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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 12/13/2024. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
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 of this title, 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 1-10, 13, 15-20 are rejected under 35 U.S.C. 103 as being unpatentable over Hotta et al. (US Pub No. 20110155904 A1) in view of Gutman et al. (US Pub No. 20190178639 A1).
Regarding Claim 1,
Hotta discloses A system comprising one or more processing circuitries, wherein the one or more processing circuitries are operative, wherein the one or more processing circuitries are configured to: (Hotta, [0014], discloses a system for measuring relative positions of a plurality of semiconductor device layers in a double-patterning semiconductor device fabrication process includes an image acquisition module, an image processing module, a display device, and an output module; system is disclosed)
obtain a design image of the given overlay target, feed the design image to simulate at least one image of the given overlay target that would have been acquired by an electron beam examination system, (Hotta, [0002-0003], [0008-0009], [0055], Fig. 6, discloses measurement system 600 for evaluating the degradation of pattern features according to various embodiments. The measurement system 600 includes a microscope for imaging minute features of a sample. For example, the microscope is a critical-dimension scanning electron microscope (CD-SEM) 602. The CD-SEM 602 includes a microscope column 604 with a variety of components for electron beam generation and detection. An electron gun 608 produces an electron beam 612, the direction and width of which are controlled using a first electromagnetic lens 610, a second electromagnetic lens 616, and a deflector 614. The electron beam 612 irradiates a particular location 622 on a sample 620 with electrons thereby generating secondary electrons 624; [0002] A semiconductor device is formed by patterning one or more layers on a semiconductor substrate or wafer. In the semiconductor manufacturing process, the overlay between previous patterned layers and a current layer to be patterned is controlled to within a tight tolerance, referred to as an overlay error budget. Typically, overlay between different layers has been measured by optical microscopy of relatively large targets specifically designed for overlay analysis. These targets are referred to as optical overlay targets, examples of which are shown in FIGS. 1A-1D. The sizes of these overlay targets vary from between 10 .mu.m and 40 .mu.m; overlay is independently measured for each subsequently patterned layer with respect to the previously patterned layer, thus requiring overlay targets positioned on each layer. Moreover, to allow for independent measurement, overlay targets should not overlap. Overlay targets thus require a significant amount of substrate area because of these size and non-overlap requirements. To improve overlay measurement precision, additional sampling is desired. Thus, there exists necessarily a trade-off between overlay target size and location with overlay measurement precision due to semiconductor device area considerations; actual device patterns imaged via scanning electron microscopy (SEM) are used to measure overlay between different layers in a semiconductor manufacturing process, for example, a double-patterning process. Images of features from two or more patterning layers are acquired by SEM. An edge detection algorithm is applied to all or a selected portion of the features in the images. The relative positions of these features are then determined using the detected edge information. The position of a respective patterning layer can thus be determined using the relative position information of all or a selected portion of the imaged features for the respective patterning layer. A relative position of each patterning layer with respect to the other patterning layers is determined, for example, in vector form, based on the determined feature positions. Overlay error between the two or more patterning layers is determined based on a comparison of the relative position with reference values from design or simulation; a method for measuring relative positions of a plurality of semiconductor device layers includes selecting one or more patterns for each semiconductor device layer. Each semiconductor device layer includes one or more patterns. The one or more selected patterns are selected based on line symmetry or point symmetry of said patterns within at least one said semiconductor device layer. The method further includes obtaining one or more CD-SEM images of the selected patterns. The method also includes calculating a relative pattern position between each semiconductor device layer based on the obtained CD-SEM images; CD-SEM images (design image) corresponding to the electron beam semiconductor overlay image (pattern) is obtained)
use the at least one image to determine, before actual manufacturing of the given overlay target, data informative of at least one simulated overlay in the at least one image, (Hotta, [0010], discloses a method for measuring relative positions of a plurality of semiconductor device layers in a double-patterning semiconductor fabrication process includes selecting a plurality of patterns for each semiconductor device layer. Each semiconductor device layer is formed using a different mask. The plurality of patterns includes contact holes for a semiconductor device. The plurality of selected patterns is selected based on a symmetry of the contact holes in at least a first pattern of the plurality of selected patterns. The symmetry of contact holes is determined with respect to at least one line extending in a first direction across the first pattern; position (data informative) is determined based on the informative of the simulated and obtained image patterns) and
use the data informative of the at least one simulated overlay of each given
overlay target to select at least one optimal overlay target among the plurality of different overlay targets, wherein the at least one optimal overlay target is
usable to be actually manufactured on the semiconductor specimen. (Hotta, [0011-0013], discloses obtaining one or more critical dimension scanning electron microscope (CD-SEM) images of the selected patterns. A magnification used for confirming the positions of the patterns is lower than that used for the obtaining one or more CD-SEM images. The method also includes extracting edge information associated with the patterns in the CD-SEM images. The edge information includes a contour of at least one of the selected patterns; determining a pattern position for each semiconductor device layer by calculating a pattern position centroid of each of the selected patterns based on the edge information. The method further includes calculating a relative pattern position between each semiconductor device layer based on the determined pattern positions. The relative pattern position includes position information in two dimensions; on an output display device the relative pattern position between each semiconductor device layer in vector form and displaying on the output display device the pattern position of each semiconductor device layer together with the relative pattern position between each semiconductor device layer. The method further includes comparing the relative pattern position between each said semiconductor device layer to a predetermined reference value and outputting a notification if a difference between the relative pattern position and the predetermined reference vector exceeds a predetermined tolerance; relative positions of overlay patterns and design patterns are determined and patterns among the compared and patterns that matches the overlay are selected that are within the tolerances)
Hotta does not explicitly disclose implement a trained machine learning model,
feed the image to a trained machine learning model.
Gutman discloses implement a trained machine learning model,
feed the image to a trained machine learning model (Gutman, [0074-0075], discloses a mapping between scan signals and asymmetry offsets may be generated by training a machine-learning algorithm such as, but not limited to, a neural network, or a support-vector machine (SVM) algorithm. For example, the corresponding asymmetry offsets and any combination of calibration scan signals (e.g., the calibration scan signals 514) or symmetry measurements of the calibration signals based on one or more symmetry metrics may be provided as training signals to the machine learning algorithm. In this regard, the machine-learning algorithm may determine correlations between the asymmetry offsets and associated calibration scan signals and/or symmetry measurements of the calibration scan signals. Once the machine-learning algorithm has been trained, the machine-learning algorithm may determine asymmetry offsets for the sample 118 being measured based on the scan signals generated in step 202 and the mapping generated during the training phase; the step 208 includes generating an overlay measurement for the sample layers of interest based on the asymmetry offsets between the overlay target features on the sample layers. As described previously herein, an overlay target may be fabricated with any selected asymmetry offsets of the overlay target elements. Accordingly, the step 208 may include adjusting the asymmetry offsets by a selected value to generate the overlay measurement; machine learning model is trained on image overlay patterns and overlay target is fabricated based on machine learning model selected manufacturing overlay patterns)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Hotta in view of Hotta having a method of matching design image and simulated overlay image patterns to determine optimal manufacturing overlay with the teachings of Gutman having a machine learning model to train and optimize the pattern matching for manufacturing precise overlay layer semiconductor images.
Regarding Claim 2,
The combination of Hotta and Gutman further discloses obtain one or more parameters of the electron beam examination system, and feed the one or more parameters and the design image to the trained machine learning model, to simulate the at least one image of the given overlay target that would have been acquired by an electron beam examination system with said one or more parameters. (Gutman, [0074-0075], discloses a mapping between scan signals and asymmetry offsets may be generated by training a machine-learning algorithm such as, but not limited to, a neural network, or a support-vector machine (SVM) algorithm. For example, the corresponding asymmetry offsets and any combination of calibration scan signals (e.g., the calibration scan signals 514) or symmetry measurements of the calibration signals based on one or more symmetry metrics may be provided as training signals to the machine learning algorithm. In this regard, the machine-learning algorithm may determine correlations between the asymmetry offsets and associated calibration scan signals and/or symmetry measurements of the calibration scan signals. Once the machine-learning algorithm has been trained, the machine-learning algorithm may determine asymmetry offsets for the sample 118 being measured based on the scan signals generated in step 202 and the mapping generated during the training phase; the step 208 includes generating an overlay measurement for the sample layers of interest based on the asymmetry offsets between the overlay target features on the sample layers. As described previously herein, an overlay target may be fabricated with any selected asymmetry offsets of the overlay target elements. Accordingly, the step 208 may include adjusting the asymmetry offsets by a selected value to generate the overlay measurement; machine learning model is trained on image overlay patterns and overlay target is fabricated based on machine learning model selected manufacturing overlay patterns and the parameters (features)). Additionally, the rational and motivation to combine the references Hotta and Gutman as applied in rejection of claim 1 apply to this claim.
Regarding Claim 3,
The combination of Hotta and Gutman further discloses wherein each given overlay target is associated with at least one given overlay value in the design data, wherein the system is configured to determine, for at least one given overlay target, data informative of a difference between the at least one simulated overlay and the at least one given overlay value, and to use the data informative of a difference between the at least one simulated overlay and the at least one given overlay value of the at least one given overlay target to update design data associated with the at least one given overlay target. (Gutman, [0074-0075], discloses a mapping between scan signals and asymmetry offsets may be generated by training a machine-learning algorithm such as, but not limited to, a neural network, or a support-vector machine (SVM) algorithm. For example, the corresponding asymmetry offsets and any combination of calibration scan signals (e.g., the calibration scan signals 514) or symmetry measurements of the calibration signals based on one or more symmetry metrics may be provided as training signals to the machine learning algorithm. In this regard, the machine-learning algorithm may determine correlations between the asymmetry offsets and associated calibration scan signals and/or symmetry measurements of the calibration scan signals. Once the machine-learning algorithm has been trained, the machine-learning algorithm may determine asymmetry offsets for the sample 118 being measured based on the scan signals generated in step 202 and the mapping generated during the training phase; the step 208 includes generating an overlay measurement for the sample layers of interest based on the asymmetry offsets between the overlay target features on the sample layers. As described previously herein, an overlay target may be fabricated with any selected asymmetry offsets of the overlay target elements. Accordingly, the step 208 may include adjusting the asymmetry offsets by a selected value to generate the overlay measurement; machine learning model is trained on image overlay patterns and overlay target is fabricated based on machine learning model selected manufacturing overlay patterns). Additionally, the rational and motivation to combine the references Hotta and Gutman as applied in rejection of claim 1 apply to this claim.
Regarding Claim 4,
The combination of Hotta and Gutman further discloses wherein each given overlay target is associated with at least one given overlay value in the design data, wherein the system is configured to determine, for each given overlay target, data informative of a difference between the at least one simulated overlay and the at least one given overlay value and use said data to select said at least one optimal overlay target among the plurality of different overlay targets. (Gutman, [0074-0075], discloses a mapping between scan signals and asymmetry offsets may be generated by training a machine-learning algorithm such as, but not limited to, a neural network, or a support-vector machine (SVM) algorithm. For example, the corresponding asymmetry offsets and any combination of calibration scan signals (e.g., the calibration scan signals 514) or symmetry measurements of the calibration signals based on one or more symmetry metrics may be provided as training signals to the machine learning algorithm. In this regard, the machine-learning algorithm may determine correlations between the asymmetry offsets and associated calibration scan signals and/or symmetry measurements of the calibration scan signals. Once the machine-learning algorithm has been trained, the machine-learning algorithm may determine asymmetry offsets for the sample 118 being measured based on the scan signals generated in step 202 and the mapping generated during the training phase; the step 208 includes generating an overlay measurement for the sample layers of interest based on the asymmetry offsets between the overlay target features on the sample layers. As described previously herein, an overlay target may be fabricated with any selected asymmetry offsets of the overlay target elements. Accordingly, the step 208 may include adjusting the asymmetry offsets by a selected value to generate the overlay measurement; machine learning model is trained on image overlay patterns and overlay target is fabricated based on machine learning model selected manufacturing overlay patterns and offset values (differences in patterns of overlay target image data and simulated image information data is determined). Additionally, the rational and motivation to combine the references Hotta and Gutman as applied in rejection of claim 1 apply to this claim.
Regarding Claim 5,
The combination of Hotta and Gutman further discloses for at least one given overlay target: for each given overlay value of a plurality of overlay values, feed
a design image associated with the given overlay value to the trained machine learning model, to simulate an image of the given overlay target associated with the given overlay value, that would have been acquired by the electron beam examination system, thereby obtaining a set of a plurality of images, and before actual manufacturing of the given overlay target, determine, in each image of the set of a plurality of images, data informative of at least one given simulated overlay in the image. (Gutman, [0074-0075], discloses a mapping between scan signals and asymmetry offsets may be generated by training a machine-learning algorithm such as, but not limited to, a neural network, or a support-vector machine (SVM) algorithm. For example, the corresponding asymmetry offsets and any combination of calibration scan signals (e.g., the calibration scan signals 514) or symmetry measurements of the calibration signals based on one or more symmetry metrics may be provided as training signals to the machine learning algorithm. In this regard, the machine-learning algorithm may determine correlations between the asymmetry offsets and associated calibration scan signals and/or symmetry measurements of the calibration scan signals. Once the machine-learning algorithm has been trained, the machine-learning algorithm may determine asymmetry offsets for the sample 118 being measured based on the scan signals generated in step 202 and the mapping generated during the training phase; the step 208 includes generating an overlay measurement for the sample layers of interest based on the asymmetry offsets between the overlay target features on the sample layers. As described previously herein, an overlay target may be fabricated with any selected asymmetry offsets of the overlay target elements. Accordingly, the step 208 may include adjusting the asymmetry offsets by a selected value to generate the overlay measurement; machine learning model is trained on image overlay patterns and overlay target is fabricated based on machine learning model selected manufacturing overlay patterns)
Regarding Claim 6,
The combination of Hotta and Gutman further discloses determine, for each given overlay target, for each given overlay value of the plurality of overlay values, data informative of a difference between the given simulated overlay and the given overlay value, and use said data to select the at least one optimal overlay target among the plurality of different overlay targets. (Gutman, [0074-0075], discloses a mapping between scan signals and asymmetry offsets may be generated by training a machine-learning algorithm such as, but not limited to, a neural network, or a support-vector machine (SVM) algorithm. For example, the corresponding asymmetry offsets and any combination of calibration scan signals (e.g., the calibration scan signals 514) or symmetry measurements of the calibration signals based on one or more symmetry metrics may be provided as training signals to the machine learning algorithm. In this regard, the machine-learning algorithm may determine correlations between the asymmetry offsets and associated calibration scan signals and/or symmetry measurements of the calibration scan signals. Once the machine-learning algorithm has been trained, the machine-learning algorithm may determine asymmetry offsets for the sample 118 being measured based on the scan signals generated in step 202 and the mapping generated during the training phase; the step 208 includes generating an overlay measurement for the sample layers of interest based on the asymmetry offsets between the overlay target features on the sample layers. As described previously herein, an overlay target may be fabricated with any selected asymmetry offsets of the overlay target elements. Accordingly, the step 208 may include adjusting the asymmetry offsets by a selected value to generate the overlay measurement; machine learning model is trained on image overlay patterns and overlay target is fabricated based on machine learning model selected manufacturing overlay patterns)
Regarding Claim 7,
The combination of Hotta and Gutman further discloses upon manufacturing of the optimal overlay target: obtain an inspection image of the optimal overlay target acquired using an electron beam examination system, and determine at least one actual overlay based on the inspection image. (Gutman, [0074-0075], discloses a mapping between scan signals and asymmetry offsets may be generated by training a machine-learning algorithm such as, but not limited to, a neural network, or a support-vector machine (SVM) algorithm. For example, the corresponding asymmetry offsets and any combination of calibration scan signals (e.g., the calibration scan signals 514) or symmetry measurements of the calibration signals based on one or more symmetry metrics may be provided as training signals to the machine learning algorithm. In this regard, the machine-learning algorithm may determine correlations between the asymmetry offsets and associated calibration scan signals and/or symmetry measurements of the calibration scan signals. Once the machine-learning algorithm has been trained, the machine-learning algorithm may determine asymmetry offsets for the sample 118 being measured based on the scan signals generated in step 202 and the mapping generated during the training phase; the step 208 includes generating an overlay measurement for the sample layers of interest based on the asymmetry offsets between the overlay target features on the sample layers. As described previously herein, an overlay target may be fabricated with any selected asymmetry offsets of the overlay target elements. Accordingly, the step 208 may include adjusting the asymmetry offsets by a selected value to generate the overlay measurement; machine learning model is trained on image overlay patterns and overlay target is fabricated based on machine learning model selected manufacturing overlay patterns)
Regarding Claim 8,
The combination of Hotta and Gutman further discloses wherein the optimal overlay target is associated with at least one given overlay value in the design data, wherein the system is configured to compare the at least one actual overlay with the at least one given overlay value associated with the optimal overlay target. (Gutman, [0074-0075], discloses a mapping between scan signals and asymmetry offsets may be generated by training a machine-learning algorithm such as, but not limited to, a neural network, or a support-vector machine (SVM) algorithm. For example, the corresponding asymmetry offsets and any combination of calibration scan signals (e.g., the calibration scan signals 514) or symmetry measurements of the calibration signals based on one or more symmetry metrics may be provided as training signals to the machine learning algorithm. In this regard, the machine-learning algorithm may determine correlations between the asymmetry offsets and associated calibration scan signals and/or symmetry measurements of the calibration scan signals. Once the machine-learning algorithm has been trained, the machine-learning algorithm may determine asymmetry offsets for the sample 118 being measured based on the scan signals generated in step 202 and the mapping generated during the training phase; the step 208 includes generating an overlay measurement for the sample layers of interest based on the asymmetry offsets between the overlay target features on the sample layers. As described previously herein, an overlay target may be fabricated with any selected asymmetry offsets of the overlay target elements. Accordingly, the step 208 may include adjusting the asymmetry offsets by a selected value to generate the overlay measurement; machine learning model is trained on image overlay patterns and overlay target is fabricated based on machine learning model selected manufacturing overlay patterns)
Regarding Claim 9,
The combination of Hotta and Gutman further discloses to determine data informative of a quality of the inspection image. (Gutman, [0074-0075], discloses a mapping between scan signals and asymmetry offsets may be generated by training a machine-learning algorithm such as, but not limited to, a neural network, or a support-vector machine (SVM) algorithm. For example, the corresponding asymmetry offsets and any combination of calibration scan signals (e.g., the calibration scan signals 514) or symmetry measurements of the calibration signals based on one or more symmetry metrics may be provided as training signals to the machine learning algorithm. In this regard, the machine-learning algorithm may determine correlations between the asymmetry offsets and associated calibration scan signals and/or symmetry measurements of the calibration scan signals. Once the machine-learning algorithm has been trained, the machine-learning algorithm may determine asymmetry offsets for the sample 118 being measured based on the scan signals generated in step 202 and the mapping generated during the training phase; the step 208 includes generating an overlay measurement for the sample layers of interest based on the asymmetry offsets between the overlay target features on the sample layers. As described previously herein, an overlay target may be fabricated with any selected asymmetry offsets of the overlay target elements. Accordingly, the step 208 may include adjusting the asymmetry offsets by a selected value to generate the overlay measurement; machine learning model is trained on image overlay patterns and overlay target is fabricated based on machine learning model selected manufacturing overlay patterns)
Regarding Claim 10,
The combination of Hotta and Gutman further discloses wherein the system enables user modification of a level of noise present in the at least one image generated by the machine learning model. (Gutman, [0074-0075], discloses a mapping between scan signals and asymmetry offsets may be generated by training a machine-learning algorithm such as, but not limited to, a neural network, or a support-vector machine (SVM) algorithm. For example, the corresponding asymmetry offsets and any combination of calibration scan signals (e.g., the calibration scan signals 514) or symmetry measurements of the calibration signals based on one or more symmetry metrics may be provided as training signals to the machine learning algorithm. In this regard, the machine-learning algorithm may determine correlations between the asymmetry offsets and associated calibration scan signals and/or symmetry measurements of the calibration scan signals. Once the machine-learning algorithm has been trained, the machine-learning algorithm may determine asymmetry offsets for the sample 118 being measured based on the scan signals generated in step 202 and the mapping generated during the training phase; the step 208 includes generating an overlay measurement for the sample layers of interest based on the asymmetry offsets between the overlay target features on the sample layers. As described previously herein, an overlay target may be fabricated with any selected asymmetry offsets of the overlay target elements. Accordingly, the step 208 may include adjusting the asymmetry offsets by a selected value to generate the overlay measurement; machine learning model is trained on image overlay patterns and overlay target is fabricated based on machine learning model selected manufacturing overlay patterns)
Regarding Claim 13,
The combination of Hotta and Gutman further discloses wherein the trained machine learning model has been trained using a training set including, for each given manufactured overlay target of a plurality of manufactured overlay targets: at least one image of the given manufactured overlay target acquired by an electron beam examination system, a design image associated with the given manufactured overlay target and one or more parameters of the electron beam examination system. (Gutman, [0074-0075], discloses a mapping between scan signals and asymmetry offsets may be generated by training a machine-learning algorithm such as, but not limited to, a neural network, or a support-vector machine (SVM) algorithm. For example, the corresponding asymmetry offsets and any combination of calibration scan signals (e.g., the calibration scan signals 514) or symmetry measurements of the calibration signals based on one or more symmetry metrics may be provided as training signals to the machine learning algorithm. In this regard, the machine-learning algorithm may determine correlations between the asymmetry offsets and associated calibration scan signals and/or symmetry measurements of the calibration scan signals. Once the machine-learning algorithm has been trained, the machine-learning algorithm may determine asymmetry offsets for the sample 118 being measured based on the scan signals generated in step 202 and the mapping generated during the training phase; the step 208 includes generating an overlay measurement for the sample layers of interest based on the asymmetry offsets between the overlay target features on the sample layers. As described previously herein, an overlay target may be fabricated with any selected asymmetry offsets of the overlay target elements. Accordingly, the step 208 may include adjusting the asymmetry offsets by a selected value to generate the overlay measurement; machine learning model is trained on image overlay patterns and overlay target is fabricated based on machine learning model selected manufacturing overlay patterns)
Claims 15-19 recite method with steps corresponding to the system elements recited in Claims 1-5 respectively. Therefore, the recited steps of the method Claims 15-19 are mapped to the proposed combination in the same manner as the corresponding elements of Claims 1-5 respectively. Additionally, the rationale and motivation to combine the Hotta and Gutman references presented in rejection of Claim 1, apply to these claims.
Claim 20 recite computer readable medium with instructions corresponding to the system elements recited in Claim 1. Therefore, the recited instruction of the computer readable medium claim 20 are mapped to the proposed combination in the same manner as the corresponding elements of Claim 1. Additionally, the rationale and motivation to combine the Hotta and Gutman references presented in rejection of Claim 1, apply to these claims.
Furthermore, the combination of Hotta and Gutman further discloses A non-transitory computer readable medium comprising instructions that, when executed by one or more processing circuitries, cause the one or more processing circuitries to perform (Hotta, [0061-0063] It is noted that various components illustrated in FIG. 6 need not be embodied as separate components. Rather, one or more of the image acquisition module 606, image processing module 630, memory 628, output module 632, and display device 634 may be embodied as a single computer or processor 636, or as separate modules operatively connected together, such as independent computers or processors connected together using data transmission or interfacing means. The modules 606, 630, and 632 may also be combined with one or more other modules, for example, as part of quality control processors or controllers in a semiconductor manufacturing line. Likewise, the memory 628 may be separated into multiple memory devices or shared amongst multiple components; one or more of the modules 606, 630, and 632 may be integrated with the SEM 602. Although separate components are illustrated in FIG. 6 with associated functions discussed above, components may be added, omitted, or combined and/or functions may be added, omitted, or transferred amongst components without departing from the spirit and scope of the disclosed embodiments; a sequence of programmed instructions that, when executed by the modules 606, 630, 632, and 634, and/or processor 636, cause the modules to perform the operations herein described, can be stored using the memory 628. Accordingly, memory 638 can be a computer or processor readable storage medium).
Allowable Subject Matter
Claims 11-12 and 14 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
JP 2023089034 A (Abstract, a tool for training a model, and using the trained model to determine patterns that will be printed on a substrate in a patterning process. The invention provides a method for training a model, the model being configured to predict a pattern that will be formed by a patterning process. The method involves: obtaining an image data associated with a desired pattern, a measured pattern of a substrate, a first model including a first set of parameters, and a machine learning model including a second set of parameters; and iteratively determining values of the first and second sets of parameters to train the model. The iteration involves: executing, using the image data, the first model and the machine learning model to cooperatively predict a printed pattern; and modifying the values of the first and second sets of parameters such that a difference between the measured pattern and the predicted pattern is reduced)
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PINALBEN V PATEL whose telephone number is (571)270-5872. The examiner can normally be reached M-F: 10am - 8pm.
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, Chineyere Wills-Burns can be reached at 571-272-9752. 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.
/Pinalben Patel/Examiner, Art Unit 2673