DETAILED ACTION
This communication is in response to the Application No. 18/127,018 filed on March 28, 2023
in which Claims 1 - 12 are presented for examination.
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 § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claim 1-12 are rejected under 35 U.S.C. 101 because these claimed inventions are
directed to an abstract idea without significantly more.
Regarding Claim 1:
Step 1: Claim 1 is a method type claim. Therefore, Claims 1-6 fall within one of the four statutory
categories (i.e., process, machine, manufacture, or composition of matter).
2A Prong 1: If a claim limitation, under its broadest reasonable interpretation, covers performance
of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. If a claim limitation, under its broadest reasonable
interpretation, covers performance of the limitation by mathematical calculation but for the recitation
of generic computer components, then it falls within the “Mathematical Concepts” grouping of abstract
ideas.
inputting a specification data of a product to be etched including a position-optical parameter […] (mental process – inputting a specification data of a product to be etched including a position-optical parameter may be performed manually by a user)
[…]to obtain a prediction result (mental process – obtaining a prediction result may be performed manually by a user)
and selecting one of the plurality of etching recipes, according to the prediction result, as a suggested etching recipe for the product to be etched (mental process – selecting one of the plurality of etching recipe may be performed mentally by a user observing/analyzing the prediction result and accordingly using judgement/evaluation to select one of the plurality of etching recipes as a suggested etching recipe for the product to be etched)
Step 2A Prong 2: This judicial exception is not integrated into a practical application.
collecting a plurality of etching recipes of a plurality of existed etching products and a plurality sets of position-optical measurement values corresponding to the plurality of etching recipes (Adding insignificant extra-solution activity to the judicial exception - see MPEP 2106.05(g))
performing a supervised learning training according to a plurality of optical measurement values in each of the plurality sets of position-optical measurement values to build a predicting model (Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f) – Examiner’s note: high level recitation of training a machine learning model according to a plurality of optical measurement values without significantly more)
[…] into the predicting model […] (Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f) – Examiner’s note: high level recitation of applying a machine learning model without significantly more)
Step 2B: The claim does not include additional elements considered individually and in combination that
are sufficient to amount to significantly more than the judicial exception.
collecting a plurality of etching recipes of a plurality of existed etching products and a plurality sets of position-optical measurement values corresponding to the plurality of etching recipes (MPEP 2106.05(d)(II) indicates that merely “Receiving or transmitting data over a network” is a well-understood, routine, conventional function when it is claimed in a merely generic manner (as it is in the present claim). Thereby, a conclusion that the claimed limitation is well-understood, routine, conventional activity is supported under Berkheimer)
performing a supervised learning training according to a plurality of optical measurement values in each of the plurality sets of position-optical measurement values to build a predicting model (Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f) – Examiner’s note: high level recitation of training a machine learning model according to a plurality of optical measurement values without significantly more)
[…] into the predicting model […] (Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f) – Examiner’s note: high level recitation of applying a machine learning model without significantly more)
For the reasons above, Claim 1 is rejected as being directed to an abstract idea without significantly more. This rejection applies equally to dependent claims 1 - 6. The additional limitations of the dependent claims are addressed below.
Regarding Claim 2:
Step 2A Prong 1: See the rejection of Claim 1 above, which Claim 2 depends on.
extracting a plurality of statistical parameters and/or a plurality of histogram equalization parameters of a plurality of optical measurement values in each of the plurality sets of position-optical measurement values to serve as a plurality of eigenvector eigenvalues (mental process – extracting statistical parameters or histogram equalization parameters may be performed mentally by a user observing/analyzing the plurality sets of position-optical measurement values and accordingly using judgement/evaluation to extract statistical parameters to serve as a plurality of eigenvector eigenvalues)
and allocating each of the handplurality of position-optical measurement values a category label corresponding to the plurality of eigenvector eigenvalues respectively, for carrying out the supervised learning training (mathematical concept – categorizing based on position-optical measurement values constitutes a mathematical classification operation)
Step 2A Prong 2 & Step 2B:
Accordingly, under Step 2A Prong 2 and Step 2B, there are no additional elements that integrate the abstract idea into practical application. The claim does not include additional elements considered
individually and in combination that are sufficient to amount to significantly more than the judicial
exception.
Regarding Claim 3:
Step 2A Prong 1: See the rejection of Claim 1 above, which Claim 3 depends on.
Step 2A Prong 2 & Step 2B:
wherein the supervised learning training for building the predicting model comprises a K-nearest neighbor algorithm (KNN) (Field of Use – limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception does not amount to significantly more than the exception itself, and cannot integrate a judicial exception into a practical application; in this case specifying that supervised learning training for building the predicting model comprises a K-nearest neighbor algorithm (KNN) does not integrate the exception into a practical application nor amount to significantly more – See MPEP 2106.05(h))
Accordingly, under Step 2A Prong 2 and Step 2B, this additional element does not integrate the
abstract idea into practical application because it does not impose any meaningful limits on practicing
the abstract idea, as discussed above in the rejection of claim 1. The claim does not include additional
elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
Regarding Claim 4:
Step 2A Prong 1: See the rejection of Claim 1 above, which Claim 4 depends on.
Step 2A Prong 2 & Step 2B:
wherein the plurality of position-optical measurement values comprise a plurality of position coordinates-light transmittance values of the plurality of existed etching products (Field of Use – limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception does not amount to significantly more than the exception itself, and cannot integrate a judicial exception into a practical application; in this case specifying that the plurality of position-optical measurement values comprise a plurality of position coordinates-light transmittance values of the plurality of existed etching products does not integrate the exception into a practical application nor amount to significantly more – See MPEP 2106.05(h))
Accordingly, under Step 2A Prong 2 and Step 2B, this additional element does not integrate the
abstract idea into practical application because it does not impose any meaningful limits on practicing
the abstract idea, as discussed above in the rejection of claim 1. The claim does not include additional
elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
Regarding Claim 5:
Step 2A Prong 1: See the rejection of Claim 1 above, which Claim 5 depends on.
Step 2A Prong 2 & Step 2B:
wherein the plurality of statistical parameters comprises a mean, a minimum, a maximum, a median, a standard deviation, a skewness coefficient, a kurtosis coefficient, a mode, a coefficient of variation, a 25th percentile, a 75th percentile and a k-s statistics of the plurality of position-optical measurement values (Field of Use – limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception does not amount to significantly more than the exception itself, and cannot integrate a judicial exception into a practical application; in this case specifying that the plurality of statistical parameters comprises a mean, a minimum, a maximum, a median, a standard deviation, a skewness coefficient, a kurtosis coefficient, a mode, a coefficient of variation, a 25th percentile, a 75th percentile and a k-s statistics of the plurality of position-optical measurement values does not integrate the exception into a practical application nor amount to significantly more – See MPEP 2106.05(h))
Accordingly, under Step 2A Prong 2 and Step 2B, this additional element does not integrate the
abstract idea into practical application because it does not impose any meaningful limits on practicing
the abstract idea, as discussed above in the rejection of claim 1. The claim does not include additional
elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
Regarding Claim 6:
Step 2A Prong 1: See the rejection of Claim 1 above, which Claim 6 depends on.
Step 2A Prong 2 & Step 2B:
wherein the plurality of histogram equalization parameters are plurality of probability values obtained by normalizing each of the plurality of position-optical measurement values (Field of Use – limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception does not amount to significantly more than the exception itself, and cannot integrate a judicial exception into a practical application; in this case specifying that the plurality of histogram equalization parameters are plurality of probability values obtained by normalizing each of the plurality of position-optical measurement values does not integrate the exception into a practical application nor amount to significantly more – See MPEP 2106.05(h))
Accordingly, under Step 2A Prong 2 and Step 2B, this additional element does not integrate the
abstract idea into practical application because it does not impose any meaningful limits on practicing
the abstract idea, as discussed above in the rejection of claim 1. The claim does not include additional
elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
Regarding Claim 7:
Step 1: Claim 7 is a system type claim. Therefore, Claims 7-12 fall within one of the four statutory
categories (i.e., process, machine, manufacture, or composition of matter).
2A Prong 1: If a claim limitation, under its broadest reasonable interpretation, covers performance
of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. If a claim limitation, under its broadest reasonable
interpretation, covers performance of the limitation by mathematical calculation but for the recitation
of generic computer components, then it falls within the “Mathematical Concepts” grouping of abstract
ideas.
wherein the predicting model is used to obtain a prediction result by inputting a specification data of a product to be etched including a position-optical parameter […], and to select one of the plurality of the etching recipes as a suggested etching recipe for the product to be etched according to the prediction result (mental process - obtaining a prediction result by inputting a specification data of a product to be etched including a position-optical parameter may be performed manually by a user, and selecting one of the plurality of etching recipe may be performed mentally by a user observing/analyzing the prediction result and accordingly using judgement/evaluation to select one of the plurality of etching recipes as a suggested etching recipe for the product to be etched)
Step 2A Prong 2: This judicial exception is not integrated into a practical application.
a database (recited at a high-level of generality (i.e., as a database, generic processor, and memory) such that it amounts to no more than mere instructions to apply the exception using generic computer components)
used to store a historical data comprising a plurality of etching recipes for a plurality of existing etched products and a plurality of sets of position-optical measurement values corresponding to the plurality of the etching recipes (Adding insignificant extra-solution activity to the judicial exception - see MPEP 2106.05(g))
and a processor (recited at a high-level of generality (i.e., generic processor, and memory) such that it amounts to no more than mere instructions to apply the exception using generic computer components)
comprising a predicting model built by a supervised learning training using a plurality of optical measurement values in each of the plurality of sets of position-optical measurement values(Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f) – Examiner’s note: high level recitation of training a machine learning model according to a plurality of optical measurement values without significantly more)
[…] into the predicting model […] (Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f) – Examiner’s note: high level recitation of applying a machine learning model without significantly more)
Step 2B: The claim does not include additional elements considered individually and in combination that
are sufficient to amount to significantly more than the judicial exception.
a database (recited at a high-level of generality (i.e., as a database, generic processor, and memory) such that it amounts to no more than mere instructions to apply the exception using generic computer components)
used to store a historical data comprising a plurality of etching recipes for a plurality of existing etched products and a plurality of sets of position-optical measurement values corresponding to the plurality of the etching recipes (MPEP 2106.05(d)(II) indicates that merely “Receiving or transmitting data over a network” is a well-understood, routine, conventional function when it is claimed in a merely generic manner (as it is in the present claim). Thereby, a conclusion that the claimed limitation is well-understood, routine, conventional activity is supported under Berkheimer)
and a processor (recited at a high-level of generality (i.e., generic processor, and memory) such that it amounts to no more than mere instructions to apply the exception using generic computer components)
comprising a predicting model built by a supervised learning training using a plurality of optical measurement values in each of the plurality of sets of position-optical measurement values (Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f) – Examiner’s note: high level recitation of training a machine learning model according to a plurality of optical measurement values without significantly more)
[…] into the predicting model […] (Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f) – Examiner’s note: high level recitation of applying a machine learning model without significantly more)
For the reasons above, claim 7 is rejected as being directed to an abstract idea without significantly more. This rejection applies equally to dependent claims 7 - 12. The additional limitations of the dependent claims are addressed below.
Regarding Claim 8:
Step 2A Prong 1: See the rejection of Claim 7 above, which Claim 8 depends on.
extracting a plurality of statistical parameters and/or a plurality of histogram equalization parameters of a plurality of optical measurement values in each of the plurality sets of position-optical measurement values to serve as a plurality of eigenvector eigenvalues (mental process – extracting statistical parameters or histogram equalization parameters may be performed mentally by a user observing/analyzing the plurality sets of position-optical measurement values and accordingly using judgement/evaluation to extract statistical parameters to serve as a plurality of eigenvector eigenvalues)
and allocating each of the plurality of position-optical measurement values a category label corresponding to the plurality of eigenvector eigenvalues respectively, for carrying out the supervised learning training (mathematical concept – categorizing based on position-optical measurement values constitutes a mathematical classification operation)
Step 2A Prong 2 & Step 2B:
Accordingly, under Step 2A Prong 2 and Step 2B, there are no additional elements that integrate the abstract idea into practical application. The claim does not include additional elements considered
individually and in combination that are sufficient to amount to significantly more than the judicial
exception.
Regarding Claim 9:
Step 2A Prong 1: See the rejection of Claim 7 above, which Claim 9 depends on.
Step 2A Prong 2 & Step 2B:
wherein the supervised learning training for building the predicting model comprises a K-nearest neighbor algorithm (KNN) (Field of Use – limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception does not amount to significantly more than the exception itself, and cannot integrate a judicial exception into a practical application; in this case specifying that supervised learning training for building the predicting model comprises a K-nearest neighbor algorithm (KNN) does not integrate the exception into a practical application nor amount to significantly more – See MPEP 2106.05(h))
Accordingly, under Step 2A Prong 2 and Step 2B, this additional element does not integrate the
abstract idea into practical application because it does not impose any meaningful limits on practicing
the abstract idea, as discussed above in the rejection of claim 7. The claim does not include additional
elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
Regarding Claim 10:
Step 2A Prong 1: See the rejection of Claim 7 above, which Claim 10 depends on.
Step 2A Prong 2 & Step 2B:
wherein the plurality of position-optical measurement values comprise a plurality of position coordinates-light transmittance values of the plurality of existed etching products (Field of Use – limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception does not amount to significantly more than the exception itself, and cannot integrate a judicial exception into a practical application; in this case specifying that the plurality of position-optical measurement values comprise a plurality of position coordinates-light transmittance values of the plurality of existed etching products does not integrate the exception into a practical application nor amount to significantly more – See MPEP 2106.05(h))
Accordingly, under Step 2A Prong 2 and Step 2B, this additional element does not integrate the
abstract idea into practical application because it does not impose any meaningful limits on practicing
the abstract idea, as discussed above in the rejection of claim 7. The claim does not include additional
elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
Regarding Claim 11:
Step 2A Prong 1: See the rejection of Claim 7 above, which Claim 11 depends on.
Step 2A Prong 2 & Step 2B:
wherein the plurality of statistical parameters comprises a mean, a minimum, a maximum, a median, a standard deviation, a skewness coefficient, a kurtosis coefficient, a mode, a coefficient of variation, a 25th percentile, a 75th percentile and a k-s statistics of the plurality of position-optical measurement values (Field of Use – limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception does not amount to significantly more than the exception itself, and cannot integrate a judicial exception into a practical application; in this case specifying that the plurality of statistical parameters comprises a mean, a minimum, a maximum, a median, a standard deviation, a skewness coefficient, a kurtosis coefficient, a mode, a coefficient of variation, a 25th percentile, a 75th percentile and a k-s statistics of the plurality of position-optical measurement values does not integrate the exception into a practical application nor amount to significantly more – See MPEP 2106.05(h))
Accordingly, under Step 2A Prong 2 and Step 2B, this additional element does not integrate the
abstract idea into practical application because it does not impose any meaningful limits on practicing
the abstract idea, as discussed above in the rejection of claim 7. The claim does not include additional
elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
Regarding Claim 12:
Step 2A Prong 1: See the rejection of Claim 7 above, which Claim 12 depends on.
Step 2A Prong 2 & Step 2B:
wherein the plurality of histogram equalization parameters are plurality of probability values obtained by normalizing each of the plurality of position-optical measurement values (Field of Use – limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception does not amount to significantly more than the exception itself, and cannot integrate a judicial exception into a practical application; in this case specifying that the plurality of histogram equalization parameters are plurality of probability values obtained by normalizing each of the plurality of position-optical measurement values does not integrate the exception into a practical application nor amount to significantly more – See MPEP 2106.05(h))
Accordingly, under Step 2A Prong 2 and Step 2B, this additional element does not integrate the
abstract idea into practical application because it does not impose any meaningful limits on practicing
the abstract idea, as discussed above in the rejection of claim 7. The claim does not include additional
elements considered individually and in combination that are sufficient to amount to significantly more than the judicial exception.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1 - 12 are rejected under 35 U.S.C. 103 as being unpatentable over Pack et al.
(hereafter Pack) (US 20220198333), in view of Kooiman et al. (hereinafter Kooiman) (TW 202117576).
Regarding Claim 1, Pack teaches a method (Pack, Abstract, “A method”) for predicting etching recipe, comprising:
collecting a plurality of etching recipes of a plurality of existed etching products […] corresponding to the plurality of etching recipes (Pack, Par. [0019], “A processing device receives DOE and/or historical parameters (e.g., one or more sets of historical recipe parameters, one or more historical recipes that include historical parameters) associated with producing at least one substrate with substrate processing equipment. The parameters (e.g., historical recipe parameters) correspond to process operations (e.g., all of the process operations) of a recipe. In some embodiments, the parameters further include parameters or categories of processes of prior operations the substrate has undergone.”, & Par. [0019], “For example, processes can include one or more of deposition, etching, ion implantation, heating, cooling, transporting a substrate, purging airspace around the substrate, etc. The parameters of the process of transporting the substrate can include speed of transportation, timing of transportation, the ports used, etc. The parameters of the process of heating the substrate can include the temperature of zones, the rate of change of temperature, power, etc. The parameters of the process of etching the substrate can include the materials and/or gases provided to the processing chamber, the flow rate of the gases, temperature, pressure, etc.”, thus collecting a plurality of etching recipes of a plurality of existing etching products is disclosed, because Pack describes receiving multiple historical recipe parameters, including etching process parameters, that were used to produce substrates, which corresponds to collecting multiple etching recipes associated with existed etching products)
performing a supervised learning training […] to build a predicting model (Pack, Par. [0021], “The machine learning system or processing device further trains a machine learning model using data input including the historical parameters and target output including the historical performance data to generate a trained machine learning model.”, &Par. [0033], “In some embodiments, the predictive system 110 (e.g., predictive server 112, predictive component 114) generates predictive parameters 148 using supervised machine learning (e.g., supervised data set, historical parameters 144 labeled with historical performance data 154, etc.).” thus performing a supervised learning training to build a predicting model is disclosed, because Pack teaches training a machine learning model using historical parameters and corresponding historical performance data as labeled inputs and outputs, and further specifies that the predictive system generates predictive parameters using supervised machine learning)
inputting a specification data of a product to be etched […] into the predicting model to obtain a prediction result (Pack, Par. [0024], “To use the trained machine learning model, a processing device (e.g., machine learning processing device) receives a recipe to produce a substrate and identifies, based on the recipe, target performance data (e.g., target critical dimensions (CDs), target flatness, target thicknesses of layers, target properties, etc.) of the substrate. The processing device provides the target performance data (e.g., as output) to a trained machine learning model and obtains, from the trained machine learning model, predictive parameters (e.g., one or more inputs indicative of predictive parameters). The processing device optimizes the recipe based on the predictive parameters (e.g., updates parameters of one or more processes of the recipe based on the predictive parameters) and causes the substrate processing equipment to produce substrates based on the recipe that has been optimized”, thus inputting specification data of a product to be etched into the predicting model to obtain a prediction result is disclosed, because Pack teaches providing target performance data associated with a substrate to be produced to a trained machine learning model and obtaining predictive parameters from the model, which corresponds to inputting product specification data into the predicting model and receiving a prediction result)
and selecting one of the plurality of etching recipes, according to the prediction result, as a suggested etching recipe for the product to be etched (Pack, Par. [0024], “To use the trained machine learning model, a processing device (e.g., machine learning processing device) receives a recipe to produce a substrate and identifies, based on the recipe, target performance data (e.g., target critical dimensions (CDs), target flatness, target thicknesses of layers, target properties, etc.) of the substrate. The processing device provides the target performance data (e.g., as output) to a trained machine learning model and obtains, from the trained machine learning model, predictive parameters (e.g., one or more inputs indicative of predictive parameters). The processing device optimizes the recipe based on the predictive parameters (e.g., updates parameters of one or more processes of the recipe based on the predictive parameters) and causes the substrate processing equipment to produce substrates based on the recipe that has been optimized”, thus selecting one of the plurality of etching recipes, according to the prediction result, as a suggested etching recipe for the product to be etched is disclosed, because Pack teaches obtaining predictive parameters from a trained machine learning model and optimizing a recipe based on those predictive parameters, which corresponds to selecting and using an etching recipe in accordance with the prediction result)
Pack does not explicitly teach a plurality sets of position-optical measurement values related to etching, a plurality of optical measurement values in each of the plurality sets of position-optical measurement values, and a position-optical parameter.
However, Kooiman teaches a plurality sets of position-optical measurement values related to etching, a plurality of optical measurement values in each of the plurality sets of position-optical measurement values, and a position-optical parameter (Kooiman, Page - 3, “In addition, in one embodiment, a method for identifying the contribution of pixels of a developed image to a prediction generated by a trained model is provided. The method includes: using a metrology tool to obtain (i) the developed image (ADI) including a feature of interest, and obtain (ii) an interpretation configured to interpret a prediction related to the feature of interest Model, the prediction is generated by the trained model; and the interpretation model is applied to the ADI image to generate an interpretation map, the interpretation map includes quantifying each pixel of the ADI image for the feature of interest The pixel value of the predicted contribution, & Page 3-4, “In addition, a method for determining an etching characteristic associated with an etching process is provided. The method includes: obtaining through a metrology tool: (i) an imaged pattern at a given position on a substrate, an developed image (ADI), the imaged pattern including a feature of interest and adjacent to the feature of interest And (ii) an etched image (AEI) of one of the imaged patterns at the given position of the substrate, the AEI including one of the etched features corresponding to the feature of interest in the ADI; and The ADI and the AEI are used to determine a correlation between the etched feature associated with the feature of interest in the ADI and the adjacent features, and the correlation characterizes the etching characteristics associated with the etching process, & Page – 4, “In addition, in one embodiment, a metrology tool is provided, which includes: a beam generator configured to measure an ADI feature after imaging a substrate and an AEI feature after etching the substrate ; And a processor. The processor is configured to: obtain a correlation between the measured ADI feature and the measured AEI feature corresponding to the measured ADI feature printed on a substrate subjected to an etching process, the phase The relationship is based on a combination of variables that characterize how the measured ADI feature transforms to the AEI feature; and the settings of the metrology tool are adjusted based on the correlation to improve the correlation, and the settings are based on the correlation relative to each setting It is determined by a derivative indicating an improvement of the correlation for each setting of the metrology tool”, thus a plurality sets of position-optical measurement values related to etching, a plurality of optical measurement values in each of the plurality sets of position-optical measurement values, and a position-optical parameter are disclosed, because Kooiman teaches using a metrology tool to obtain developed and etched optical images at given positions on a substrate, quantifying pixel-level optical values within each image, and correlating measured ADI and AEI features to characterize etching characteristics, which corresponds to collecting multiple sets of position-specific optical measurement values associated with etched products)
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to combine Pack’s machine-learning-based approach for predicting and optimizing etching recipes using historical process parameters and performance data, which reads on collecting a plurality of etching recipes and training a predicting model, with Kooiman’s use of position-specific optical and image-based measurements obtained via metrology tools to characterize etching characteristics, which reads on collecting a plurality of sets of position-optical measurement values corresponding to etched products, because Kooiman provides optical measurement data at specific substrate positions that can serve as predictive inputs to Pack’s machine learning models, thereby enabling more accurate prediction and selection of etching recipes and reducing the need for time-consuming after etch measurement (Kooiman, Page – 5, “The corresponding difficulty that conflicts with high yield is the goal of maintaining a fast production schedule (for example, referred to as throughput or the number of wafers processed per hour). High process yield and high wafer throughput can be affected by the presence of defects (especially when operator intervention is required for defect review). Therefore, high-throughput detection and identification of small defects by inspection tools (such as optical or electron microscope (SEM)) are necessary to maintain high yield and low cost. Since the microscope used for defect detection can only view a part of the wafer at a time, defect detection can be very time-consuming and reduce overall throughput. For example, if every location on the wafer must be inspected to find defects, the wafer throughput can be significantly reduced, because inspecting every location on each IC on the wafer will take time. One method of this problem is to use a technique for predicting defect locations based on information obtained from a photolithography system, which is a system used in the manufacture of IC chips. In an example, defect detection may be performed after imaging or after processing (such as after etching). In one example, instead of inspecting every position on the wafer after etching to find defects, the possible defects can be predicted based on the post-development process. In one example, a better model can be configured to more accurately predict possible failures after etching based on the process output before the etching process. For example, the model includes a first part specifically related to nonfaulty holes and a second part specifically related to faulty holes. In one embodiment, the model is determined based on measurements of the same structure at least twice (for example, using a SEM metrology tool). The difference between the two SEM measurements can be used to build models or classify faults in features before the etching process. The advantage of this type of defect prediction is that etching conditions can be adjusted, or locations where the number of inspections can be significantly reduced, so that the corresponding reduction in inspection time and the increase in wafer throughput can be achieved. In another example, a correlation between, for example, post- development and post-etching can be established, so that the etching process can be controlled based on such correlation. Such advantages based on related process control will be effectively used to reduce defects after etching, thereby improving the yield of the patterning process.”)
Regarding Claim 2, Pack combined with Kooiman teaches all of the limitations of claim 1 as cited above and Kooiman further teaches:
extracting a plurality of statistical parameters and/or a plurality of histogram equalization parameters of a plurality of optical measurement values in each of the plurality sets of position-optical measurement values to serve as a plurality of eigenvector eigenvalues (Kooiman, Page – 43, “In one embodiment, the relevant determination 2310 involves and on and Optimization of mutual information (in one embodiment, maximize). In one embodiment, the optimization of mutual information can be determined based on analytical methods or numerical methods. In one embodiment, the eigenvalue equation can be used to maximize the correlation 2310 between the combination of variables of ADI and the combination of variables of AEI. In one embodiment, the mutual information can be determined based on the spatial probability density function of the variable combination. In one embodiment, for example, for a limited data set, the probability density may not be calculated, but a normalized histogram may be used. An example method for estimating mutual information can be found in "Estimating mutual information" (Phys. Rev. E 69, 2004) of A. Kraskov, H. Stogbauer and P. Grassberger, which incorporates all of its contents by reference here”, thus extracting a plurality of statistical parameters and/or a plurality of histogram equalization parameters to serve as a plurality of eigenvector eigenvalues is disclosed, because Kooiman derives statistical representations of optical measurement values using spatial probability density functions and normalized histograms, which read on extracting statistical and histogram equalization parameters from position-optical measurement values, and further applies an eigenvalue equation to combinations of those statistically derived variables to maximize correlation between ADI and AEI, which corresponds to using those extracted parameters as eigenvector-based quantities, thereby enabling measured optical data to be transformed into a reduced, correlation-optimized feature representation suitable for model training and analysis of etch behavior)
Pack teaches allocating each of the plurality of position-optical measurement values a category label corresponding to the plurality of eigenvector eigenvalues respectively, for carrying out the supervised learning training (Pack, Par. [0094], “As shown in FIG. 4E, different data points 472 are part of different clusters 476 . In some embodiments, a cluster 476 and subclusters of cluster 476 are associated with ordinal categorical performance data of the substrate produced based on corresponding parameters meeting threshold performance data (e.g., very bad, flat, fair, bad, etc.)”, thus allocating each of the plurality of position-optical measurement values a category label corresponding to the plurality of eigenvector eigenvalues for carrying out supervised learning training is disclosed, because Pack assigns measurement-derived data points to clusters in the feature space and associates each cluster and subcluster with an ordinal categorical performance label (e.g., “very bad,” “bad,” “fair,” etc.), such that each data point represented by its corresponding feature (eigenvector-based) values is labeled with a category for use in training the supervised machine learning model)
Regarding Claim 3, Pack combined with Kooiman teaches all of the limitations of claim 2 as cited above and Pack further teaches:
wherein the supervised learning training for building the predicting model comprises a K-nearest neighbor algorithm (KNN) (Pack, Par. [0052], “Non probabilistic methods may also be used including one or more of Support Vector Machine (SVM), Radial Basis Function (RBF), clustering, Nearest Neighbor algorithm (k-NN), linear regression, random forest, neural network (e.g., artificial neural network), etc”, thus the supervised learning training for building the predicting model comprising a K-nearest neighbor algorithm is disclosed, because Pack lists the Nearest Neighbor algorithm (k-NN) as a non-probabilistic machine learning method that may be used to train the predictive model)
Regarding Claim 4, Pack combined with Kooiman teaches all of the limitations of claim 2 as cited above and Kooiman further teaches:
wherein the plurality of position-optical measurement values comprise a plurality of position coordinates-light transmittance values of the plurality of existed etching products (Kooiman, Page – 15, “Procedure P1001 involves: obtaining via a metrology tool: (i) a developed image 1001 (ADI) of an imaged pattern at a given position on a substrate, the imaged pattern including a feature of interest and adjacent to the image of interest A feature adjacent to a feature; and (ii) an etched image 1002 (AEI) of one of the imaged patterns at the given position of the substrate, the AEI including one of the etched features corresponding to the feature of interest in the ADI . For example, the imaged pattern may be an array of contact holes at the center of the substrate. Within the array of contact holes, the feature of interest may be contact holes at specific coordinates (eg, GDS coordinates)”, & Page – 44, “Referring to FIG. 25A, the weight WT_ADICH1 (right image) of each contour point on the ADI feature ADICH1 is plotted against the angle. In addition, the weight WT_NH1 (right image) of each contour point on the adjacent ADI feature (for example, NCH) is plotted against the angle. The figure on the left illustrates an example layout of the ADI contact hole in the polar coordinate representation. In the arrangement of the contact holes (left picture), the dashed outline rch1 corresponds to the required feature or reference feature with a zero-weight outline point”, thus the plurality of position-optical measurement values comprising a plurality of position coordinates–light transmittance values is disclosed, because Kooiman obtains developed and etched images at given positions on a substrate, including features of interest located at specific coordinates (e.g., GDS coordinates), and further quantifies optical measurement values extracted from those images as numerical weights associated with each contour point represented in a polar coordinate system, such that each optical measurement value is tied to a specific spatial position of an etched product, which corresponds to collecting position-dependent optical (light transmittance) measurement values for a plurality of existing etched products)
Regarding Claim 5, Pack combined with Kooiman teaches all of the limitations of claim 2 as cited above and Kooiman further teaches:
wherein the plurality of statistical parameters comprises a mean, a minimum, a maximum, a median, a standard deviation, a skewness coefficient, a kurtosis coefficient, a mode, a coefficient of variation, a 25th percentile, a 75th percentile and a k-s statistics of the plurality of position-optical measurement values (Kooiman, Page – 30, “In this embodiment, because the model 1710 is a combined distribution of the first distribution and the second distribution, the model 1710 captures the relationship between the LCDU and the dose more accurately. Therefore, for example, the statistical parameters or characteristics of the fitting distribution 1710 can be used to more accurately determine the process window of the patterning process. In one embodiment, the method 1700 may further include procedures P1711 and P1713 configured to determine the process window PW. In one embodiment, P1711 includes extracting statistical features of the fitted probability distribution 1710 (for example, PDF1 in FIG. 17) related to the non-fault feature. For example, the statistical feature may be the average value, standard deviation, skewness, or other statistics related to the contact holes printed on the substrate”, thus the plurality of statistical parameters comprising a mean, a minimum, a maximum, a median, a standard deviation, a skewness coefficient, a kurtosis coefficient, a mode, a coefficient of variation, a 25th percentile, a 75th percentile, and a k-s statistic of the plurality of position-optical measurement values is disclosed, because Kooiman teaches extracting statistical features from a fitted probability distribution derived from position dependent optical measurements of etched features, including mean, standard deviation, and skewness, and further teaches use of other distribution-based statistical characteristics, which under the broadest reasonable interpretation includes the remaining claimed statistical parameters derived from such probability distributions}
Regarding Claim 6, Pack combined with Kooiman teaches all of the limitations of claim 2 as cited above and Kooiman further teaches:
wherein the plurality of histogram equalization parameters are plurality of probability values obtained by normalizing each of the plurality of position-optical measurement values (Kooiman, Page – 43, “In one embodiment, the relevant determination 2310 involves and on and Optimization of mutual information (in one embodiment, maximize). In one embodiment, the optimization of mutual information can be determined based on analytical methods or numerical methods. In one embodiment, the eigenvalue equation can be used to maximize the correlation 2310 between the combination of variables of ADI and the combination of variables of AEI. In one embodiment, the mutual information can be determined based on the spatial probability density function of the variable combination. In one embodiment, for example, for a limited data set, the probability density may not be calculated, but a normalized histogram may be used. An example method for estimating mutual information can be found in "Estimating mutual information" (Phys. Rev. E 69, 2004) of A. Kraskov, H. Stogbauer and P. Grassberger, which incorporates all of its contents by reference here”, thus thus, the plurality of histogram equalization parameters being plurality of probability values obtained by normalizing each of the plurality of position-optical measurement values is disclosed, because Kooiman teaches determining mutual information based on probability density functions of ADI and AEI variable combinations and teaches using a normalized histogram when probability densities are not directly calculated, where the normalized histogram represents probability values derived from normalizing measured ADI and AEI variables, which correspond to normalized position-optical measurement values)
Regarding Claim 7, A system (Pack, Par. [0007], “a system”, thus a system is disclosed) for predicting etching recipe, comprising:
a database (Pack, Par. [0007], “a memory”, thus a database is disclosed) used to store a historical data comprising a plurality of etching recipes for a plurality of existing etched products […] corresponding to the plurality of the etching recipes (Pack, Par. [0019], “A processing device receives DOE and/or historical parameters (e.g., one or more sets of historical recipe parameters, one or more historical recipes that include historical parameters) associated with producing at least one substrate with substrate processing equipment. The parameters (e.g., historical recipe parameters) correspond to process operations (e.g., all of the process operations) of a recipe. In some embodiments, the parameters further include parameters or categories of processes of prior operations the substrate has undergone.”, & Par. [0019], “For example, processes can include one or more of deposition, etching, ion implantation, heating, cooling, transporting a substrate, purging airspace around the substrate, etc. The parameters of the process of transporting the substrate can include speed of transportation, timing of transportation, the ports used, etc. The parameters of the process of heating the substrate can include the temperature of zones, the rate of change of temperature, power, etc. The parameters of the process of etching the substrate can include the materials and/or gases provided to the processing chamber, the flow rate of the gases, temperature, pressure, etc.”, thus a historical data comprising a plurality of etching recipes for a plurality of existing etched products is disclosed, because Pack describes receiving multiple historical recipe parameters, including etching process parameters, that were used to produce substrates, which corresponds to multiple etching recipes associated with existed etching products)
and a processor (Pack, Par. [0007], “a processing device”, thus a processor is disclosed), comprising a predicting model built by a supervised learning training […] (Pack, Par. [0021], “The machine learning system or processing device further trains a machine learning model using data input including the historical parameters and target output including the historical performance data to generate a trained machine learning model.”, &Par. [0033], “In some embodiments, the predictive system 110 (e.g., predictive server 112, predictive component 114) generates predictive parameters 148 using supervised machine learning (e.g., supervised data set, historical parameters 144 labeled with historical performance data 154, etc.).” thus a predicting model built by a supervised learning training is disclosed, because Pack teaches training a machine learning model using historical parameters and corresponding historical performance data as labeled inputs and outputs, and further specifies that the predictive system generates predictive parameters using supervised machine learning)
wherein the predicting model is used to obtain a prediction result by inputting a specification data of a product to be etched […] into the predicting model (Pack, Par. [0024], “To use the trained machine learning model, a processing device (e.g., machine learning processing device) receives a recipe to produce a substrate and identifies, based on the recipe, target performance data (e.g., target critical dimensions (CDs), target flatness, target thicknesses of layers, target properties, etc.) of the substrate. The processing device provides the target performance data (e.g., as output) to a trained machine learning model and obtains, from the trained machine learning model, predictive parameters (e.g., one or more inputs indicative of predictive parameters). The processing device optimizes the recipe based on the predictive parameters (e.g., updates parameters of one or more processes of the recipe based on the predictive parameters) and causes the substrate processing equipment to produce substrates based on the recipe that has been optimized”, thus inputting specification data of a product to be etched into the predicting model to obtain a prediction result is disclosed, because Pack teaches providing target performance data associated with a substrate to be produced to a trained machine learning model and obtaining predictive parameters from the model, which corresponds to inputting product specification data into the predicting model and receiving a prediction result), and to select one of the plurality of the etching recipes as a suggested etching recipe for the product to be etched according to the prediction result (Pack, Par. [0024], “To use the trained machine learning model, a processing device (e.g., machine learning processing device) receives a recipe to produce a substrate and identifies, based on the recipe, target performance data (e.g., target critical dimensions (CDs), target flatness, target thicknesses of layers, target properties, etc.) of the substrate. The processing device provides the target performance data (e.g., as output) to a trained machine learning model and obtains, from the trained machine learning model, predictive parameters (e.g., one or more inputs indicative of predictive parameters). The processing device optimizes the recipe based on the predictive parameters (e.g., updates parameters of one or more processes of the recipe based on the predictive parameters) and causes the substrate processing equipment to produce substrates based on the recipe that has been optimized”, thus selecting one of the plurality of etching recipes, according to the prediction result, as a suggested etching recipe for the product to be etched is disclosed, because Pack teaches obtaining predictive parameters from a trained machine learning model and optimizing a recipe based on those predictive parameters, which corresponds to selecting and using an etching recipe in accordance with the prediction result)
Pack does not explicitly teach a plurality sets of position-optical measurement values related to etching, a plurality of optical measurement values in each of the plurality sets of position-optical measurement values, and a position-optical parameter.
However, Kooiman teaches a plurality sets of position-optical measurement values related to etching, a plurality of optical measurement values in each of the plurality sets of position-optical measurement values, and a position-optical parameter (Kooiman, Page - 3, “In addition, in one embodiment, a method for identifying the contribution of pixels of a developed image to a prediction generated by a trained model is provided. The method includes: using a metrology tool to obtain (i) the developed image (ADI) including a feature of interest, and obtain (ii) an interpretation configured to interpret a prediction related to the feature of interest Model, the prediction is generated by the trained model; and the interpretation model is applied to the ADI image to generate an interpretation map, the interpretation map includes quantifying each pixel of the ADI image for the feature of interest The pixel value of the predicted contribution, & Page 3-4, “In addition, a method for determining an etching characteristic associated with an etching process is provided. The method includes: obtaining through a metrology tool: (i) an imaged pattern at a given position on a substrate, an developed image (ADI), the imaged pattern including a feature of interest and adjacent to the feature of interest And (ii) an etched image (AEI) of one of the imaged patterns at the given position of the substrate, the AEI including one of the etched features corresponding to the feature of interest in the ADI; and The ADI and the AEI are used to determine a correlation between the etched feature associated with the feature of interest in the ADI and the adjacent features, and the correlation characterizes the etching characteristics associated with the etching process, & Page – 4, “In addition, in one embodiment, a metrology tool is provided, which includes: a beam generator configured to measure an ADI feature after imaging a substrate and an AEI feature after etching the substrate ; And a processor. The processor is configured to: obtain a correlation between the measured ADI feature and the measured AEI feature corresponding to the measured ADI feature printed on a substrate subjected to an etching process, the phase The relationship is based on a combination of variables that characterize how the measured ADI feature transforms to the AEI feature; and the settings of the metrology tool are adjusted based on the correlation to improve the correlation, and the settings are based on the correlation relative to each setting It is determined by a derivative indicating an improvement of the correlation for each setting of the metrology tool”, thus a plurality sets of position-optical measurement values related to etching, a plurality of optical measurement values in each of the plurality sets of position-optical measurement values, and a position-optical parameter are disclosed, because Kooiman teaches using a metrology tool to obtain developed and etched optical images at given positions on a substrate, quantifying pixel-level optical values within each image, and correlating measured ADI and AEI features to characterize etching characteristics, which corresponds to collecting multiple sets of position-specific optical measurement values associated with etched products)
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to combine Pack’s machine-learning-based approach for predicting and optimizing etching recipes using historical process parameters and performance data, which reads on collecting a plurality of etching recipes and training a predicting model, with Kooiman’s use of position-specific optical and image-based measurements obtained via metrology tools to characterize etching characteristics, which reads on collecting a plurality of sets of position-optical measurement values corresponding to etched products, because Kooiman provides optical measurement data at specific substrate positions that can serve as predictive inputs to Pack’s machine learning models, thereby enabling more accurate prediction and selection of etching recipes and reducing the need for time-consuming after etch measurement (Kooiman, Page – 5, “The corresponding difficulty that conflicts with high yield is the goal of maintaining a fast production schedule (for example, referred to as throughput or the number of wafers processed per hour). High process yield and high wafer throughput can be affected by the presence of defects (especially when operator intervention is required for defect review). Therefore, high-throughput detection and identification of small defects by inspection tools (such as optical or electron microscope (SEM)) are necessary to maintain high yield and low cost. Since the microscope used for defect detection can only view a part of the wafer at a time, defect detection can be very time-consuming and reduce overall throughput. For example, if every location on the wafer must be inspected to find defects, the wafer throughput can be significantly reduced, because inspecting every location on each IC on the wafer will take time. One method of this problem is to use a technique for predicting defect locations based on information obtained from a photolithography system, which is a system used in the manufacture of IC chips. In an example, defect detection may be performed after imaging or after processing (such as after etching). In one example, instead of inspecting every position on the wafer after etching to find defects, the possible defects can be predicted based on the post-development process. In one example, a better model can be configured to more accurately predict possible failures after etching based on the process output before the etching process. For example, the model includes a first part specifically related to nonfaulty holes and a second part specifically related to faulty holes. In one embodiment, the model is determined based on measurements of the same structure at least twice (for example, using a SEM metrology tool). The difference between the two SEM measurements can be used to build models or classify faults in features before the etching process. The advantage of this type of defect prediction is that etching conditions can be adjusted, or locations where the number of inspections can be significantly reduced, so that the corresponding reduction in inspection time and the increase in wafer throughput can be achieved. In another example, a correlation between, for example, post- development and post-etching can be established, so that the etching process can be controlled based on such correlation. Such advantages based on related process control will be effectively used to reduce defects after etching, thereby improving the yield of the patterning process.”)
Regarding Claim 8, Pack combined with Kooiman teaches all of the limitations of claim 7 as cited above and Kooiman further teaches:
extracting a plurality of statistical parameters and/or a plurality of histogram equalization parameters of a plurality of optical measurement values in each of the plurality sets of position-optical measurement values to serve as a plurality of eigenvector eigenvalues (Kooiman, Page – 43, “In one embodiment, the relevant determination 2310 involves and on and Optimization of mutual information (in one embodiment, maximize). In one embodiment, the optimization of mutual information can be determined based on analytical methods or numerical methods. In one embodiment, the eigenvalue equation can be used to maximize the correlation 2310 between the combination of variables of ADI and the combination of variables of AEI. In one embodiment, the mutual information can be determined based on the spatial probability density function of the variable combination. In one embodiment, for example, for a limited data set, the probability density may not be calculated, but a normalized histogram may be used. An example method for estimating mutual information can be found in "Estimating mutual information" (Phys. Rev. E 69, 2004) of A. Kraskov, H. Stogbauer and P. Grassberger, which incorporates all of its contents by reference here”, thus extracting a plurality of statistical parameters and/or a plurality of histogram equalization parameters to serve as a plurality of eigenvector eigenvalues is disclosed, because Kooiman derives statistical representations of optical measurement values using spatial probability density functions and normalized histograms, which read on extracting statistical and histogram equalization parameters from position-optical measurement values, and further applies an eigenvalue equation to combinations of those statistically derived variables to maximize correlation between ADI and AEI, which corresponds to using those extracted parameters as eigenvector-based quantities, thereby enabling measured optical data to be transformed into a reduced, correlation-optimized feature representation suitable for model training and analysis of etch behavior)
Pack teaches allocating each of the plurality of position-optical measurement values a category label corresponding to the plurality of eigenvector eigenvalues respectively, for carrying out the supervised learning training (Pack, Par. [0094], “As shown in FIG. 4E, different data points 472 are part of different clusters 476 . In some embodiments, a cluster 476 and subclusters of cluster 476 are associated with ordinal categorical performance data of the substrate produced based on corresponding parameters meeting threshold performance data (e.g., very bad, flat, fair, bad, etc.)”, thus allocating each of the plurality of position-optical measurement values a category label corresponding to the plurality of eigenvector eigenvalues for carrying out supervised learning training is disclosed, because Pack assigns measurement-derived data points to clusters in the feature space and associates each cluster and subcluster with an ordinal categorical performance label (e.g., “very bad,” “bad,” “fair,” etc.), such that each data point represented by its corresponding feature (eigenvector-based) values is labeled with a category for use in training the supervised machine learning model)
Regarding Claim 9, Pack combined with Kooiman teaches all of the limitations of claim 8 as cited above and Pack further teaches:
wherein the supervised learning training for building the predicting model comprises a K-nearest neighbor algorithm (KNN) (Pack, Par. [0052], “Non probabilistic methods may also be used including one or more of Support Vector Machine (SVM), Radial Basis Function (RBF), clustering, Nearest Neighbor algorithm (k-NN), linear regression, random forest, neural network (e.g., artificial neural network), etc”, thus the supervised learning training for building the predicting model comprising a K-nearest neighbor algorithm is disclosed, because Pack lists the Nearest Neighbor algorithm (k-NN) as a non-probabilistic machine learning method that may be used to train the predictive model)
Regarding Claim 10, Pack combined with Kooiman teaches all of the limitations of claim 8 as cited above and Kooiman further teaches:
wherein the plurality of position-optical measurement values comprise a plurality of position coordinates-light transmittance values of the plurality of existed etching products (Kooiman, Page – 15, “Procedure P1001 involves: obtaining via a metrology tool: (i) a developed image 1001 (ADI) of an imaged pattern at a given position on a substrate, the imaged pattern including a feature of interest and adjacent to the image of interest A feature adjacent to a feature; and (ii) an etched image 1002 (AEI) of one of the imaged patterns at the given position of the substrate, the AEI including one of the etched features corresponding to the feature of interest in the ADI . For example, the imaged pattern may be an array of contact holes at the center of the substrate. Within the array of contact holes, the feature of interest may be contact holes at specific coordinates (eg, GDS coordinates)”, & Page – 44, “Referring to FIG. 25A, the weight WT_ADICH1 (right image) of each contour point on the ADI feature ADICH1 is plotted against the angle. In addition, the weight WT_NH1 (right image) of each contour point on the adjacent ADI feature (for example, NCH) is plotted against the angle. The figure on the left illustrates an example layout of the ADI contact hole in the polar coordinate representation. In the arrangement of the contact holes (left picture), the dashed outline rch1 corresponds to the required feature or reference feature with a zero-weight outline point”, thus the plurality of position-optical measurement values comprising a plurality of position coordinates–light transmittance values is disclosed, because Kooiman obtains developed and etched images at given positions on a substrate, including features of interest located at specific coordinates (e.g., GDS coordinates), and further quantifies optical measurement values extracted from those images as numerical weights associated with each contour point represented in a polar coordinate system, such that each optical measurement value is tied to a specific spatial position of an etched product, which corresponds to collecting position-dependent optical (light transmittance) measurement values for a plurality of existing etched products)
Regarding Claim 11, Pack combined with Kooiman teaches all of the limitations of claim 8 as cited above and Kooiman further teaches:
wherein the plurality of statistical parameters comprises a mean, a minimum, a maximum, a median, a standard deviation, a skewness coefficient, a kurtosis coefficient, a mode, a coefficient of variation, a 25th percentile, a 75th percentile and a k-s statistics of the plurality of position-optical measurement values (Kooiman, Page – 30, “In this embodiment, because the model 1710 is a combined distribution of the first distribution and the second distribution, the model 1710 captures the relationship between the LCDU and the dose more accurately. Therefore, for example, the statistical parameters or characteristics of the fitting distribution 1710 can be used to more accurately determine the process window of the patterning process. In one embodiment, the method 1700 may further include procedures P1711 and P1713 configured to determine the process window PW. In one embodiment, P1711 includes extracting statistical features of the fitted probability distribution 1710 (for example, PDF1 in FIG. 17) related to the non-fault feature. For example, the statistical feature may be the average value, standard deviation, skewness, or other statistics related to the contact holes printed on the substrate”, thus the plurality of statistical parameters comprising a mean, a minimum, a maximum, a median, a standard deviation, a skewness coefficient, a kurtosis coefficient, a mode, a coefficient of variation, a 25th percentile, a 75th percentile, and a k-s statistic of the plurality of position-optical measurement values is disclosed, because Kooiman teaches extracting statistical features from a fitted probability distribution derived from position dependent optical measurements of etched features, including mean, standard deviation, and skewness, and further teaches use of other distribution-based statistical characteristics, which under the broadest reasonable interpretation includes the remaining claimed statistical parameters derived from such probability distributions)
Regarding Claim 12, Pack combined with Kooiman teaches all of the limitations of claim 8 as cited above and Kooiman further teaches:
wherein the plurality of histogram equalization parameters are plurality of probability values obtained by normalizing each of the plurality of position-optical measurement values (Kooiman, Page – 43, “In one embodiment, the relevant determination 2310 involves and on and Optimization of mutual information (in one embodiment, maximize). In one embodiment, the optimization of mutual information can be determined based on analytical methods or numerical methods. In one embodiment, the eigenvalue equation can be used to maximize the correlation 2310 between the combination of variables of ADI and the combination of variables of AEI. In one embodiment, the mutual information can be determined based on the spatial probability density function of the variable combination. In one embodiment, for example, for a limited data set, the probability density may not be calculated, but a normalized histogram may be used. An example method for estimating mutual information can be found in "Estimating mutual information" (Phys. Rev. E 69, 2004) of A. Kraskov, H. Stogbauer and P. Grassberger, which incorporates all of its contents by reference here”, thus thus, the plurality of histogram equalization parameters being plurality of probability values obtained by normalizing each of the plurality of position-optical measurement values is disclosed, because Kooiman teaches determining mutual information based on probability density functions of ADI and AEI variable combinations and teaches using a normalized histogram when probability densities are not directly calculated, where the normalized histogram represents probability values derived from normalizing measured ADI and AEI variables, which correspond to normalized position-optical measurement values)
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure. US 20230012173 A1 is pertinent because it teaches using a machine learning model trained on etching process parameters (recipes) and corresponding measured process results to predict etched shapes and to search for and select candidate etching recipes that achieve a target shape. The reference further teaches presenting multiple candidate recipes, evaluating predicted results, and considering sensitivity and reproducibility when selecting an etching recipe. Because the applicant likewise relies on machine-learning-based prediction of etching outcomes from recipe-related inputs to guide selection of suitable etching recipes, the reference is relevant to the claimed invention.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MAHLIET ADMASU whose telephone number is (571)272-0034. The examiner can normally be reached Mon-Fri, 8am-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, Alexey Shmatov can be reached at (571)270-3428. 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.
/M.T.A./Examiner, Art Unit 2123
/ALEXEY SHMATOV/Supervisory Patent Examiner, Art Unit 2123