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 .
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.
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 1-30 is/are rejected under 35 U.S.C. 103 as being unpatentable over Shaubi et al (US 20200226420 A1) in view of Zhang et al (US 20170148226 A1)
Regarding claim 1, Shaubi discloses a method for generating synthetic semiconductor image data ([0030] examination system can be used for examination of a specimen (e.g. of a wafer and/or parts thereof) as a part of the specimen fabrication process), the method comprising:
generating a set of synthetic segmented images, each synthetic segmented image of the set of synthetic segmented images representing a segmented semiconductor metrology image ([0030] examination system 100 comprises computer-based system 103 capable of automatically determining metrology-related and/or defect-related information using images obtained during specimen fabrication);
generating, using a first trained GAN, a set of virtual images, each virtual image corresponding to one of the synthetic segmented images in the set of synthetic segmented images;
and constructing a training set comprising a plurality of training samples, each training sample comprising a synthetic segmented image from the set of synthetics segmented images and a corresponding virtual image from the set of virtual images, wherein the training set is usable to train a downstream model configured to model semiconductor fabrication processes ([0034] The weighting and/or threshold values of a deep neural network can be initially selected prior to training, and can be further iteratively adjusted or modified during training to achieve an optimal set of weighting and/or threshold values in a trained DNN. After each iteration, a difference can be determined between the actual output produced by DNN module and the target output associated with the respective training set of data.).
Zhang generating, using a first trained GAN, a set of virtual images, each virtual image corresponding to one of the synthetic segmented images in the set of synthetic segmented images ([0086] the one or more computer subsystems are configured for training the two or more encoder layers and the two or more decoder layers by learning the features for design information in a training dataset, and the learning includes inferring the features for the design information in the training dataset using the two or more encoder layers, regenerating the design information in the training dataset from the inferred features using the two or more decoder layers, generating simulated images for the design information in the training dataset from the inferred features using the two or more decoder layers, and modifying one or more parameters of the two or more decoder layers until the simulated images for the design information in the training dataset match actual images for the design information in the training dataset)
Shaubi and Zhang are combinable because they are from the same field of invention.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify examination system of Shaubi to include generating, using a first trained GAN, a set of virtual images, each virtual image corresponding to one of the synthetic segmented images in the set of synthetic segmented images as described by Zhang
The motivation for doing so would have been to generate simulated images from design information including generative model includes two or more encoder layers configured for determining features of design information for a specimen (Zhang, [0012]).
Therefore, it would have been obvious to combine Shaubi and Zhang to obtain the invention as specified in claim 1.
Regarding claim 2, Shaubi discloses wherein the set of synthetic segmented images are generated using a second trained GAN ([0032] , the layers of DNN can be organized in accordance with Convolutional Neural Network (CNN) architecture, Recurrent Neural Network architecture, Recursive Neural Networks architecture, Generative Adversarial Network (GAN) architecture or otherwise).
Regarding claim 3, Shaubi discloses wherein the first trained GAN and the second trained GAN were trained concurrently ([0056] generating the training set can include generating synthetic images (and obtaining the ground truth data if necessary) and including the synthetic images into the training samples.).
Regarding claim 4, Shaubi discloses wherein training the first trained GAN and the second trained GAN concurrently comprises updating weights associated with a first discriminator and a first generator associated with the first trained GAN based on a discriminator loss and/or a generator loss associated with a second discriminator and/or a second generator associated with the second trained GAN ([0033] given CE can be configured to compute an activation value (e.g. the weighted sum of the inputs) and further derive an output by applying an activation function to the computed activation. The activation function can be, for example, an identity function, a deterministic function (e.g., linear, sigmoid, threshold, or the like), a stochastic function or other suitable function.).
Regarding claim 5, Shaubi discloses wherein generating the set of synthetic segmented images comprises generating each synthetic segmented image using a semiconductor process model ([0030] examination tools are configured to capture FP images and/or to review the captured FP image(s) and/or to enable or provide measurements related to the captured image(s).).
Regarding claim 6, Shaubi discloses wherein the semiconductor process model is a model configured to represent a particular semiconductor fabrication process ([0030] The system 103 is referred to hereinafter as an FPEI (Fabrication Process Examination Information) system. FPEI system 103 can be operatively connected to one or more low-resolution examination tools 101 and/or one or more high-resolution examination tools 102 and/or other examination tools.).
Regarding claim 7, Shaubi is silent to wherein the particular semiconductor fabrication process is an etch process, and wherein the semiconductor process model generates image representing an etch profile as a result of the etch process given a set of process conditions provided as an input to the semiconductor process model.
Zhang discloses wherein the particular semiconductor fabrication process is an etch process, and wherein the semiconductor process model generates image representing an etch profile as a result of the etch process given a set of process conditions provided as an input to the semiconductor process model ([0097] simulate the variations that may be present in the patterned features on the specimen (and therefore in images of the patterned features) that are due to post-lithography processes such as etch and chemical-mechanical polishing (CMP), which cannot be simulated by models that are capable of only simulating the optical processes involved in printing the patterned features on the specimen and/or the processes (optical or otherwise) involved in generating images of the patterned features on the specimen).
Shaubi and Zhang are combinable because they are from the same field of invention.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify examination system of Shaubi to include wherein the particular semiconductor fabrication process is an etch process, and wherein the semiconductor process model generates image representing an etch profile as a result of the etch process given a set of process conditions provided as an input to the semiconductor process model as described by Zhang
The motivation for doing so would have been to generate simulated images from design information including generative model includes two or more encoder layers configured for determining features of design information for a specimen (Zhang, [0012]).
Therefore, it would have been obvious to combine Shaubi and Zhang to obtain the invention as specified in claim 7.
Regarding claim 8, Shaubi discloses further comprising applying a texture mapping deformation technique to at least one synthetic segmented image of the set of synthetic segmented images generated by the semiconductor process model, and wherein the at least one synthetic segmented image to which the texture mapping deformation technique is applied is included in the set of synthetic segmented images ([0056] Generating the training set can include augmenting the training samples (and the ground truth data if applicable) and including the augmented training images and augmented ground truth data into the training samples)
Regarding claim 9, Shaubi discloses wherein generating the set of virtual images comprises:
generating, from a given synthetic segmented image of the set of synthetic segmented images, a corresponding gray scale image ([0028] . Design data can be provided in different formats as, by way of non-limiting examples, GDSII format, OASIS format, etc. Design data can be presented in vector format, grayscale intensity image format or otherwise.); and
providing the corresponding gray scale image to the first trained GAN ([0034] Training can be determined to be complete when a cost function indicative of the error value is less than a predetermined value or when a limited change in performance between iterations is achieved).
Regarding claim 10, Shaubi discloses wherein generating the corresponding gray scale image comprises applying a randomly generated color palette to the given synthetic segmented image.
Regarding claim 11, Shaubi discloses wherein the segmented semiconductor metrology image corresponds to an electron microscopy (EM) image, scanning electron microscopy (SEM) image, a critical-dimension SEM image (CD-SEM), or a transmission electron microscopy (TEM) image ([0041] the specimen can be examined by a high-resolution machine 102 (e.g. a subset of potential defect locations selected for review can be reviewed by a scanning electron microscope (SEM) or Atomic Force Microscopy (AFM))).
Regarding claim 12, Shaubi discloses wherein the downstream model trained using the training set is configured to label interfaces between materials in an input image having a same type as the segmented semiconductor metrology image ([0050] segmentation of the fabrication process image including partitioning of FP image into segments (e.g. material types, edges, pixel labeling, regions of interest, etc.);).
Regarding claim 13, Shaubi discloses wherein the downstream model trained using the training set is configured to provide dimension measurements of one or more wafer features included in an input image having a same type as the segmented semiconductor metrology image ([0066] FP sample can further comprise metadata (e.g. imaging conditions, pixel-size, engineered attributes (e.g. defect size, orientation, background segment, etc.),)
Regarding claim 14, Shaubi discloses wherein the downstream model trained using the training set is configured to provide at least one measurement associated with an interface between materials in an input image having a same type as the segmented semiconductor metrology image ([0050] segmentation of the fabrication process image including partitioning of FP image into segments (e.g. material types, edges, pixel labeling, regions of interest, etc.)).
Regarding claim 15, Shaubi discloses wherein the first trained GAN utilizes a plurality of sets of discriminators and generators, each set of discriminator and generator corresponding to a different layer of a pyramidal structure, and each layer configured to utilize an image of a different size ([0098] Upon training, latent space 603 shall represent mapping of observed data (FAB data or part thereof stored in real world images database 606) to very high dimensional abstract hyperplane (Z-space),)..
Regarding claim 16, Shaubi discloses wherein each set of discriminator and generator of the plurality of sets of discriminators and generators are trained sequentially ([0034] Training can be determined to be complete when a cost function indicative of the error value is less than a predetermined value or when a limited change in performance between iterations is achieved).
Regarding claim 17, Shaubi discloses A computer program product comprising a non-transitory computer readable medium on which is provided computer executable instructions ([0015] there is provided a non-transitory computer readable medium comprising instructions that, when executed by a computer, cause the computer to perform the method above.)
for causing a computational system to perform a method for generating synthetic semiconductor image data ([0030] examination system can be used for examination of a specimen (e.g. of a wafer and/or parts thereof) as a part of the specimen fabrication process), the method comprising:
generating a set of synthetic segmented images, each synthetic segmented image of the set of synthetic segmented images representing a segmented semiconductor metrology image ([0030] examination system 100 comprises computer-based system 103 capable of automatically determining metrology-related and/or defect-related information using images obtained during specimen fabrication);
generating, using a first trained GAN, a set of virtual images, each virtual image corresponding to one of the synthetic segmented images in the set of synthetic segmented images;
and constructing a training set comprising a plurality of training samples, each training sample comprising a synthetic segmented image from the set of synthetics segmented images and a corresponding virtual image from the set of virtual images, wherein the training set is usable to train a downstream model configured to model semiconductor fabrication processes ([0034] The weighting and/or threshold values of a deep neural network can be initially selected prior to training, and can be further iteratively adjusted or modified during training to achieve an optimal set of weighting and/or threshold values in a trained DNN. After each iteration, a difference can be determined between the actual output produced by DNN module and the target output associated with the respective training set of data.).
Zhang generating, using a first trained GAN, a set of virtual images, each virtual image corresponding to one of the synthetic segmented images in the set of synthetic segmented images ([0086] the one or more computer subsystems are configured for training the two or more encoder layers and the two or more decoder layers by learning the features for design information in a training dataset, and the learning includes inferring the features for the design information in the training dataset using the two or more encoder layers, regenerating the design information in the training dataset from the inferred features using the two or more decoder layers, generating simulated images for the design information in the training dataset from the inferred features using the two or more decoder layers, and modifying one or more parameters of the two or more decoder layers until the simulated images for the design information in the training dataset match actual images for the design information in the training dataset)
Shaubi and Zhang are combinable because they are from the same field of invention.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify examination system of Shaubi to include generating, using a first trained GAN, a set of virtual images, each virtual image corresponding to one of the synthetic segmented images in the set of synthetic segmented images as described by Zhang
The motivation for doing so would have been to generate simulated images from design information including generative model includes two or more encoder layers configured for determining features of design information for a specimen (Zhang, [0012]).
Therefore, it would have been obvious to combine Shaubi and Zhang to obtain the invention as specified in claim 17.
Regarding claim 18, Shaubi discloses wherein the set of synthetic segmented images are generated using a second trained GAN ([0032] , the layers of DNN can be organized in accordance with Convolutional Neural Network (CNN) architecture, Recurrent Neural Network architecture, Recursive Neural Networks architecture, Generative Adversarial Network (GAN) architecture or otherwise).
Regarding claim 19, Shaubi discloses wherein the first trained GAN and the second trained GAN were trained concurrently ([0056] generating the training set can include generating synthetic images (and obtaining the ground truth data if necessary) and including the synthetic images into the training samples.).
Regarding claim 20, Shaubi discloses wherein training the first trained GAN and the second trained GAN concurrently comprises updating weights associated with a first discriminator and a first generator associated with the first trained GAN based on a discriminator loss and/or a generator loss associated with a second discriminator and/or a second generator associated with the second trained GAN ([0033] given CE can be configured to compute an activation value (e.g. the weighted sum of the inputs) and further derive an output by applying an activation function to the computed activation. The activation function can be, for example, an identity function, a deterministic function (e.g., linear, sigmoid, threshold, or the like), a stochastic function or other suitable function.).
Regarding claim 21, Shaubi discloses wherein generating the set of synthetic segmented images comprises generating each synthetic segmented image using a semiconductor process model ([0030] examination tools are configured to capture FP images and/or to review the captured FP image(s) and/or to enable or provide measurements related to the captured image(s).).
Regarding claim 22, Shaubi discloses wherein the semiconductor process model is a model configured to represent a particular semiconductor fabrication process ([0030] The system 103 is referred to hereinafter as an FPEI (Fabrication Process Examination Information) system. FPEI system 103 can be operatively connected to one or more low-resolution examination tools 101 and/or one or more high-resolution examination tools 102 and/or other examination tools.).
Regarding claim 23, Shaubi is silent to wherein the particular semiconductor fabrication process is an etch process, and wherein the semiconductor process model generates image representing an etch profile as a result of the etch process given a set of process conditions provided as an input to the semiconductor process model.
Zhang discloses wherein the particular semiconductor fabrication process is an etch process, and wherein the semiconductor process model generates image representing an etch profile as a result of the etch process given a set of process conditions provided as an input to the semiconductor process model ([0097] simulate the variations that may be present in the patterned features on the specimen (and therefore in images of the patterned features) that are due to post-lithography processes such as etch and chemical-mechanical polishing (CMP), which cannot be simulated by models that are capable of only simulating the optical processes involved in printing the patterned features on the specimen and/or the processes (optical or otherwise) involved in generating images of the patterned features on the specimen).
Shaubi and Zhang are combinable because they are from the same field of invention.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify examination system of Shaubi to include wherein the particular semiconductor fabrication process is an etch process, and wherein the semiconductor process model generates image representing an etch profile as a result of the etch process given a set of process conditions provided as an input to the semiconductor process model as described by Zhang
The motivation for doing so would have been to generate simulated images from design information including generative model includes two or more encoder layers configured for determining features of design information for a specimen (Zhang, [0012]).
Therefore, it would have been obvious to combine Shaubi and Zhang to obtain the invention as specified in claim 23.
Regarding claim 24, Shaubi discloses further comprising applying a texture mapping deformation technique to at least one synthetic segmented image of the set of synthetic segmented images generated by the semiconductor process model, and wherein the at least one synthetic segmented image to which the texture mapping deformation technique is applied is included in the set of synthetic segmented images ([0056] Generating the training set can include augmenting the training samples (and the ground truth data if applicable) and including the augmented training images and augmented ground truth data into the training samples)
Regarding claim 25, Shaubi discloses wherein generating the set of virtual images comprises:
generating, from a given synthetic segmented image of the set of synthetic segmented images, a corresponding gray scale image ([0028] . Design data can be provided in different formats as, by way of non-limiting examples, GDSII format, OASIS format, etc. Design data can be presented in vector format, grayscale intensity image format or otherwise.); and
providing the corresponding gray scale image to the first trained GAN ([0034] Training can be determined to be complete when a cost function indicative of the error value is less than a predetermined value or when a limited change in performance between iterations is achieved).
Regarding claim 26, Shaubi discloses wherein generating the corresponding gray scale image comprises applying a randomly generated color palette to the given synthetic segmented image.
Regarding claim 27, Shaubi discloses wherein the segmented semiconductor metrology image corresponds to an electron microscopy (EM) image, scanning electron microscopy (SEM) image, a critical-dimension SEM image (CD-SEM), or a transmission electron microscopy (TEM) image ([0041] the specimen can be examined by a high-resolution machine 102 (e.g. a subset of potential defect locations selected for review can be reviewed by a scanning electron microscope (SEM) or Atomic Force Microscopy (AFM))).
Regarding claim 28, Shaubi discloses wherein the downstream model trained using the training set is configured to label interfaces between materials in an input image having a same type as the segmented semiconductor metrology image ([0050] segmentation of the fabrication process image including partitioning of FP image into segments (e.g. material types, edges, pixel labeling, regions of interest, etc.);).
Regarding claim 29, Shaubi discloses wherein the downstream model trained using the training set is configured to provide dimension measurements of one or more wafer features included in an input image having a same type as the segmented semiconductor metrology image ([0066] FP sample can further comprise metadata (e.g. imaging conditions, pixel-size, engineered attributes (e.g. defect size, orientation, background segment, etc.),)
Regarding claim 30, Shaubi discloses wherein the downstream model trained using the training set is configured to provide at least one measurement associated with an interface between materials in an input image having a same type as the segmented semiconductor metrology image ([0050] segmentation of the fabrication process image including partitioning of FP image into segments (e.g. material types, edges, pixel labeling, regions of interest, etc.)).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SHIVANG I PATEL whose telephone number is (571)272-8964. The examiner can normally be reached on M-F 9am-5pm.
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, Alicia Harrington can be reached on (571) 272-2330. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see https://ppair-my.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/SHIVANG I PATEL/Primary Examiner, Art Unit 2615
