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 .
This action is responsive to communication filed on 07/23/2024.
Claims 1-14 and 16-21 are pending. Claim 15 have been cancelled. Claims 16-21 are new. Claims 1-14 have been amended. Entry of this amendment is accepted and made or record.
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.
Claims 1-14 and 16-21 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. A subject matter eligibility analysis is set forth below. See MPEP 2106.
Under Step 1 of the analysis, claims 1, belongs to a statutory category, namely a method. Similarly claims 16 belongs to a statutory category, namely a non-transitory computer-readable medium.
Under Step 2A, prong 1: This part of the eligibility analysis evaluates whether the claim recites a judicial exception. As explained in MPEP 2106.04, subsection II, a claim “recites” a judicial exception when the judicial exception is “set forth” or “described” in the claim.
The claim(s) 1 an d16 recite(s) concepts related to mathematical algorithms/concepts, and mental processes and concepts performed in the human mind e.g. observation, evaluation, judgment, opinion for “obtaining a trained computer model, having been trained on metrology data and the layout data to infer a value and/or probability metric relating to a parameter of interest from at least the layout data, the metrology data relating to a plurality of measurements of the parameter of interest at a respective plurality of measurement locations on the substrate; and determining, by a hardware computer system, a value and/or probability metric relating to the parameter of interest at one or more locations on the substrate different from the measurement locations from at least the layout data using the trained model” and which is mere characterization of the data necessary to implement the judicial exception.
The concepts discussed above in bold can be considered to describe mental processes, namely concepts performed in the human mind or with pen and paper, and/or mathematical concepts, namely a series of calculations leading to one or more numerical results or answers (emphasis added). Although the claim does not spell out any particular equation or formula being used, the lack of specific equations for individual steps merely points out that the claim would monopolize all possible calculations in performing the steps. These steps recited by the claims, therefore amount to a series of mental or mathematical steps, making these limitations amount to an abstract idea.
Step 2A, prong 2 of the eligibility analysis evaluates whether the claim as a whole integrates the recited judicial exception(s) into a practical application of the exception. This evaluation is performed by (a) identifying whether there are any additional elements recited in the claim beyond the judicial exception, and (b) evaluating those additional elements individually and in combination to determine whether the claim as a whole integrates the exception into a practical application.
This judicial exception is not integrated into a practical application because the abstract idea is not performed by using any particular device and because the “hardware computer system” recited in claims 1 and “computer system” recited in claim 16 which amounts to the recitation of a general purpose computer used to apply the abstract idea; and the “obtaining layout data relating to a layout of a pattern to be applied to at least one structure formed on a substrate in a manufacturing process, the pattern comprising the at least one structure” recited by claims 1 and 16, amounts to mere data gathering recited at a high level of generality and generally linking the abstract idea to a field of use (i.e. substrate manufacturing process) or technological environment in which the judicial exception is performed and the results are not used in any particular matter as to integrate the abstract idea in a practical application and the results of the algorithm are merely output/stored as part of insignificant post-solution activity, and the results of the mathematical algorithm are not used in any particular matter as to integrate the abstract idea in a practical application.
Under Step 2B, the claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements, as described above with respect to Step 2A Prong 2, merely amount to a general purpose computer (i.e. hardware computer system, computer system), used to apply the abstract idea and mere data gathering/output recited at a high level of generality and insignificant extra-solution activity that when further analyzed under Step 2B is found to be well-understood, routine and conventional activities as evidenced by MPEP 2106.05(d)(II), MPEP 2106.05(f)(2); and because the data of performing the algorithm must necessarily be “obtained” and the use of a general purpose computer to implement the abstract idea for performing the algorithm does not amount to significantly more than the recitation of the abstract idea itself.
The additional element of claims 1 and 16 recite “a substrate in a manufacturing process” which is field of use as discussed above and “obtaining layout data relating to a layout of a pattern to be applied to the at least one structure, the said pattern comprising the at least one structure” and which is well understood routine and conventional as evidenced by Chen US2021/0263428A1, Werkman et al. US2021/0405544 A1, Feng et al. US2022/0334554 A1, and Shinoda et al. US 2019/0228522 A1. Therefore, the bearing recited by claims 1 and 16 is not sufficient to amount to significantly more than the recited judicial exception.
Therefore, claims 1 and 16 are rejected under 35 U.S.C. 101 as directed to an abstract idea without significantly more.
Dependent claims 2-14 and 17-21 merely expand on the abstract idea by appending additional steps to the mathematical algorithm on their respective independent claim 1 and 16.
Dependent claims 2-14 and 17-21 merely expands on the abstract idea by reciting additional steps related to mathematical algorithms/concepts, and mental processes and concepts performed in the human mind e.g. observation, evaluation, judgment, opinion “wherein the parameter of interest is overlay or edge placement error” (claims 2 and 17), “wherein the trained model has been trained to interpolate the metrology data using the layout data to an expected value for the parameter of interest; and the determining a value and/or probability metric relating to the parameter of interest comprises determining the value for a parameter of interest at one or more locations on the substrate different from the measurement locations from the metrology data and the layout data using the trained model” (claims 3 and 18), “wherein the metrology data comprises after etch inspection metrology data measured subsequent to an etching and/or a polishing step” (claim 5), “wherein the metrology data comprises connectivity e-test data or scanning electron microscope measurement data” (claim 6), “wherein the layout data comprises a pattern density spatial distribution” (claim 7), “determining comprises determining a spatial distribution of the parameter of interest over at least an exposure field” (claim 8 and 19), “determining uses substrate position data to determine a spatial distribution of the parameter of interest over the substrate, the trained model having been trained per-field based on the substrate location data” (claim 9 and 20), “using the spatial distribution of the parameter of interest to optimize one or more settings in the manufacturing process and/or identify one or more areas or structures for further inspection” (claim 10 and 21), “obtaining training layout data comprising a similar type of data as the layout data; obtaining training metrology data corresponding to the training layout data, and training a machine learning model with the training metrology data and dense layout data to obtain the trained model” (claim 11), “wherein the training metrology data comprises at least after-etch inspection metrology data measured subsequent to an etching and/or polishing step” (claim 12), “wherein the training metrology data further comprises after-develop inspection metrology data, and the training comprises training the machine learning model to interpolate a sparse sampling of after-develop inspection metrology data to a denser sampling of after-etch inspection metrology data” (claim 13) and mere characterization of the data acquired and applied for performing the abstract idea (claims 2-14).
Dependent claims 2-14, do not set forth further additional elements that integrate the rejected abstract idea into a practical application or amount to significantly more than the abstract idea itself. Therefore, these claims are found to be ineligible for the reasons described with respect to independent claim 1 from which they depend.
The additional element of claims 2 and 17 recite “wherein the parameter of interest is overlay or edge placement error” and which is well understood routine and conventional as evidenced by Middlebrooks et la. US20220187713A1 (para. 0133), Werkman et al. US 20210405544 A1 (para. 0004), Chen US 20210263428 A1 (para. 0100).
The additional element of claims 4 recite “wherein the metrology data comprises after develop inspection metrology data measured by a scatterometer” and which is well understood routine and conventional as evidenced by Middlebrooks et la. US20220187713A1 (para. 0133), Werkman et al. US 20210405544 A1 (para. 0004), Chen US 20210263428 A1 (para. 0100).
The additional element of claims 14 recite “wherein the layout data and training layout data comprise pattern density images” and which is well understood routine and conventional as evidenced by Moest US11,237,490B2 (claim 4), Shinoda et al. US 20190228522 A1 (para. 0095), Shinoda et al. US 2019/0228522A1 (para. 0095).
Therefore, for similar reasons as discussed above, the additional elements disclosed by dependent claims 2-14 and 17-21 fail to integrate the recited abstract idea into a practical application or amount to significantly more than the abstract idea itself.
Therefore claims 1-14 and 16-21 are rejected under 35 USC 101 as being directed to non-statutory subject matter.
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 (i.e., changing from AIA to pre-AIA ) 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(s) 1-2, 4-6, 8-10, and 16-17, 19-21 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chen US2021/0263428A1 in view of Werkman et al. US2021/0405544 A1 (hereinafter Werkman).
Regarding claim 1, Chen disclose a method for determining a parameter of interest relating to at least one structure formed on a substrate in a manufacturing process (see abstract, para. 0003, 0005, 0092), the method comprising:
obtaining layout data relating to a layout of a pattern to be applied to the at least one structure, the pattern comprising the at least one structure (see abstract, para. 0003-0005, where metrology data corresponding to the portion of the substrate is discussed; para. 0062, 0071, 0112, where patterns and variables of the design layout of the substrate are disclosed);
obtaining a trained computer model (see para. 0015, 00127, “machine leaning model”), having been trained on metrology data and the layout data to infer a value (see para. 0015, 00127, “machine leaning model” used to accurately characterize a parameter of the process models (i.e. “machine learning model”) of the patterning process and to accurately calibrate process models of the patterning process) and/or probability metric relating to the parameter of interest from at least the layout data (para. 0113, 0127, 0145-0146, wherein any statistical technique may be employed for model calibration), the metrology data relating to a plurality of measurements of the parameter of interest at a respective plurality of measurement locations on the substrate (see para. 0027, 0102); and
determining, by a hardware computer system (para. 0179, 0186), a value and/or probability metric relating to the parameter of interest at one or more locations on the substrate from at least the layout data using the trained model (see para. 0040, 0102, 0112, where layout design is disclosed, para. 0113, 0127, where machine learning is disclosed for determining parameters)
However Chen do not expressly or specifically disclose that the locations for which the parameter of interest are calculated are different from the measurement locations from the at least the layout data.
Werkman disclose that additional data can also be generated spatially based on sparser measurements. For example, where metrology data for only a few points on a substrate is available, additional metrology data can be calculated for other locations on the substrate (see para. 0075).
Therefore given the teachings of Werkman it would have been obvious to one of ordinary skilled in the art before the effective filing date of the claimed invention to configure the system of Chen for determining, by a hardware computer system, a value and/or probability metric relating to the parameter of interest at one or more locations on the substrate different from the measurement locations from at least the layout data using the trained model for the benefit of providing a means for determining metrology data for locations based on sparser measurements for areas in which actual measured data is not available (see in para. 0075).
Regarding claim 2, the combination of Chen and Werkman disclose the materials discussed with respect to claim 1. Chen further disclose wherein the parameter of interest is overlay or edge placement error (see para. 0009, 0012, 0124, 0150).
Regarding claim 4, the combination of Chen and Werkman disclose the materials discussed with respect to claim 1. Chen further disclose wherein the metrology data comprises after develop inspection metrology data measured by a scatterometer (see Chen para. 0093, where measurement can be performed after-development of a resist that can be performed after-etch; see para. 0100, 0108 where scatterometer is disclosed as an inspection apparatus; para. 0094, 0182).
Regarding claim 5, the combination of Chen and Werkman disclose the materials discussed with respect to claim 1. Chen and Werkman further disclose wherein the metrology data comprises after etch inspection metrology data measured subsequent to an etching and/or a polishing step (see Chen para. 0093, that measurement may be performed on a target of the product substrate itself and/or on a dedicated metrology target provided on the substrate and that the measurement can be performed after-development of a resist that can be performed after-etch; see Werkman para. 0022, 0033, 0074, where post etch annealing step is disclosed and where after etch measurements are performed).
Regarding claim 6, the combination of Chen and Werkman disclose the materials discussed with respect to claim 1. Chen further disclose wherein the metrology data comprises connectivity e-test data or scanning electron microscope measurement data (see Chen, para. 0013, 0050, 0094 “scanning electron microscope” ).
Regarding claim 8, the combination of Chen and Werkman disclose the materials discussed with respect to claim 1. Chen further disclose wherein the determining comprises determining a spatial distribution of the parameter of interest over at least an exposure field (see para. 0003, 0008, 0025, 0065, 0073, 0080-0081, 0084-0085, where the map is a distribution of values of a process variable across the substrate, and where the exposure field corresponds to the substrate being exposed).
Regarding claim 9, the combination of Chen and Werkman disclose the materials discussed with respect to claim 1. Chen further disclose wherein the determining uses substrate position data (para. 0095, where positional information is extracted; para. 0102, where position of a target of interest is acquired) to determine a spatial distribution of the parameter of interest over the substrate (see para. 0102, 0134, where focus map is generated based on different focus contributions of different processing variables associated with the projection system of the lithographic apparatus during the substrate’s exposure; para. 0135, 137 where in the focus map equations various functions can be obtained by simulation mathematical modeling and/or experimentation; Fig. 9A-9B), the trained model having been trained per-field based on the substrate location data (see para.0125-0127,0150 where OPC model which is a machine learning model is trained based on substrate metrology data at different locations of interest, therefore the trained model is trained per-field based on the substrate location data).
Regarding claim 10, the combination of Chen and Werkman disclose the materials discussed with respect to claim 8. Chen further disclose using the spatial distribution of the parameter of interest (see para. 0003, 0008, 0025, 0065, 0073, 0080-0081, 0084-0085, where the map is a distribution of values of a process variable across the substrate) to optimize one or more settings in the manufacturing process and/or identify one or more areas or structures for further inspection (para. 0263, where optimization is performed by adjusting a patterning apparatus (e.g. lithography apparatus), a patterning process, etc. such that results and processes have more desirable characteristics; see para. 0003-0004, where lithography apparatus is used in manufacture of integrated circuit and inspection is performed; para. 0006-0007, calibration of a process model of a patterning process is performed including identifying a portion of the substrate that has values within a tolerance band of one or more parameters of the patterning process, the identifying step includes obtaining a plurality of process variations and identifying the portion of the substrate that has values within tolerance band; para. 0008, where the process variation is a map of the substrate, which is a distribution of values of a process variable across the substrate monitored).
Regarding claim 16, Chen disclose a non-transitory computer-readable medium having instructions therein, the instructions, when executed by a computer system, configured to cause the computer system (see para. 0034, 0266) to at least:
obtaining layout data relating to a layout of a pattern to be applied to at least one structure formed on a substrate in a manufacturing process, the pattern comprising the at least one structure (see abstract, para. 0003-0005, where metrology data corresponding to the portion of the substrate is discussed; 0062, 0071, 0112, where patterns and variables of the design layout of the substrate are disclosed; 0092, “manufacturing process”);
obtaining a trained computer model (see para. 0015, 00127, “machine leaning model”), having been trained on metrology data and the layout data to infer a value (see para. 0015, 00127, “machine leaning model” used to accurately characterize a parameter of the process models (i.e. “machine learning model”) of the patterning process and to accurately calibrate process models of the patterning process) and/or probability metric relating to the parameter of interest from at least the layout data (para. 0113, 0127, 0145-0146, wherein any statistical technique may be employed for model calibration), the metrology data relating to a plurality of measurements of the parameter of interest at a respective plurality of measurement locations on the substrate (see para. 0027, 0102); and
determining, by a hardware computer system (para. 0179, 0186), a value and/or probability metric relating to the parameter of interest at one or more locations on the substrate from at least the layout data using the trained model (see para. 0040, 0102, 0112, where layout design is disclosed, para. 0113, 0127, where machine learning is disclosed for determining parameters).
However Chen do not expressly or specifically disclose that the locations for which the parameter of interest are calculated are different from the measurement locations from the at least the layout data.
Werkman disclose that additional data can also be generated spatially based on sparser measurements. For example, where metrology data for only a few points on a substrate is available, additional metrology data can be calculated for other locations on the substrate (see para. 0075), meeting the claimed locations for which the parameter of interest are calculated are different from the measurement locations from the at least the layout data.
Therefore given the teachings of Werkman it would have been obvious to one of ordinary skilled in the art before the effective filing date of the claimed invention to configure the system of Chen for determining, by a hardware computer system, a value and/or probability metric relating to the parameter of interest at one or more locations on the substrate different from the measurement locations from at least the layout data using the trained model for the benefit of providing a means for determining metrology data for locations based on sparser measurements for areas in which actual measured data is not available (see para. 0075).
Regarding claim 17, the combination of Chen and Werkman disclose the materials discussed with respect to claim 16. Chen further disclose wherein the parameter of interest is overlay or edge placement error (see para. 0009, 0012, 0124, 0150).
Regarding claim 19, the combination of Chen and Werkman disclose the materials discussed with respect to claim 16. Chen further disclose wherein the instructions configured to cause the computer system to determine a value and/or probability metric relating to the parameter of interest (see para. 0040, 0102, 0112, where layout design is disclosed, para. 0113, 0127, where machine learning is disclosed for determining parameters) are configured to cause the computer system to determine a spatial distribution of the parameter of interest over at least an exposure field (see para. 0003, 0008, 0025, 0065, 0073, 0080-0081, 0084-0085, where the map is a distribution of values of a process variable across the substrate, and where the exposure field corresponds to the substrate being exposed).
Regarding claim 20, the combination of Chen and Werkman disclose the materials discussed with respect to claim 16. Chen further disclose wherein the instructions configured to cause the computer system to determine a value and/or probability metric relating to the parameter of interest (see para. 0040, 0102, 0112, where layout design is disclosed, para. 0113, 0127, where machine learning is disclosed for determining parameters) are configured to cause the computer system to use substrate position data (para. 0095, where positional information is extracted; para. 0102, where position of a target of interest is acquired) to determine a spatial distribution of the parameter of interest over the substrate (see para. 0102, 0134, where focus map is generated based on different focus contributions of different processing variables associated with the projection system of the lithographic apparatus during the substrate’s exposure; para. 0135, 137 where in the focus map equations various functions can be obtained by simulation mathematical modeling and/or experimentation; Fig. 9A-9B), the trained model having been trained per-field based on the substrate location data (see para. 0125-0127,0150 where OPC model which is a machine learning model is trained based on substrate metrology data at different locations of interest, therefore the trained model is trained per-field based on the substrate location data).
Regarding claim 21, the combination of Chen and Werkman disclose the materials discussed with respect to claim 16. Chen further disclose wherein the instructions are further configured to cause the computer system to use the spatial distribution of the parameter of interest (see para. 0003, 0008, 0025, 0065, 0073, 0080-0081, 0084-0085, where the map is a distribution of values of a process variable across the substrate) to optimize one or more settings in the manufacturing process and/or identify one or more areas or structures for further inspection (para. 0263, where optimization is performed by adjusting a patterning apparatus (e.g. lithography apparatus), a patterning process, etc. such that results and processes have more desirable characteristics; see para. 0003-0004, where lithography apparatus is used in manufacture of integrated circuit and inspection is performed; para. 0006-0007, calibration of a process model of a patterning process is performed including identifying a portion of the substrate that has values within a tolerance band of one or more parameters of the patterning process, the identifying step includes obtaining a plurality of process variations and identifying the portion of the substrate that has values within tolerance band; para. 0008, where the process variation is a map of the substrate, which is a distribution of values of a process variable across the substrate monitored).
Claim(s) 3 and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chen US2021/0263428A1 in view of Werkman et al. US2021/0405544A1 in further view of Feng et al. US2022/0334554A1 (hereinafter Feng).
Regarding claim 3, the combination of Chen and Werkman disclose the materials discussed with respect to claim 1. Chen further disclose measured data and information from log files may be combined by interpolation to generate process variation map (para. 0132), and determining, by a hardware computer system (para. 0179, 0186), a value and/or probability metric relating to the parameter of interest at one or more locations on the substrate from at least the layout data using the trained model (see para. 0040, 0102, 0112, where layout design is disclosed, 0113, 0127, where machine learning is disclosed for determining parameters).
However Chen do not expressly or specifically disclose that the locations for which the parameter of interest are calculated are different from the measurement locations from the at least the layout data.
Werkman disclose that additional data can also be generated spatially based on sparser measurements. For example, where metrology data for only a few points on a substrate is available, additional metrology data can be calculated for other locations on the substrate (see para. 0075).
Therefore given the teachings of Werkman it would have been obvious to one of ordinary skilled in the art before the effective filing date of the claimed invention to configure the system of Chen for determining, by a hardware computer system, a value and/or probability metric relating to the parameter of interest at one or more locations on the substrate different from the measurement locations from at least the layout data using the trained model for the benefit of providing a means for determining metrology data for locations based on sparser measurements for areas in which actual measured data is not available (see para. 0075).
However, the combination of Chen and Werkman do not expressly or explicitly disclose:
wherein the trained model has been trained to interpolate the metrology data using the layout data to an expected value for the parameter of interest; and
the determining a value and/or probability metric relating to the parameter of interest comprises determining the value for a parameter of interest at one or more locations on the substrate different from the measurement locations from the metrology data and the layout data using the trained model.
Feng teach wherein the trained model has been trained to interpolate the metrology data using the layout data to an expected value for the parameter of interest (see para. 0198, where machine learning model is trained by interpolating metrology data using the data as a tag or ground truth for the expected metrology signals at defined location on a training wafer surface; see para. 0203, 0212, where supplemental metrology data for a given training wafer by sampling from locations that do not correspond to the sample positions of the large beam spot metrology is disclosed; para. 0207, where spatial model may be employed for this interpolation from the positional data obtained with the supplemental metrology tool to the information obtained using the large beam spot metrology tool, and spatial model is crated to fit the first set of data points obtained by the supplemental metrology tool and provide a function or algorithm for calculating an expected metrology value at all locations on the wafer surface, not just those locations where the metrology data samples were acquired); and
the determining a value and/or probability metric relating to the parameter of interest comprises determining the value for a parameter of interest at one or more locations on the substrate different from the measurement locations from the metrology data and the layout data using the trained model (see para. 0150, 0192, where training data and design layout at a position is disclosed; 0198, where the machine learning model make use of the metrology data in determining parameter of interest for defined locations; see para. 0203, 0212, where supplemental metrology data for a given training wafer by sampling from locations that do not correspond to the sample positions of the large beam spot metrology is disclosed; para. 0207, where spatial model may be employed for this interpolation from the positional data obtained with the supplemental metrology tool to the information obtained using the large beam spot metrology tool, and spatial model is crated to fit the first set of data points obtained by the supplemental metrology tool and provide a function or algorithm for calculating an expected metrology value at all locations on the wafer surface, not just those locations where the metrology data samples were acquired, therefore the locations are different).
Therefore, it would have been obvious to one of ordinary skilled in the art before the effective filing date of the claimed invention, given the teachings of Feng as discussed above to configure the system of Chen as modified by Werkman such that the trained model has been trained to interpolate the metrology data using the layout data to an expected value for the parameter of interest; and the determining a value and/or probability metric relating to the parameter of interest comprises determining the value for a parameter of interest at one or more locations on the substrate different from the measurement locations from the metrology data and the layout data using the trained model for the benefit of estimate lithography process parameters between measurement data points enabling more accurate, efficient and cost-effective wafer level control by reducing measurement load and cost and for the benefit of providing a means for determining metrology data for locations based on sparser measurements for areas in which actual measured data is not available.
Regarding claim 18, the combination of Chen and Werkman disclose the materials discussed with respect to claim 16. Chen further disclose measured data and information from log files may be combined by interpolation to generate process variation map (para. 0132), and determining, by a hardware computer system (para. 0179, 0186), a value and/or probability metric relating to the parameter of interest at one or more locations on the substrate from at least the layout data using the trained model (see para. 0040, 0102, 0112, where layout design is disclosed, para. 0113, 0127, where machine learning is disclosed for determining parameters).
However Chen do not expressly or specifically disclose that the locations for which the parameter of interest are calculated are different from the measurement locations from the at least the layout data.
Werkman disclose that additional data can also be generated spatially based on sparser measurements. For example, where metrology data for only a few points on a substrate is available, additional metrology data can be calculated for other locations on the substrate (see para. 0075).
Therefore given the teachings of Werkman it would have been obvious to one of ordinary skilled in the art before the effective filing date of the claimed invention to configure the system of Chen for determining, by a computer system, a value and/or probability metric relating to the parameter of interest at one or more locations on the substrate different from the measurement locations from at least the layout data using the trained model for the benefit of providing a means for determining metrology data for locations based on sparser measurements for areas in which actual measured data is not available (see para. 0075).
However, the combination of Chen and Werkman do not expressly or explicitly disclose:
wherein the trained model has been trained to interpolate the metrology data using the layout data to an expected value for the parameter of interest; and
the determining a value and/or probability metric relating to the parameter of interest comprises determining the value for a parameter of interest at one or more locations on the substrate different from the measurement locations from the metrology data and the layout data using the trained model.
Feng teach wherein the trained model has been trained to interpolate the metrology data using the layout data to an expected value for the parameter of interest (see para. 0198, where machine learning model is trained by interpolating metrology data using the data as a tag or ground truth for the expected metrology signals at defined location on a training wafer surface; see para. 0203, 0212, where supplemental metrology data for a given training wafer by sampling from locations that do not correspond to the sample positions of the large beam spot metrology is disclosed; para. 0207, where spatial model may be employed for this interpolation from the positional data obtained with the supplemental metrology tool to the information obtained using the large beam spot metrology tool, and spatial model is crated to fit the first set of data points obtained by the supplemental metrology tool and provide a function or algorithm for calculating an expected metrology value at all locations on the wafer surface, not just those locations where the metrology data samples were acquired); and
the determining a value and/or probability metric relating to the parameter of interest comprises determining the value for a parameter of interest at one or more locations on the substrate different from the measurement locations from the metrology data and the layout data using the trained model (see para. 0150, 0192, where training data and design layout at a position is disclosed; para. 0198, where the machine learning model make use of the metrology data in determining parameter of interest for defined locations; see para. 0203, 0212, where supplemental metrology data for a given training wafer by sampling from locations that do not correspond to the sample positions of the large beam spot metrology is disclosed; para. 0207, where spatial model may be employed for this interpolation from the positional data obtained with the supplemental metrology tool to the information obtained using the large beam spot metrology tool, and spatial model is crated to fit the first set of data points obtained by the supplemental metrology tool and provide a function or algorithm for calculating an expected metrology value at all locations on the wafer surface, not just those locations where the metrology data samples were acquired, therefore the locations are different).
Therefore, it would have been obvious to one of ordinary skilled in the art before the effective filing date of the claimed invention, given the teachings of Feng as discussed above to configure the system of Chen as modified by Werkman such that the trained model has been trained to interpolate the metrology data using the layout data to an expected value for the parameter of interest; and the determining a value and/or probability metric relating to the parameter of interest comprises determining the value for a parameter of interest at one or more locations on the substrate different from the measurement locations from the metrology data and the layout data using the trained model for the benefit of estimate lithography process parameters between measurement data points enabling more accurate, efficient and cost-effective wafer level control by reducing measurement load and cost and for the benefit of providing a means for determining metrology data for locations based on sparser measurements for areas in which actual measured data is not available.
Claim(s) 7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chen US2021/0263428A1 in view of Werkman et al. US20210405544A1 Moest et al US11,237,490B2 (hereinafter Moest).
Regarding claim 7, the combination of Chen and Werkman disclose the materials discussed with respect to claim 1. Chen further disclose spatial intensity distribution data being adjusted (see para. 0066, “spatial intensity distribution”).
However Chen do not expressly or explicitly disclose wherein the layout data comprises a pattern density spatial distribution.
Moest disclose a Lithographic apparatus and device manufacturing method in which a spatial distribution of dissipation of a pattern based on the density distribution of the pattern is determined (see claims 1, 9, 11, 15). Therefore the pattern density spatial distribution is disclosed by Moest.
Therefore, it would have been obvious to one of ordinary skilled in the art before the effective filing date of the claimed invention to configure the system of Chen as modified by Werkman so that wherein the layout data comprises a pattern density spatial distribution, for the benefit of providing an enhanced and accurate lithography modeling of optical and process effects in order to provide and uniform layout model to a more physically accurate layout aware simulation.
It would have been obvious to one of ordinary still in the art before the effective filing date of the claimed invention to include in the system of Chen as Modified by Werkman layout data comprises a pattern density spatial distribution as taught by Moest since the claimed invention is merely a combination of old elements, and in the combination each element merely would have performed the same function as it did separately. One of ordinary skill in the art would have recognized that the results of the combination were predictably improve data interpolation by ensuring sample points accurately capture underlining variations and reduce prediction error.
Claim(s) 11-14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chen US2021/0263428A1 in view of Werkman et al. US20210405544A1 (hereinafter Werkman) in further view of Shinoda et al. US 2019/0228522 A1 (hereinafter Shinoda).
Regarding claim 11, the combination of Chen and Werkman disclose the materials discussed with respect to claim 1. Chen further teach training a machine learning model with the training metrology data and dense layout data to obtain the trained model (see para. 0043, where dense focus map is disclosed ; para. 0117, 0119, where denser sampling per substrate for metrology is discussed; para. 0132, 00137, Fig. 9A-9D, where measured data and information from log files may be combined to generate process variation map which result in a hybrid dense focus map which is densely sampled and accurate; para. 0127, where process variation maps are obtained and combined map may be used to sample metrology data at a location of interest, where maps can be used on a process model (i.e. machine learning model), therefore the machine learning model is trained with training metrology data and dense layout data).
However, Chen do not expressly or explicitly disclose obtaining training layout data comprising a similar type of data as the layout data; obtaining training metrology data corresponding to the training layout data; and training a machine learning model with the training metrology data and dense layout data to obtain the trained model.
Shinoda disclose obtaining training layout data comprising a similar type of data as the layout data (see Figs 11-17, para. 0078-0089, where training layout data from (4) is obtained by Machine learning unit (5) comprising a type of data similar to layout data (2));
obtaining training metrology data corresponding to the training layout data (“training metrology data (1) corresponds to the training layout data from (4)); and
training a machine learning model with the training metrology data and dense layout data to obtain the trained model (where machine learning model is trained with the training metrology data (1) and layout data (from 4), thus obtaining the trained model).
Therefore, it would have been obvious to one of ordinary skilled in the art before the effective filing date of the claimed invention given the teachings of Shinoda to configure the machine learning model of the system of Chen as modified by Werkman to obtaining training layout data comprising a similar type of data as the layout data; obtaining training metrology data corresponding to the training layout data; and training a machine learning model with the training metrology data and dense layout data to obtain the trained model for the benefit of providing an enhanced detection system that would accurately crates a model for generating design data image from inspection target image improving inspection performance and determination accuracy in order to detect a systematic defect (see para. 0073, 0095).
Regarding claim 12, the combination of Chen as modified by Werkman and Shinoda and disclose the materials discussed with respect to claim 11. Chen as modified by Werkman further disclose wherein the metrology data comprises after etch inspection metrology data measured subsequent to an etching and/or a polishing step (see Chen para. 0093, that measurement may be performed on a target of the product substrate itself and/or on a dedicated metrology target provided on the substrate and that the measurement can be performed after-development of a resist that can be performed after-etch; see Werkman para. 0022, 0033, 0074, where post etch annealing step is disclosed and where after etch measurements are performed).
Regarding claim 13, the combination of Chen as modified by Werkman and Shinoda and disclose the materials discussed with respect to claim 12. Chen as modified by Werkman further disclose wherein the training metrology data further comprises after-develop inspection metrology data (see Chen para. 0093, that measurement may be performed on a target of the product substrate itself and/or on a dedicated metrology target provided on the substrate and that the measurement can be performed after-development of a resist that can be performed after-etch; see Werkman para. 0022, 0033, 0074, where post etch annealing step is disclosed and where after etch measurements are performed), and the training comprises training the machine learning model to interpolate a sparse sampling of after-develop inspection metrology data to a denser sampling of after-etch inspection metrology data (see para. 0093, where measurement may be performed after-development that can be performed after-etch; para. 0132, where interpolation is performed to generate a hybrid dense focus map which is both densely sampled and accurate).
Regarding claim 14, the combination of Chen as modified by Werkman and Shinoda and disclose the materials discussed with respect to claim 11. Chen further discloses The method as claimed in claim 11, wherein the layout data and training layout data comprise pattern density images (see para. 0112, where a design layout in patterning process is disclosed; para. 0132, 0137 where focus map is generated based on combination of measured data and information from log files related to a patterning apparatus, and where a hybrid focus map which is both densely sampled and accurate is obtained).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to YARITZA H PEREZ BERMUDEZ whose telephone number is (571)270-1520. The examiner can normally be reached Monday-Friday.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Shelby A Turner can be reached at (571) 272-6334. 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.
/YARITZA H PEREZ BERMUDEZ/Examiner, Art Unit 2857
/JORDAN L JACKSON/Primary Examiner, Art Unit 2857
Prosecution Insights