overarching systems to predictable success, for the reasons outlined above.
Conclusion
Applicant’s amendment necessitated the new grounds 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 NOAH WILLIAM BOYAR whose telephone number is 571-272- 8392. The examiner can normally be reached 10:00 AM – 6:00 PM EST, Monday – Friday. 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, Chan Park can be reached at 571-272-7409. 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.
/NOAH W BOYAR/
Examiner, Art Unit 2669
/IAN L LEMIEUX/Primary Examiner, Art Unit 2669
Prosecution Insights