DETAILED ACTION
This Action is in response to Applicant’s response filed on 12/04/2025. Claims 1-20 are still pending in the present application. This Action is made FINAL.
Response to Arguments
Applicant's arguments have been considered but are moot in view of the new ground(s) of rejection in view of Odaibo (US 2017/0357879 A1).
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 1-2, 4-8 and 15-18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Venkataraman (US 2016/0358041 A1) in view of Odaibo (US 2017/0357879 A1).
Regarding claims 1 and 15, Venkataraman discloses a computer device comprising at least one processor in communication with at least one memory device, wherein the at least one processor programmed to: (figure 1)
[claim 15: A computer-implemented method performed by a computer system including at least one processor in communication with at least one memory device, the method comprising: receiving at least one image of a material to be analyzed: (figure 1)]
receive at least one image of a material to be analyzed; (figure 1, steps 202-204: acquire image including multiple defects types, group defects into groups)
execute a plurality of models trained to classify the at least one image to detect a first defect type; (paragraphs 37: multiple decision tree classifiers)
receive from each of the plurality of models a prediction that the at least one image includes the first defect type; (paragraphs 42-49: confidence level)
combine the plurality of predictions to calculate a final prediction of whether or not the at least one image includes the first defect type; and (paragraph 42: see confidence level formula calculated via a majority two vote scheme)
reject or approve the material to be analyzed based upon the final prediction. (paragraphs 18, 34: defect review and classification; paragraph 46: adjust the confidence threshold; paragraph 53: adjust upstream process tool parameters to reduce the formation of the particular defect types classified of the fabrication line)
Venkataraman fails to disclose applying a weight of a plurality of weights to each of the plurality of predictions, wherein the weight is based on past performance of the corresponding model of the plurality of models that generated the prediction and combining the plurality of predictions with their corresponding weights.
In related art, Odaibo discloses applying a weight of a plurality of weights to each of the plurality of predictions, wherein the weight is based on past performance of the corresponding model of the plurality of models that generated the prediction (paragraphs 19 and 59; Odaibo teaches that the performance of each model on the test dataset is noted, ranked and stored and that a weight is assigned to each model according to its rank such that better performing models receive higher weights. Odaibo further confirms that model weights are determined based on performance of the individual models on test data and those assigned weights are then multiplied by each model’s predicted score.) and combining the plurality of predictions with their corresponding weights. (paragraphs 19 and 59-60; Odaibo teaches the class prediction of each model in the ensemble is computed, then for each model, the model’s assigned weight is multiplied by the class score of the subject image and the sum of all such products is taken, that is, the weighted average of class scores is computed and is taken as the ensemble class score of the subject image.)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate to modify Venkataraman’s combination of multiple model predictions by applying Odaibo’s performance based weighting scheme because Odaibo teaches that equal or non-performance based averaging can degrade generalization by over influencing poorly performing models, whereas weighting models according to prior test performance improves the ensemble classification result. Doing so would merely have involved using a known technique to improve a similar image classification ensemble system, yielding the predictable result of a more accurate final prediction for approval or rejection of the inspected material.
Regarding claim 2, Venkataraman, as modified by Odaibo, discloses the claimed invention wherein the material is a single crystal. (paragraph 17)
Regarding claims 4 and 16, Venkataraman, as modified by Odaibo, discloses the claimed invention wherein the material is a silicon wafer. (paragraph 17)
Regarding claim 5, Venkataraman, as modified by Odaibo, discloses the claimed invention wherein the material is a semiconductor material. (paragraph 17)
Regarding claims 6 and 17, Venkataraman, as modified by Odaibo, discloses the claimed invention wherein the at least one image was generated by an infrared radiation detection system. (paragraph 19)
Regarding claim 7, Venkataraman, as modified by Odaibo, discloses the claimed invention wherein the at least one image is generated by one of metrology, a flatness measurement, a capacitance test, and a conductance test. (paragraph 25)
Regarding claims 8 and 18, Venkataraman, as modified by Odaibo, discloses the claimed invention wherein the first defect type is at least one air pocket in the material. (paragraph 31)
Claim 3 is/are rejected under 35 U.S.C. 103 as being unpatentable over Venkataraman in view of Odaibo and in further view of Valley (US 9,317,912).
Regarding claim 3, Venkataraman, as modified by Odaibo, discloses the claimed invention except for wherein the crystal is formed by the Czochralski process.
In related art, Valley discloses the crystal is formed by the Czochralski process. (col. 3, lines 9-11)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate the teachings of Valley into the teachings of Venkataraman and Odaibo to effectively subject the crystal material to testing in a variety of conditions.
Claims 9, 10, 12-13, 19 and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Venkataraman in view of Odaibo and in further view of Hsu (“Ensemble convolutional neural networks with weighted majority for wafer bin map pattern classification”).
Regarding claims 9 and 19, Venkataraman, as modified by Odaibo, discloses the claimed invention except for wherein the at last one processor is further programmed to: train the plurality of models using a first image training set; and validate the plurality of models using a second image training set.
In related art, Hsu discloses training the plurality of models using a first image training set; and validate the plurality of models using a second image training set. (see the “Proposed ECNN framework” on page 833)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate the teachings of Hsu into the teachings of Venkataraman and Odaibo to effectively adopt a weighted majority function to select higher weights for the base classifiers that have higher predictive performance.
Regarding claims 10 and 20, Venkataraman, as modified by Odaibo and Hsu, discloses the claimed invention wherein the at least one processor is further programmed to calculate the plurality of weights for combining the plurality of predictions using the validation of the second image training set. (Hsu: page 835, equation 2)
Regarding claim 12, Venkataraman, as modified by Odaibo, discloses the claimed invention except for wherein the plurality of models include three different models.
In related art, Hsu discloses the plurality of models include three different models. (figure 2 base classifier 1, 2 and 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 Hsu into the teachings of Venkataraman and Odaibo to effectively adopt a weighted majority function to select higher weights for the base classifiers that have higher predictive performance.
Regarding claim 13, Venkataraman, as modified by Odaibo and Hsu, discloses the claimed invention wherein the three different models are convolution neural networks. (figure 2 base classifier 1, 2 and 3)
Claim 11 is/are rejected under 35 U.S.C. 103 as being unpatentable over Venkataraman in view of Odaibo and Hsu, and in further view of Murai (2022/0328332 A1).
Regarding claim 11, Venkataraman, as modified by Odaibo and Hsu, discloses the claimed invention except for wherein the weights ae calculated using Bayesian optimization.
In related art, Murai discloses weights ae calculated using Bayesian optimization. (paragraph 47)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate the teachings of Murai into the teachings of Venkataraman, Odaibo and Hsu to effectively refine the predictive distribution of the product characteristics.
Claim 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Venkataraman in view of Odaibo and Hsu and in further view of Kim (US 2022/0374680 A1).
Regarding claim 14, Venkataraman, as modified by Odaibo and Hsu, discloses the claimed invention except for wherein the three different models are Efficientnet models.
In related art, Kim discloses Efficientnet models. (paragraph 58)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate the teachings of Kim into the teachings of Venkataraman, Odaibo and Hsu to effectively optimize performance and efficiency.
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.
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