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 .
Priority
The instant application claims priority to and benefit of German Application No. DE102023120810.1, filed on 08/04/2023. Thus, the effective filing date of Claims 1-32 are 8/04/2023.
Information Disclosure Statement
The information disclosure statement (“IDS”) filed on 09/03/2024 was reviewed and the listed references were noted.
Drawings
The 8 page drawings have been considered and placed on record in the file.
Status of Claims
Claims 1-32 are currently pending.
Claim Objections
Claims 11-13 and 15 objected to under 37 CFR 1.75 as being a substantial duplicate of claim 11. When two claims in an application are duplicates or else are so close in content that they both cover the same thing, despite a slight difference in wording, it is proper after allowing one claim to object to the other as being a substantial duplicate of the allowed claim. See MPEP § 608.01(m).
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
Use of the word “means” (or “step for”) in a claim with functional language creates a rebuttable presumption that the claim element is to be treated in accordance with 35 U.S.C. 112(f) (pre-AIA 35 U.S.C. 112, sixth paragraph). The presumption that 35 U.S.C. 112(f) (pre-AIA 35 U.S.C. 112, sixth paragraph) is invoked is rebutted when the function is recited with sufficient structure, material, or acts within the claim itself to entirely perform the recited function.
Absence of the word “means” (or “step for”) in a claim creates a rebuttable presumption that the claim element is not to be treated in accordance with 35 U.S.C. 112(f) (pre-AIA 35 U.S.C. 112, sixth paragraph). The presumption that 35 U.S.C. 112(f) (pre-AIA 35 U.S.C. 112, sixth paragraph) is not invoked is rebutted when the claim element recites function but fails to recite sufficiently definite structure, material or acts to perform that function.
Claim elements in this application that use the word “means” (or “step for”) are presumed to invoke 35 U.S.C. 112(f) except as otherwise indicated in an Office action. Similarly, claim elements that do not use the word “means” (or “step for”) are presumed not to invoke 35 U.S.C. 112(f) except as otherwise indicated in an Office action.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitation is: “an imaging device configured to…” in Claim 32.
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claim 30 is rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter as follows.
Claim 30 is directed to a "computer-readable medium." The specification issilent with respect to the definition of a "computer-readable medium." The broadest reasonable interpretation of a claim drawn to a computer-readable medium typically covers forms of non-transitory tangible media and transitory propagating signals per se in view of the ordinary and customary meaning of computer readable media, particularly when the specification is silent. See Subject Matter Eligibility of Computer Readable Media, 1351 OG 212 (26 Jan 2010). See MPEP 2111.01. Signals are nothing but the physical characteristics of a form of energy, and assuch is nonstatutory natural phenomena. See, e.g., In re Nuitjen, 500 F. 3d 1346, 1357 (Fed. Cir. 2007)(slip. op. at 18)("A transitory, propagating signal like Nuitjen's is not a process, machine, manufacture, or composition of matter.' ... Thus, such a signal cannot be patentable subject matter."). Thus, claim 30 is rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. The rejection of claim 30 may be overcome by amending the claim to add the term “non-transitory” before “computer-readable medium”.
Claim 31 is rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter as follows.
Claim 31 recites “A computer program product comprising instructions …” (computer program). Computer programs, per se, are not in one of the statutory categories of invention because a computer program is merely a set of instructions capable of being executed by a computer - the computer program itself is not a process. MPEP § 2106.
A computer program, at best, is a functional descriptive material per se. Descriptive material can be characterized as either "functional descriptive material" or "nonfunctional descriptive material." Both types of "descriptive material" are nonstatutory when claimed as descriptive material per se, 33 F.3d at 1360, 31 USPQ2d at 1759. When functional descriptive material is recorded on some computer-readable medium, it becomes structurally and functionally interrelated to the medium and will be statutory in most cases since use of technology permits the function of the descriptive material to be realized. Compare In re Lowry, 32 F.3d 1579, 1583-84, 32 USPQ2d 1031, 1035 (Fed. Cir. 1994) )(discussing patentable weight of data structure limitations in the context of a statutory claim to a data structure stored on a computer readable medium that increases computer efficiency) and >In re Warmerdam, 33 F.3d *>1354, 1360- 61,31 USPQ2d *>1754, 1759 (claim to computer having a specific data structure stored in memory held statutory product-by-process claim) with Warmerdam, 33 F.3d at 1361,31 USPQ2d at 1760 (claim to a data structure per se held nonstatutory). See MPEP 2106.01. Accordingly, claim 31 is rejected under 35 U.S.C. 101.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1-2, 6-8, 10-13, 15, 20-22, and 24-26 are rejected under 35 U.S.C. 102 (a)(1) as being anticipated by Baranwal et. al. (“A Deep Learning Toolset to Mask Analysis with SEM Digital Twins” published in April, 2021).
Consider Claim 1, Baranwal “A computer implemented method for defect detection in an object comprising integrated circuit patterns comprising:” (Baranwal; Fig. 20 (See image below; Abstract; “A third tool uses a DL multi-class classifier to categorize various types of VSB mask writer defects.”) “- obtaining an imaging dataset and a reference dataset of the object;” (Baranwal; Pg. 15; 2.3 Deep Learning Model; “Reference and defect SEM images are input to the DL model…”) “- generating an input representation of a subset of the imaging dataset and a reference representation of a corresponding subset of the reference dataset in a feature space, wherein the feature space is configured to preserve the information of the subset of the imaging dataset and of the subset of the reference dataset that is relevant for the detection of defects; and” (Baranwal; Fig-20 (See image below)) “- detecting defects in the object by comparing the input representation to the reference representation in the feature space.” (Baranwal; 2.3 Deep learning Model; “Reference and defect SEM images are input to the DL model, which outputs a probability that the error belongs to one of the three error classes or is normal.”).
PNG
media_image1.png
633
1447
media_image1.png
Greyscale
Consider Claim 2, Baranwal teaches “The method of claim 1, wherein the dimension of the feature space is lower than the dimension of the subset of the imaging dataset.” (Baranwal; Fig-20 (See image above); Convolution and pooling layers of ResNET).
Consider Claim 6, Baranwal teaches “The method of claim 5, wherein the appearance of the respective dataset is modified by applying a trained machine learning model to the respective dataset.” (Baranwal; Fig-4 (See image below); Pg. 3; 1.2 SEM Digital Twins; “Based on this concept, as shown in Fig-4 below, we built deep learning-based SEM digital twins to generate realistic-looking SEM images [6]. The SEM digital twins take CAD data, which is a simulated mask pattern, and output corresponding generated SEM images.”).
PNG
media_image2.png
300
805
media_image2.png
Greyscale
Consider Claim 7, Baranwal teaches “The method of claim 1, wherein the feature space is defined depending on at least one of meta information concerning the imaging dataset, the reference dataset, the integrated circuit patterns of the object, the defects, or the location of the subset of the imaging dataset.” (Baranwal; Fig-20 (See image above); Examiner notes the feature space defined by the patterns extracted from input and reference images for defect detection.).
Consider Claim 8, Baranwal teaches “The method of claim 1, wherein generating the input representation in the feature space comprises applying a trained input machine learning model to the subset of the imaging dataset, and wherein generating the reference representation in the feature space comprises applying a trained reference machine learning model to the subset of the reference dataset.” (Baranwal; Fig-20 (See image above)).
Consider Claim 10, Baranwal teaches “The method of claim 8, wherein the input machine learning model comprises an input neural network, and wherein the reference machine learning model comprises a reference neural network, and wherein the feature space comprises activations of one or more layers of the input neural network and activations of one or more layers of the reference neural network.” (Baranwal; Fig-20 (See image above); “Convolution” and “Pooling”).
Consider Claim 11, Baranwal teaches “The method of claim 10, wherein the input neural network and the reference neural network have a sequence of at least one intermediate layer in common.” (Baranwal; Fig-20 (See image above); Feature Extraction and Classification sections within ResNET; Examiner notes the reference and defect SEM share the same neural network, ResNET; therefore, both share the shame intermediate layers.).
Consider Claim 12, Baranwal teaches “The method of claim 11, wherein the architecture of the input neural network and the architecture of the reference neural network are configured such that the input neural network and the reference neural network share a sequence of at least one intermediate layer.” (Baranwal; Fig-20 (See image above); Feature Extraction and Classification sections within ResNET).
Consider Claim 13, Baranwal teaches “The method of claim 11, wherein the input neural network and the reference neural network comprise an identical sequence of at least one intermediate layer.” (Baranwal; Fig-20 (See image above); Feature Extraction and Classification sections within ResNET).
Consider Claim 15, Baranwal teaches “The method of claim 10, wherein the input neural network and the reference neural network each contain a sequence comprising the same number of one or more corresponding, structurally identical intermediate layers.” (Baranwal; Fig-20 (See image above); Feature Extraction and Classification sections within ResNET; Examiner notes the reference and defect SEM use the same neural network, ResNET; therefore, both share the shame intermediate layers.).
Consider Claim 20, Baranwal teaches “The method of claim 8, wherein the reference machine learning model is identical to the input machine learning model.” (Baranwal; Fig-20 (See image above); Examiner notes the reference and defect SEM use the same neural network, ResNET).
Consider Claim 21, Baranwal teaches “The method of claim 8, wherein the input machine learning model and the reference machine learning model are loaded from a memory or database depending on at least one of meta information concerning the imaging dataset, the reference dataset, the integrated circuit patterns of the object, the defects, the input machine learning model, or the reference machine learning model.” (Baranwal; Fig-14, Training and Test Data, Examiner notes the SEM data created acts as a database of images to training the neural network.).
Consider Claim 22, Baranwal teaches “The method of claim 1, wherein the input machine learning model is trained to map the subset of the imaging dataset to an output space, and wherein the reference machine learning model is trained to map the subset of the reference dataset to the same output space.” (Baranwal; Fig-20 (See image above); Output).
Consider Claim 24, Baranwal teaches “The method of claim 1, wherein detecting defects comprises applying a trained machine learning model to the input representation and the reference representation in the feature space or to a function of the input representation and the reference representation in the feature space. (Baranwal; Fig-20 (See image above); Classification Layers; Pg. 17; 2.6 Generalization to Classifying Other SEM-based Defects; “We again used the SEM digital twins to generate synthetic SEM images, trained a classification model on them, and applied the trained model to real SEM images.” (emphasis added)).
Consider Claim 25, Baranwal teaches “The method of claim 1, further comprising classifying one or more of the detected defects by applying a defect classification method to the input representation in the feature space.” (Baranwal; Fig-20 (See image above); Classification Layers).
Consider Claim 26, Baranwal teaches “A computer implemented method for training an input machine learning model and/or a reference machine learning model according to claim 8.” (Baranwal; Pg. 15; 2.4 Results; “This was only possible because we were able to complete the DL training with more than a million SEM images with a large variety of the errors in each category using digital twins.”)
Claim Rejections - 35 USC § 103 Single Reference
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 for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
Determining the scope and contents of the prior art.
Ascertaining the differences between the prior art and the claims at issue.
Resolving the level of ordinary skill in the pertinent art.
Considering objective evidence present in the application indicating obviousness or nonobviousness.
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.
Claims 3-5 and 29 are rejected under 35 U.S.C. 103 as being unpatentable over Baranwal (“A Deep Learning Toolset to Mask Analysis with SEM Digital Twins” published in April, 2021).
Consider Claim 3, Baranwal “The method of claim 1, wherein the input representation comprises a probability distribution in the feature space, and wherein the reference representation comprises a probability distribution in the feature space.” (Baranwal; Pg. 6; 2.3 Deep Learning Model; “The output from the anomaly detection network is a probability distribution for good and bad images, which is used to filter the dataset of the images.”). Accordingly, before the effective filing date of the instant application, it would have been obvious to one of ordinary skill in the art to combine the third and second embodiments of Baranwal to further determine a probability distribution of the reference representations in the feature space. One of ordinary skill in the art would be motivated to combine the two embodiments of Baranwal to “filter the dataset of the images” (Baranwal; Pg. 6; 2.3 Deep Learning Model) and more effectively training the machine learning model. Accordingly, the single reference Baranwal discloses the invention of Claim 3.
Consider Claim 4, Baranwal teaches “The method of claim 1, wherein the appearance of the imaging dataset differs from the appearance of the reference dataset, and wherein the appearance comprises at least one aspect from the group containing image statistics, image modality, image generation type, image alignment.”
(Baranwal; Pg. 9; 1.2 Training and Test data; “Using the digital twins, we generated a large number of pairs of aligned CAD data and resulting SEM images. We induced misalignment by applying transformations such as scaling, rotation, and translation with a varying range of values for transformation…. To test the model (Fig-14), we generated 70,000 test images from the digital twins. We also manually aligned 185 real SEM images to see how the model performed on real SEM images.” (emphasis added)). Accordingly, before the effective filing date of the instant application, it would have been obvious to one of ordinary skill in the art to combine the third and first embodiment of Baranwal to further have differing reference and imaging datasets. One of ordinary skill in the art would be motivated to combine the two embodiments of Baranwal to more effectively training the machine learning model on a larger dataset. Accordingly, the single reference Baranwal discloses the invention of Claim 4.
Consider Claim 5, Baranwal teaches “The method of claim 1, wherein the appearance of the reference dataset is modified to imitate the appearance of the imaging dataset, or wherein the appearance of the imaging dataset is modified to imitate the appearance of the reference dataset.” (Baranwal; Fig-11 and Fig-12 (See image below)). Accordingly, before the effective filing date of the instant application, it would have been obvious to one of ordinary skill in the art to combine the third and first embodiment of Baranwal to further to modify reference and imaging datasets to imitate each other. One of ordinary skill in the art would be motivated to combine the two embodiments of Baranwal because “SEM images taken by the mask shops are often misaligned with the corresponding CAD/design-data in offset, rotation and scaling. For these reasons, for applications such as DL projects that require both CAD data and their resulting SEM images, CAD to SEM image alignment is essential. We encountered this misalignment issue while improving SEM digital twins’ accuracy.” (Baranwal; Pg. 8; 1.1 Need for the Tool). Accordingly, the single reference Baranwal discloses the invention of Claim 5.
PNG
media_image3.png
913
707
media_image3.png
Greyscale
Consider Claim 29, Baranwal teaches The method of claim 26, wherein the input neural network and the reference neural network are trained sequentially.” (Baranwal; Pg 6; 2.3 Deep Learning Model; “The deep autoencoder was first trained on good SEM images to learn a probability distribution of good SEM image data and produce a vectorized embedding for the images (Fig-8). The trained autoencoder also calculates a reconstruction error which is low for good SEM images and high for bad SEM images.”). Accordingly, before the effective filing date of the instant application, it would have been obvious to one of ordinary skill in the art to combine the third and first embodiment of Baranwal to further train the input and reference neural network sequentially. One of ordinary skill in the art would be motivated to combine the two embodiments of Baranwal to more effectively detect defects. Accordingly, the single reference Baranwal discloses the invention of Claim 29.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
Determining the scope and contents of the prior art.
Ascertaining the differences between the prior art and the claims at issue.
Resolving the level of ordinary skill in the pertinent art.
Considering objective evidence present in the application indicating obviousness or nonobviousness.
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.
Claims 14, 16, and 28 are rejected under 35 U.S.C. 103 as being unpatentable over Baranwal (“A Deep Learning Toolset to Mask Analysis with SEM Digital Twins” published in April, 2021) in view of Zheng (“Defect detection on new samples with siamese defect-aware attention network” published on June 11, 2022).
Consider Claim 14, Baranwal does not explicitly teach “The method of claim 11, wherein the feature space comprises activations of one or more of the at least one intermediate layer of the common sequence, and wherein the input representation of the subset of the imaging dataset in the feature space comprises the activation of the one or more of the at least one intermediate layer of the common sequence when applying the input neural network to the subset of the imaging dataset, and wherein the reference representation of the subset of the reference dataset comprises the activation of the one or more of the at least one intermediate layer of the common sequence when applying the reference neural network to the subset of the reference dataset.”. However, in analogous field of endeavor, Zheng teaches “The method of claim 11, wherein the feature space comprises activations of one or more of the at least one intermediate layer of the common sequence, and wherein the input representation of the subset of the imaging dataset in the feature space comprises the activation of the one or more of the at least one intermediate layer of the common sequence when applying the input neural network to the subset of the imaging dataset, and wherein the reference representation of the subset of the reference dataset comprises the activation of the one or more of the at least one intermediate layer of the common sequence when applying the reference neural network to the subset of the reference dataset.” (Zheng; Fig. 3 (Seem image below); 3.1 The proposed SDANet; “We apply a sigmoid activate function σ(⋅) on Fd to obtain the defect-aware attention map Fda:”). Accordingly, before the effective filing date of the instant application, it would have been obvious to one of ordinary skill in the art to combine Baranwal with the teachings of Zheng to further active one or more of the intermediate layer of the common sequence between the input and reference neural network. One of ordinary skill in the art would be motivated to combine Baranwal and Zheng to “…improve the ability of the model to generalize to unseen samples and recall defects that are similar to the background.” (Zheng; 3. Methodology). Accordingly, the combination of Baranwal and Zheng discloses the invention of Claim 14.
PNG
media_image4.png
731
807
media_image4.png
Greyscale
Consider Claim 16, Baranwal does not explicitly disclose “The method of claim 10, wherein each two corresponding intermediate layers of the sequences are aligned, such that they produce at least similar activations, when presenting a defect-free subset of the imaging dataset to the input neural network and a corresponding subset of the reference dataset to the reference neural network.”. However, in an analogous field of endeavor, Zheng teaches “The method of claim 10, wherein each two corresponding intermediate layers of the sequences are aligned, such that they produce at least similar activations, when presenting a defect-free subset of the imaging dataset to the input neural network and a corresponding subset of the reference dataset to the reference neural network.” (Zheng; Fig. 3 (Seem image above)). Accordingly, before the effective filing date of the instant application, it would have been obvious to one of ordinary skill in the art to combine Baranwal with the teachings of Zheng to further align corresponding intermediate layers of the sequences. One of ordinary skill in the art would be motivated to combine Baranwal and Zheng to “…improve the ability of the model to generalize to unseen samples and recall defects that are similar to the background.” (Zheng; 3. Methodology). Accordingly, the combination of Baranwal and Zheng discloses the invention of Claim 16.
Consider Claim 28, Baranwal does not explicitly disclose “The method of claim 26, wherein the input neural network and the reference neural network are trained jointly”. However, in an analogous field of endeavor, Zheng teaches “The method of claim 26, wherein the input neural network and the reference neural network are trained jointly.” (Zheng; Fig. 4 (See image below); 3.2 Efficient inference with pre-stored template features; “In the training phase, the template is fed into the network along with the input image.”). Accordingly, before the effective filing date of the instant application, it would have been obvious to one of ordinary skill in the art to combine Baranwal with the teachings of Zheng to further train the input reference neural network jointly. One of ordinary skill in the art would be motivated to combine Baranwal and Zheng to “…improve the ability of the model to generalize to unseen samples and recall defects that are similar to the background. In inference, the feature of the template image can be saved in advance and the feature extractor only needs to forward the input image, which ensures the efficiency of inference.” (Zheng; 3. Methodology). Accordingly, the combination of Baranwal and Zheng discloses the invention of Claim 28.
PNG
media_image5.png
530
1267
media_image5.png
Greyscale
Claims 23 are rejected under 35 U.S.C. 103 as being unpatentable over Baranwal (“A Deep Learning Toolset to Mask Analysis with SEM Digital Twins” published in April, 2021) in view of He ("Fault Detection Using the k-Nearest Neighbor Rule for Semiconductor Manufacturing Processes" published on November 30, 2007).
Consider Claim 23, Baranwal does not explicitly teach “The method of claim 1, wherein detecting defects comprises computing a distance measure between the input representation and the reference representation in the feature space.”. However, in an analogous field of endeavor, He teaches “The method of claim 1, wherein detecting defects comprises computing a distance measure between the input representation and the reference representation in the feature space.” (He; Section I. Introduction; “In other words, a fault sample's distance to the nearest neighboring training samples must be greater than a normal sample's distance to the nearest neighboring training samples. Again, the training samples contain no fault, only normal samples obtained under normal operation conditions. Therefore, if we can determine the distribution of training samples' distances to their nearest neighboring training samples, we can define a threshold distance for a given confidence level. The incoming sample is considered normal if its distance to its nearest neighboring training samples is below the threshold. Otherwise, a fault is detected.”)(emphasis added). Accordingly, before the effective filing date of the instant application, it would have been obvious to one of ordinary skill in the art to combine Baranwal with the teachings of He to further compute the distance between the input and the reference representation in the feature space. One of ordinary skill in the art would be motivated to combine Baranwal and He for more effective detect defects to “achieve the following goals: 1) reducing scrap; 2) increasing equipment uptime; and 3) reducing the usage of test wafers.” (He; Section I. Introduction). Accordingly, the combination of Baranwal and He discloses the invention of Claim 23.
Claims 9, 17-19, 27 and 30-32 are rejected under 35 U.S.C. 103 as being unpatentable over Baranwal (“A Deep Learning Toolset to Mask Analysis with SEM Digital Twins” published in April, 2021) in view of Ofir (US 20240338811 with filing date April 04/2023).
Consider Claim 9, Baranwal teaches “The method of claim 8, wherein the input machine learning model is trained to reconstruct the subset of the imaging dataset and/or wherein the reference machine learning model is trained to reconstruct the subset of the reference dataset.” (Ofir; [0098]; “…the ML model can be implemented as an autoencoder (AE) or variations thereof (e.g., VAE). Autoencoder is a type of neural network commonly used for the purpose of data reproduction by learning efficient data coding and reconstructing its inputs”). Accordingly, before the effective filing date of the instant application, it would have been obvious to one of ordinary skill in the art to combine Baranwal with the teachings of Ofir to further reconstruct the datasets. One of ordinary skill in the art would be motivated to combine Baranwal and Ofir to “use the representative features to reconstruct a corresponding output image which can be evaluated” (Ofir; [0099]). Accordingly, the combination of Baranwal and Ofir discloses the invention of Claim 9.
Consider Claim 17, Baranwal does not explicitly disclose “The method of claim 10, wherein the input neural network and the reference neural network comprise an autoencoder.” (Ofir; [0098]; “By way of example, the ML model can be implemented as an autoencoder (AE) or variations thereof (e.g., VAE)”). Accordingly, before the effective filing date of the instant application, it would have been obvious to one of ordinary skill in the art to combine Baranwal with the teachings of Ofir to further implement an autoencoder in the neural networks. One of ordinary skill in the art would be motivated to combine Baranwal and Ofir to use the autoencoder to “extract features representative of the input image, and ….learn the distribution of normal patterns and characteristics of defect-free images.” (Ofir; [0099]). Accordingly, the combination of Baranwal and Ofir discloses the invention of Claim 17.
Consider Claim 18, the combination of Baranwal and Ofir teaches “The method of claim 17, wherein the encoder of the autoencoder of the input neural network and the encoder of the autoencoder of the reference neural network have a sequence of at least one intermediate layer in common.” (Ofir; [0008]; “The second ML model can comprise an encoder network and a decoder network, and the first ML model is implemented using the encoder network of the second ML model upon the second ML model being trained.”). The proposed combination as well as the motivation for combining Baranwal and Ofir presented in the rejection of claim 17, apply to claim 18 and are incorporated herein by reference. Thus, the method recited in claim 18 is met by the combination of Baranwal and Ofir.
Consider Claim 19, the combination of Baranwal and Ofir teaches “The method of claim 8, wherein the reference machine learning model differs from the input machine learning model.” (Ofir; FIG. 8 (See image below)). Accordingly, before the effective filing date of the instant application, it would have been obvious to one of ordinary skill in the art to combine Baranwal with the teachings of Ofir to further differ the reference and input learning models. One of ordinary skill in the art would be motivated to combine Baranwal and Ofir to more efficiently train defects detection by further differentiating between known defected data and unknown defected data prior to inputting the dataset into the machine learning model. Accordingly, the combination of Baranwal and Ofir discloses the invention of Claim 19.
PNG
media_image6.png
499
651
media_image6.png
Greyscale
Consider Claim 27, the combination of Baranwal and Ofir teaches “A computer implemented method for training an input machine learning model and/or a reference machine learning model according to claim 17 by minimizing a loss function comprising an alignment loss that penalizes the deviation of each activation of a layer of the one or more layers of the input neural network from the activation of the corresponding layer of the one or more layers of the reference neural network, when presenting a defect-free subset of the imaging dataset to the input neural network and a corresponding subset of the reference dataset to the reference neural network.” (Baranwal, Fig-15 (See image below); 1.3 Deep Learning Model; “The network used a custom loss function to optimize the model, which takes the difference between aligned cad and the output after applying spatial transformation on misaligned cad.”).
PNG
media_image7.png
539
1457
media_image7.png
Greyscale
Consider Claim 30, Baranwal teaches “
Baranwal does not explicitly teach “A computer-readable medium, on which a computer program executable by a computing device is stored, the computer program comprising code”. However, in an analogous field of endeavor, Ofir teaches “A computer-readable medium, on which a computer program executable by a computing device is stored, the computer program comprising code” (Ofir; [0058]; “ The processor of PMC 102 can be configured to execute several functional modules in accordance with computer-readable instructions implemented on a non-transitory computer-readable memory comprised in the PMC.”). Accordingly, before the effective filing date of the instant application, it would have been obvious to one of ordinary skill in the art to combine Baranwal with the teachings of Ofir to further store the computer program on a computer readable medium. One of ordinary skill in the art would be motivated to combine Baranwal and Ofir to allow for real life application of defect detection of circuit patterns. Accordingly, the combination of Baranwal and Ofir discloses the invention of Claim 30.
Consider Claim 31, Baranwal teaches “
Baranwal does not explicitly teach “A computer program product comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method of claim 1.”. However, in an analogous field of endeavor, Ofir teaches “A computer program product comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method of claim 1.”. (Ofir; [0058]; “ The processor of PMC 102 can be configured to execute several functional modules in accordance with computer-readable instructions…”). Accordingly, before the effective filing date of the instant application, it would have been obvious to one of ordinary skill in the art to combine Baranwal with the teachings of Ofir to further implement the steps of method Claim 1 on a computer program. One of ordinary skill in the art would be motivated to combine Baranwal and Ofir to allow for real life application of defect detection of circuit patterns. Accordingly, the combination of Baranwal and Ofir discloses the invention of Claim 31.
Claim 32 recites a system with elements corresponding to the steps recited in Claim 1. Therefore, the recited steps of this claim are mapped to the proposed combination in the same manner as the corresponding elements in its corresponding system claim. Finally, Baranwal does not explicitly disclose “an imaging device configured to provide an imaging dataset of the object comprising integrated circuit patterns; one or more processing devices; and one or more machine-readable hardware storage devices comprising instructions that are executable by the one or more processing devices to perform operations”. However, in an analogous field of endeavor, Ofir teaches “an imaging device configured to provide an imaging dataset of the object comprising integrated circuit patterns;” (Ofir; [0036]; “ By way of non-limiting example, the examination process can include runtime scanning (in a single or in multiple scans), imaging…” (emphasis added)) “one or more processing devices; and” (Ofir; [0059]; “[0059] The processor referred to herein can represent one or more general-purpose processing devices…”) “ one or more machine-readable hardware storage devices comprising instructions that are executable by the one or more processing devices to perform operations” (Ofir; [0058]; “ The processor of PMC 102 can be configured to execute several functional modules in accordance with computer-readable instructions implemented on a non-transitory computer-readable memory comprised in the PMC.”). Accordingly, before the effective filing date of the instant application, it would have been obvious to one of ordinary skill in the art to combine Baranwal with the teachings of Ofir to further apply the method of Claim 1 to a system. One of ordinary skill in the art would be motivated to combine Baranwal and Ofir to allow for real life application of defect detection of circuit patterns. Accordingly, the combination of Baranwal and Ofir discloses the invention of Claim 32.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Annie Pham whose telephone number is (571)272-1673. The examiner can be normally be reached Mon-Fri 9:00a – 5:00p.
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, Amandeep Saini can be reached on (571)272-3382. 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.
/ANNIE H PHAM/ Examiner, Art Unit 2662
/Siamak Harandi/ Primary Examiner, Art Unit 2662
Prosecution Insights