DETAILED ACTION
This communication is in response to the Application No. 18/127,018 filed on April 24, 2026
in which Claims 1-3, 5-9, and 11 - 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 .
Response to Amendment
The amendments filed on April 24, 2026 have been considered. Claims 1-2, 5-8, and 11-12 have been amended. Claims 4 and 10 have been cancelled. Claims 3 and 9 are original. Thus, Claims 1-3, 5-9, and 11-12 are pending and presented for examination.
Applicant’s arguments filed April 24, 2026 with respect to the 35 U.S.C. 101 rejection have been fully considered but they are not persuasive.
Applicant’s argument on pg. 8 of Arguments/Remarks state:
PNG
media_image1.png
264
766
media_image1.png
Greyscale
PNG
media_image2.png
430
763
media_image2.png
Greyscale
Examiner respectfully disagrees. The claims merely recite “performing an optical measurement” without identifying any particular measurement instrument, metrology tool, light source, sensor, detector, or other apparatus that performs the measurement. Thus, Applicant’s argument reads into the claims a particular machine that is not recited. Although claim 7 recites a database and a processor, those generic computer components store and process data and are not recited as performing the optical measurement. The specification likewise does not identify a particular optical measurement apparatus. Paragraph [0024] merely describes performing optical measurements at position coordinates to obtain values such as light transmittance, reflectivity, or scattering degree.
Moreover, even assuming that the claims implicitly require a generic optical measurement device, the device is used only to obtain light transmittance values from previously etched semiconductor products for subsequent model training and prediction. Its involvement is therefore limited to gathering input data for the recited abstract analysis. A machine used merely in a data gathering step does not integrate the judicial exception into a practical application
Applicant’s argument on pg. 9 of Arguments/Remarks state:
PNG
media_image3.png
481
772
media_image3.png
Greyscale
Examiner respectfully disagrees. The claims require only the selection of a suggested etching recipe based on the prediction result. They do not require that the selected recipe actually be used to etch the semiconductor product. The phrase “to perform an actual etching operation” merely describes the intended use of the selected recipe and does not positively recite an etching step. Therefore, completion of the claimed method produces only a prediction result and a suggested recipe, while the semiconductor product to be etched remains physically unchanged. The specification similarly describes the actual etching operation as a later operation performed using the suggested recipe, rather than as part of the claimed method. Applicant’s argument that the claims amount to significantly more is therefore not persuasive.
Thus, the 35 U.S.C. 101 rejection is maintained.
Applicant’s arguments filed April 24, 2026 with respect to the 35 U.S.C. 103 rejections have been considered but are moot because the new ground of rejection.
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 1-3, 5-9, and 11-12 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 1-3, and 5-6 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.
dividing a surface of one of a plurality of semiconductor products into a two- dimensional coordinate system with a plurality of position coordinates (X0, Y0)-(Xi, Yj) on the surface (mathematical concept – dividing the surface into a two-dimensional coordinate system and representing locations on the surface using coordinate pairs recites a geometric mathematical relationship between points on the surface and numerical X and Y coordinates)
inputting a specification data of a semiconductor 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, […] for the semiconductor 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.
performing an optical measurement at each of the plurality of position coordinates (X0, Y0)-(Xi, Yj) to obtain one set of light transmittance values corresponding the plurality of position coordinates (X0, Y0)-(Xi, Yj), after the one of the plurality of semiconductor products is etched (Adding insignificant extra-solution activity to the judicial exception - see MPEP 2106.05(g))
collecting a plurality of etching recipes of the plurality of semiconductor products etched and a plurality sets of position light transmittance 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 light transmittance values in each of the plurality sets of position light transmittance 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)
[…] as a suggested etching recipe to perform an actual etching operation […] (mere instruction to apply an abstract idea - the limitation does not require performing the etching operation, the language states the intended use of the selected recipe rather than a physical transformation)
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.
performing an optical measurement at each of the plurality of position coordinates (X0, Y0)-(Xi, Yj) to obtain one set of light transmittance values corresponding the plurality of position coordinates (X0, Y0)-(Xi, Yj), after the one of the plurality of semiconductor products is etched (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)
collecting a plurality of etching recipes of the plurality of semiconductor products etched and a plurality sets of position light transmittance 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 light transmittance values in each of the plurality sets of position light transmittance 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)
[…] as a suggested etching recipe to perform an actual etching operation […] (mere instruction to apply an abstract idea - the limitation does not require performing the etching operation, the language states the intended use of the selected recipe rather than a physical transformation)
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 – 3 and 5-6. 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 light transmittance values in each of the plurality sets of position light transmittance 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 light transmittance 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 2 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 2. 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 2 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 light transmittance 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 2. 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 2 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 light transmittance 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 2. 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 7-9 and 11-12 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.
dividing a surface of one of a plurality of semiconductor products into a two- dimensional coordinate system with a plurality of position coordinates (X0, Y0)-(Xi, Yj) on the surface (mathematical concept – dividing the surface into a two-dimensional coordinate system and representing locations on the surface using coordinate pairs recites a geometric mathematical relationship between points on the surface and numerical X and Y coordinates)
wherein the predicting model is used to obtain a prediction result by inputting a specification data of a semiconductor 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))
performing an optical measurement at each of the plurality of position coordinates (X0, Y0)-(Xi, Yj) to obtain one set of light transmittance values corresponding the plurality of position coordinates (X0, Y0)-(Xi, Yj), after the one of the plurality of semiconductor products is etched (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 light transmittance values in each of the plurality of sets of position light transmittance 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 semiconductor for a plurality of existing etched products and a plurality of sets of position light transmittance 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)
performing an optical measurement at each of the plurality of position coordinates (X0, Y0)-(Xi, Yj) to obtain one set of light transmittance values corresponding the plurality of position coordinates (X0, Y0)-(Xi, Yj), after the one of the plurality of semiconductor products is etched (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 light transmittance values in each of the plurality of sets of position light transmittance 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 – 9 and 11-12. 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 light transmittance values in each of the plurality sets of position light transmittance 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 light transmittance 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 light transmittance values a category label corresponding to the plurality of eigenvector eigenvalues respectively, for carrying out the supervised learning training (mathematical concept – categorizing based on light transmittance 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 8 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 8. 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 8 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 light transmittance 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 8. 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 8 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 light transmittance 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 8. 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 1-3, 5-9, and 11-12 are rejected under 35 U.S.C. 103 as being unpatentable over Pack et al. (hereafter Pack) (US 20220198333) in view of Liu et al. (hereafter Liu) (US 20160268139) and in further view of Kooiman et al. (hereinafter Kooiman) (TW 202117576).
Regarding Claim 1, Pack teaches:
[…] of one of a plurality of semiconductor products […] (Pack, Claim 6, “predictive recipe parameters to be used by the substrate processing equipment to produce a plurality of substrates having the target performance data”, & Par. [0144], “the recipe may be used to produce the one or more substrates based on the recipe that has been optimized”, thus, […] of one of a plurality of semiconductor products […] is disclosed, because Pack teaches producing a plurality of substrates and processing one or more individual substrates using an optimized recipe. Pack’s individual substrate corresponds to one semiconductor product, and Pack’s plurality of substrates corresponds to the plurality of semiconductor products)
collecting a plurality of etching recipes of the plurality of semiconductor products etched […] corresponding to the plurality of etching recipes (Pack, Par. [0019], “processes can include one or more of deposition, etching, ion implantation, heating, cooling, transporting a substrate, purging airspace around the substrate, etc”, & Par. [0116], “the processing logic receives sets of historical parameters (e.g., historical parameters 144 of FIG. 1, historical recipe parameters, historical recipes that include the historical parameters) and/or historical recipes associated with producing one or more substrates with substrate processing equipment. The historical parameters may be from processes of one or more recipes”, & Par. [0118], “the processing logic receives sets of historical performance data (e.g., historical performance data 154 of FIG. 1) of the one or more substrates produced by the substrate processing equipment using the historical parameters. Each of the sets of the historical performance data corresponds to a respective set of historical parameters of the sets of historical parameters”, thus collecting a plurality of etching recipes of the plurality of semiconductor products etched […] corresponding to the plurality of etching recipes is disclosed, because Pack teaches receiving multiple historical recipes or sets of historical recipe parameters associated with producing one or more substrates using processes that include etching, and receiving multiple sets of historical performance data, with each performance-data set corresponding to a respective set of historical recipe parameters. Pack’s historical recipes associated with etching correspond to the plurality of etching recipes, Pack’s substrates correspond to the plurality of semiconductor products etched)
performing a supervised learning training according to […] each of the plurality sets […] to build a predicting model (Pack, Par. [0033], “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.)”, & Par. [0118], “the processing logic receives sets of historical performance data (e.g., historical performance data 154 of FIG. 1) of the one or more substrates produced by the substrate processing equipment using the historical parameters. Each of the sets of the historical performance data corresponds to a respective set of historical parameters of the sets of historical parameters”, & Par. [0134], “The high-dimension feature vector dataframe may be used for unsupervised and supervised learning. Unsupervised learning models may be used to gain insight on contributory variables and identify statistically unique experiments spanning this space. Supervised learning models may be trained for each response (e.g., performance data) and the most accurate supervised learning models may be used to form generalized models (e.g., the trained machine learning model)”, thus performing a supervised learning training according to […] each of the plurality sets […] to build a predicting model is disclosed, because Pack teaches using supervised machine learning with historical parameters labeled by corresponding historical performance data, receiving multiple sets of historical performance data corresponding to respective sets of historical parameters, and training supervised learning models for each performance-data response to form a trained machine learning model. Pack’s supervised machine learning corresponds to the supervised learning training, Pack’s historical performance data corresponding to respective historical parameters corresponds to each of the plurality sets, and Pack’s generalized trained machine learning model corresponds to the predicting model)
inputting a specification data of a semiconductor product to be etched […] into the predicting model to obtain a prediction result (Pack, Par. [0019], “processes can include one or more of deposition, etching, ion implantation, heating, cooling, transporting a substrate, purging airspace around the substrate, etc”, & Par. [0024], “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)”, & Par. [0055], “providing target performance data 158 into the one or more trained probabilistic machine learning models 190 to determine predictive parameters 148”, thus inputting a specification data of a semiconductor product to be etched […] into the predicting model to obtain a prediction result is disclosed, because Pack teaches identifying target performance data for a substrate processed using a recipe that may include etching, providing the target performance data to a trained machine learning model, and obtaining predictive parameters from the model. Pack’s target performance data corresponds to the specification data, Pack’s substrate processed using an etching process corresponds to the semiconductor product to be etched, Pack’s trained machine learning model corresponds to the predicting model, and Pack’s predictive parameters correspond to the prediction result)
and selecting one of the plurality of etching recipes, according to the prediction result, as a suggested etching recipe to perform an actual etching operation for the semiconductor product to be etched (Pack, Par. [0019], “processes can include one or more of deposition, etching, ion implantation, heating, cooling, transporting a substrate, purging airspace around the substrate, etc”, & Par. [0141], “processing logic obtains, from methods using the trained machine learning model, predictive data (e.g., predictive parameters, one or more inputs indicative of predictive parameters 148 of FIG. 1, predictive recipe parameters, predictive recipes, etc.). The predictive data may include target response and uncertainty distributions indicative of predictive recipes with parameters. The predictive recipes may include recipes chosen to improve overall model overall or those chosen with an aim of optimization”, & Par. [0142], “the processing logic performs numerical and/or stochastic optimization using the model to determine optimal parameter sets. In some embodiments, grid expansion is used to simulate over a grid on which the objective is subsequently sorted. In some objectives, variational statistics are gathered and used to determine the optimal parameter set which also meets sensitivity criterion (e.g., optimize recipe parameters for etch variance)”, & Par. [0144], “processing logic causes substrates to be produced based on the recipe that has been optimized. At block 550, the processing logic may cause recipes to be written in a format for the substrate processing machine and may upload this recipe. Subsequently, the recipe may be used to produce the one or more substrates based on the recipe that has been optimized (e.g., based on the predictive parameters)”, thus and selecting one of the plurality of etching recipes, according to the prediction result, as a suggested etching recipe to perform an actual etching operation for the semiconductor product to be etched is disclosed, because Pack teaches obtaining predictive recipes and predictive recipe parameters from a trained machine learning model, evaluating and sorting parameter sets to determine an optimal set for etching, and using the resulting optimized recipe in substrate-processing equipment to produce the substrate. Pack’s predictive recipes correspond to the plurality of etching recipes, Pack’s optimal recipe determined based on the predictive data corresponds to the suggested etching recipe selected according to the prediction result, and Pack’s use of the optimized recipe to process the substrate corresponds to performing the actual etching operation for the semiconductor product to be etched)
Pack does not explicitly teach dividing a surface […] into a two- dimensional coordinate system with a plurality of position coordinates (X0, Y0)-(Xi, Yj) on the surface, performing an optical measurement at […] to obtain one set of light transmittance values corresponding […] after the one of […] is etched, […] each of the plurality of position coordinates (X0, Y0)-(Xi, Yj) […] the plurality of position coordinates (X0, Y0)-(Xi, Yj), […], […] and a plurality sets of position light transmittance values […], […] a plurality of light transmittance values in […] of position light transmittance values, and […] including a position-optical parameter […].
However, Liu teaches:
performing an optical measurement at […] to obtain one set of light transmittance values corresponding […] after the one of [… plurality of semiconductor products…] is etched (Liu, Par. [0039], “the substrate may be irradiated by a light beam; the transmittance of the active layer pattern is sensed and measured; and the transmittance is taken as the transmittance reference value of the active layer. In order to guarantee the etching uniformity of the entire substrate, a plurality of data values at different positions of the active layer may be monitored, for instance, the data values at 9 to 25 points are measured”, & Par. [0057], “In the etching process, the transmittance of 9 to 25 points is monitored by same method in the step S302 and compared with data recorded in the step S302, namely the etching degree of the active layer is monitored by determining the variation between the transmittance present value and the transmittance reference value of the active layer, monitored in real time”, & Par. [0058], “when the transmittance is 100 to 120 percent of the previously recorded transmittance reference value, it indicates that the polysilicon layer (the active layer) has been just etched, and hence the etching process can be stopped”, thus performing an optical measurement to obtain one set of light-transmittance values after the semiconductor product is etched is disclosed, because Liu teaches irradiating the substrate with a light beam and sensing and measuring transmittance values at 9 to 25 positions, monitoring those transmittance values during the etching process, and determining from the measured values when the active layer has been just etched. Liu’s irradiation and sensing correspond to the optical measurement, Liu’s transmittance measurements at the 9 to 25 positions correspond to the one set of light-transmittance values, and Liu’s determination that the active layer has been just etched corresponds to obtaining the light-transmittance values after etching)
[…] and a plurality sets of position light transmittance values […] (Liu, Par. [0039], “the substrate may be irradiated by a light beam; the transmittance of the active layer pattern is sensed and measured; and the transmittance is taken as the transmittance reference value of the active layer. In order to guarantee the etching uniformity of the entire substrate, a plurality of data values at different positions of the active layer may be monitored, for instance, the data values at 9 to 25 points are measured”, & Par. [0057], “In the etching process, the transmittance of 9 to 25 points is monitored by same method in the step S302 and compared with data recorded in the step S302, namely the etching degree of the active layer is monitored by determining the variation between the transmittance present value and the transmittance reference value of the active layer, monitored in real time”, thus […] and a plurality sets of position light transmittance values […] is disclosed, because Liu teaches irradiating a substrate with a light beam and sensing and measuring transmittance values at 9 to 25 different positions of the active layer during the etching process. Liu’s transmittance measurements correspond to the light transmittance values, and Liu’s measurements at the plurality of different positions correspond to the plurality sets of position light transmittance values)
[…] a plurality of light transmittance values in […] of position light transmittance values […] (Liu, Par. [0039], “the substrate may be irradiated by a light beam; the transmittance of the active layer pattern is sensed and measured; and the transmittance is taken as the transmittance reference value of the active layer. In order to guarantee the etching uniformity of the entire substrate, a plurality of data values at different positions of the active layer may be monitored, for instance, the data values at 9 to 25 points are measured”, & Par. [0057], “In the etching process, the transmittance of 9 to 25 points is monitored by same method in the step S302 and compared with data recorded in the step S302, namely the etching degree of the active layer is monitored by determining the variation between the transmittance present value and the transmittance reference value of the active layer, monitored in real time”, thus, […] a plurality of light transmittance values in […] of position light transmittance values […] is disclosed, because Liu teaches sensing and measuring a plurality of transmittance values at 9 to 25 different positions of the active layer. Liu’s measured transmittance at each point corresponds to a light transmittance value, and Liu’s transmittance values measured at the different positions correspond to the position light transmittance values)
[…] including a position-optical parameter […] (Liu, Par. [0039], “the substrate may be irradiated by a light beam; the transmittance of the active layer pattern is sensed and measured; and the transmittance is taken as the transmittance reference value of the active layer. In order to guarantee the etching uniformity of the entire substrate, a plurality of data values at different positions of the active layer may be monitored, for instance, the data values at 9 to 25 points are measured”, thus […] including a position-optical parameter […] is disclosed, because Liu teaches measuring an optical transmittance reference value at each of a plurality of different positions of the active layer. Liu’s measured transmittance corresponds to the optical parameter, and the location at which each transmittance value is measured corresponds to the position associated with the position-optical parameter)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to combine Pack’s teaching of using supervised machine learning to analyze etching recipe parameters and corresponding performance data to predict and select an optimized etching recipe with Liu’s teaching of measuring light transmittance at a plurality of substrate positions during etching. Pack teaches using metrology and performance data corresponding to historical etching recipes to train a predicting model and determine an optimized recipe for processing a semiconductor substrate. Liu teaches optical measurements taken at multiple positions that provide information regarding the etching degree and uniformity of the substrate. Therefore, a POSITA would have been motivated to incorporate Liu’s position light transmittance measurements as performance data in Pack’s machine learning recipe optimization system so that the predicting model could account for etching degree and spatial uniformity when predicting and selecting an etching recipe, thereby improving control of the etching operation, preventing excessive etching, protecting the active layer, and improving substrate uniformity and product yield (Liu, Par. [0073], “the etching degree can be simply and effectively controlled; the etching process can be stopped in time when the active layer has been just etched; and the performance of the active layer is guaranteed not to be damaged. Moreover, with the arrangement of a plurality of monitoring points, the etching uniformity of the entire substrate can be guaranteed and the yield of prepared large area polysilicon substrates can be improved”, and Par. [0074], “can effectively monitor the etching degree of the film by comparing the transmittance of the film on different states, so as to guarantee that the film is not over etched, guarantee the performance of the film, and hence improve the yield of products”)
Pack combined with Liu does not explicitly teach dividing a surface […] into a two- dimensional coordinate system with a plurality of position coordinates (X0, Y0)-(Xi, Yj) on the surface, […] each of the plurality of position coordinates (X0, Y0)-(Xi, Yj) […] the plurality of position coordinates (X0, Y0)-(Xi, Yj), […].
However, Kooiman teaches:
dividing a surface […] into a two- dimensional coordinate system with a plurality of position coordinates (X0, Y0)-(Xi, Yj) on the surface (Kooiman, Page 52, “The two-dimensional electron beam image can be obtained by, for example, the two-dimensional scanning of the electron beam by the beam deflector EBD1 in the X or Y direction or the repeated scanning of the electron beam EBP by the beam deflector EBD1 Groundly detect the electrons generated from the sample, and continuously move the substrate PSub by the substrate stage ST in the other of the X or Y directions”, & 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)”, thus Kooiman teaches dividing or representing a surface of a semiconductor substrate using a two-dimensional coordinate system having a plurality of position coordinates, because Kooiman obtains a two-dimensional image by scanning the substrate in the X and Y directions and identifies features located at specific coordinates on the substrate)
[…] each of the plurality of position coordinates (X0, Y0)-(Xi, Yj) […] the plurality of position coordinates (X0, Y0)-(Xi, Yj), […] (Kooiman, Page 52, “The two-dimensional electron beam image can be obtained by, for example, the two-dimensional scanning of the electron beam by the beam deflector EBD1 in the X or Y direction or the repeated scanning of the electron beam EBP by the beam deflector EBD1 Groundly detect the electrons generated from the sample, and continuously move the substrate PSub by the substrate stage ST in the other of the X or Y directions”, & Page 15, “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)”, thus each of the plurality of position coordinates (X0, Y0)-(Xi, Yj) and the plurality of position coordinates (X0, Y0)-(Xi, Yj) are disclosed, because Kooiman teaches generating a two-dimensional image of the substrate by scanning in the X and Y directions and identifies features within an array at specific GDS coordinates. Kooiman’s X- and Y-direction scanning corresponds to the two-dimensional coordinate system, and Kooiman’s specific GDS coordinates correspond to the plurality of position coordinates (X0, Y0)-(Xi, Yj))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to further combine Pack and Liu with Kooiman’s teaching of identifying substrate measurement locations using a two dimensional coordinate system and specific position coordinates. Pack teaches using recipe parameters and corresponding performance data to train a predicting model, while Liu teaches measuring light transmittance at a plurality of positions to evaluate etching uniformity. Kooiman teaches that measurements should be associated with particular substrate locations because different locations may require different etching conditions. Therefore, a POSITA would have been motivated to associate each of Liu’s position light transmittance values with Kooiman’s specific two dimensional position coordinates and provide the position associated measurements to Pack’s predicting model so that the model could account for variations in etching conditions across the substrate, control the etching recipe according to the spatial measurements, improve etching uniformity, and increase the number of substrate dies within the specification range (Kooiman, Page 18, “Generally, even if the pattern density is the same, different etching conditions may be required at different positions on the substrate due to the thickness distribution of the substrate, the drift associated with the etching equipment, and so on”&Page 18-19, “the correlation can be used to monitor and control the performance of the patterning process by controlling the etching recipe and etching conditions (for example, tuning parameters), so that the correlation is kept within the target range. For example, the etching processing chamber is monitored based on the uniformity of the critical dimensions across the entire substrate or the CD difference between different features at different radii across the entire substrate. In one example, control involves not only determining the impact on CD based on selectable etching knobs (e.g., etching knobs). Air pressure, power, DC, temperature, etc. are also related. Then, the required performance can be monitored (for example, whether the correlation remains within the target range). The benefit of doing so is that in the final yield test, there will be more substrate die within the specification range”)
Regarding Claim 2, Pack and Liu combined with Kooiman teaches all 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 […] to serve as a plurality of eigenvector eigenvalues (Kooiman, Page 43, “the following correlation R² equation can be used to calculate the correlation 2310: In the above formula, cov and var represent the covariance and variance of the variables”, & Pages 43 - 44, “The first equation (A) is to determine the eigenvalues and eigenvectors of R² [using] the eigenvalue equation”, & Page 44, “the number of non zero eigenvalues is at most a vector and the minimum length. Among these non zero eigenvalues, only a limited number of eigenvalues correspond to R²”, thus, extracting a plurality of statistical parameters and/or a plurality of histogram equalization parameters of […] to serve as a plurality of eigenvector eigenvalues is disclosed, because Kooiman teaches calculating multiple statistical parameters, including covariance and variance, from sets of measured variables and applying an eigenvalue equation to determine multiple eigenvalues and corresponding eigenvectors. Kooiman’s covariance and variance correspond to the plurality of statistical parameters, and Kooiman’s multiple eigenvalues and corresponding eigenvectors correspond to the plurality of eigenvector eigenvalues)
and allocating each of […] a category label corresponding to the plurality of eigenvector eigenvalues respectively, for carrying out the supervised learning training (Kooiman, Page 14, “A set of training data can be used to train the neural network. The training data may include or consist of a training sample set. Each sample may include an input object, usually a vector, which may be called a feature vector, and a desired output value, also called a supervisory signal”, & Page 14, “xᵢ [is] the feature vector of the i th instance and yᵢ is the supervision signal”, & Pages 43 - 44, “The first equation (A) is to determine the eigenvalues and eigenvectors of R² [using] the eigenvalue equation”, & Page 28, “the first set of points P1, P2, P3, P4, and P6 represent the judgment of the trained machine learning model, that is, the feature will be defective after etching. The second point P10, P11, P12, P13, ..., P20 represents the judgment of the trained machine learning model, that is, the feature will not be defective after etching”, thus, and allocating each of […] a category label corresponding to the plurality of eigenvector eigenvalues respectively, for carrying out the supervised learning training is disclosed, because Kooiman teaches determining a plurality of eigenvalues and corresponding eigenvectors, providing each feature vector in a training sample with a corresponding desired output or supervisory signal, and using categories indicating that a feature will be defective or will not be defective. Kooiman’s desired output or supervisory signal corresponds to the category label, Kooiman’s defective and will not be defective judgments correspond to different category labels, and Kooiman’s corresponding eigenvalues and eigenvectors correspond to the plurality of eigenvector eigenvalues used as the labeled feature vectors for supervised learning training)
Liu further teaches:
[…] a plurality of optical measurement light transmittance values in each of the plurality sets of position-optical measurement light transmittance values […] (Liu, Par. [0039], “the substrate may be irradiated by a light beam; the transmittance of the active layer pattern is sensed and measured; and the transmittance is taken as the transmittance reference value of the active layer. In order to guarantee the etching uniformity of the entire substrate, a plurality of data values at different positions of the active layer may be monitored, for instance, the data values at 9 to 25 points are measured”, thus, […] a plurality of optical measurement light transmittance values in each of the plurality sets of position-optical measurement light transmittance values […] is disclosed, because Liu teaches optically measuring multiple light transmittance values at multiple positions of the active layer. Liu’s measured transmittance values correspond to the plurality of optical measurement light transmittance values, and Liu’s measurements at 9 to 25 different positions correspond to the plurality sets of position-optical measurement light transmittance values)
[…] the plurality of position-optical measurement light transmittance values […] (Liu, Par. [0039], “the substrate may be irradiated by a light beam; the transmittance of the active layer pattern is sensed and measured; and the transmittance is taken as the transmittance reference value of the active layer. In order to guarantee the etching uniformity of the entire substrate, a plurality of data values at different positions of the active layer may be monitored, for instance, the data values at 9 to 25 points are measured”, thus, […] the plurality of position-optical measurement light transmittance values […] is disclosed, because Liu teaches measuring light transmittance values at a plurality of different positions of the active layer. Liu’s measured transmittance values correspond to the optical measurement light transmittance values, and Liu’s different measurement positions correspond to the position associated with each position-optical measurement light transmittance value)
Regarding Claim 3, Pack and Liu combined with Kooiman teaches all 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 5, Pack and Liu combined with Kooiman teaches all 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 light transmittance 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. 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 statistics of the plurality of position light transmittance values is disclosed, because Kooiman teaches extracting statistical features from a fitted probability distribution, expressly including an average value, standard deviation, skewness, and other statistics. Kooiman’s average value corresponds to the mean, Kooiman’s standard deviation corresponds to the standard deviation, Kooiman’s skewness corresponds to the skewness coefficient, and Kooiman’s other distribution based statistics correspond to the remaining recited statistical parameters)
Regarding Claim 6, Pack and Liu combined with Kooiman teaches all 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 light transmittance values (Kooiman, Page 43, “In one embodiment, the relevant determination 2310 involves optimization of mutual information. 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”, thus the plurality of histogram equalization parameters being plurality of probability values obtained by normalizing each of the plurality of position light transmittance values is disclosed, because Kooiman teaches determining probability information from measured variable combinations using a spatial probability density function and using a normalized histogram when the probability density is not directly calculated. Kooiman’s normalized histogram corresponds to the plurality of histogram equalization parameters, and the normalized values represented by the histogram correspond to the plurality of probability values obtained by normalizing the plurality of position light transmittance values)
Regarding Claim 7, Pack teaches:
a database, used to store a historical data comprising a plurality of etching recipes for a plurality of semiconductor products […] corresponding to the plurality of the etching recipes […] (Pack, Par. [0039], “the data store 140 is a memory (e.g., random access memory), a drive (e.g., a hard drive, a flash drive), a database system, or another type of component or device capable of storing data”, & “the data store 140 stores one or more of parameters 142, performance data 152, recipe 160, and/or uncertainty data 162”, & Par. [0040], “Parameters 142 include historical parameters 144 (e.g., historical recipe parameters)”, & Par. [0116], “the processing logic receives sets of historical parameters (e.g., historical parameters 144 of FIG. 1, historical recipe parameters, historical recipes that include the historical parameters) and/or historical recipes associated with producing one or more substrates with substrate processing equipment”, & Par. [0118], “the processing logic receives sets of historical performance data (e.g., historical performance data 154 of FIG. 1) of the one or more substrates produced by the substrate processing equipment using the historical parameters. Each of the sets of the historical performance data corresponds to a respective set of historical parameters of the sets of historical parameters”, thus a database, used to store a historical data comprising a plurality of etching recipes for a plurality of semiconductor products […] corresponding to the plurality of the etching recipes […] is disclosed, because Pack teaches a database system that stores recipes, historical recipe parameters, and corresponding performance data for one or more substrates. Pack’s database system corresponds to the database, Pack’s stored historical recipes correspond to the plurality of etching recipes, Pack’s substrates correspond to the plurality of semiconductor products, and Pack’s performance data corresponding to respective historical parameters corresponds to the data corresponding to the plurality of etching recipes)
[…] of one of a plurality of semiconductor products […] (Pack, Claim 6, “predictive recipe parameters to be used by the substrate processing equipment to produce a plurality of substrates having the target performance data”, & Par. [0144], “the recipe may be used to produce the one or more substrates based on the recipe that has been optimized”, thus, […] of one of a plurality of semiconductor products […] is disclosed, because Pack teaches producing a plurality of substrates and processing one or more individual substrates using an optimized recipe. Pack’s individual substrate corresponds to one semiconductor product, and Pack’s plurality of substrates corresponds to the plurality of semiconductor products)
a processor, comprising a predicting model built by a supervised learning training using […] each of the plurality of sets […] (Pack, Par. [0007], “a system includes a memory and a processing device coupled to the memory. The processing device is to train a machine learning model with data input including one or more sets of historical recipe parameters associated with producing one or more substrates with substrate processing equipment and target data including historical performance data of the one or more substrates to generate a trained machine learning model”, & Par. [0033], “the predictive system 110 (e.g., predictive server 112, predictive component 114) generates predictive parameters 148 using supervised machine learning”, & Par. [0134], “Supervised learning models may be trained for each response (e.g., performance data) and the most accurate supervised learning models may be used to form generalized models (e.g., the trained machine learning model)”, thus a processor comprising a predicting model built by supervised learning using […] each of the plurality of sets […] is disclosed, because Pack teaches a processing device that trains a machine learning model through supervised learning using multiple corresponding sets of training data)
wherein the predicting model is used to obtain a prediction result by inputting a specification data of a semiconductor product to be etched […] into the predicting model, and to select one of the plurality of the etching recipes as a suggested etching recipe to performing an actual etching operation for the semiconductor product to be etched according to the prediction result (Pack, Par. [0019], “processes can include one or more of deposition, etching, ion implantation, heating, cooling, transporting a substrate, purging airspace around the substrate, etc”, & Par. [0024], “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)”, & Par. [0055], “providing target performance data 158 into the one or more trained probabilistic machine learning models 190 to determine predictive parameters 148”, & & Par. [0141], “processing logic obtains, from methods using the trained machine learning model, predictive data (e.g., predictive parameters, one or more inputs indicative of predictive parameters 148 of FIG. 1, predictive recipe parameters, predictive recipes, etc.). The predictive data may include target response and uncertainty distributions indicative of predictive recipes with parameters. The predictive recipes may include recipes chosen to improve overall model overall or those chosen with an aim of optimization”, & Par. [0142], “the processing logic performs numerical and/or stochastic optimization using the model to determine optimal parameter sets. In some embodiments, grid expansion is used to simulate over a grid on which the objective is subsequently sorted. In some objectives, variational statistics are gathered and used to determine the optimal parameter set which also meets sensitivity criterion (e.g., optimize recipe parameters for etch variance)”, & Par. [0144], “processing logic causes substrates to be produced based on the recipe that has been optimized. At block 550, the processing logic may cause recipes to be written in a format for the substrate processing machine and may upload this recipe. Subsequently, the recipe may be used to produce the one or more substrates based on the recipe that has been optimized (e.g., based on the predictive parameters)”, thus wherein the predicting model is used to obtain a prediction result by inputting a specification data of a semiconductor product to be etched […] into the predicting model, and to select one of the plurality of the etching recipes as a suggested etching recipe to performing an actual etching operation for the semiconductor product to be etched according to the prediction result is disclosed, because Pack teaches inputting target substrate performance data into a trained machine learning model, obtaining predictive recipe parameters and predictive recipes, determining an optimal recipe based on the predictive data, and using the optimized recipe in substrate processing equipment to perform a process that may include etching. Pack’s target performance data corresponds to the specification data, Pack’s predictive data corresponds to the prediction result, Pack’s optimized predictive recipe corresponds to the suggested etching recipe, and Pack’s use of the optimized recipe to process the substrate corresponds to performing the actual etching operation)
Pack does not explicitly teach […] and a plurality of sets position light transmittance values […] wherein the plurality of sets of position-light transmittance values are obtained by, dividing a surface […] into a two- dimensional coordinate system with a plurality of position coordinates (X0, Y0)-(Xi, Yj) on the surface, performing an optical measurement at […] to obtain one set of light transmittance values corresponding […] after the one of […] is etched, […] each of the plurality of position coordinates (X0, Y0)-(Xi, Yj) […] the plurality of position coordinates (X0, Y0)-(Xi, Yj), […], […] a plurality of light transmittance values in […] of position light transmittance values, and […] including a position-optical parameter […].
However, Liu teaches:
[…] and a plurality of sets position light transmittance values […] wherein the plurality of sets of position-light transmittance values are obtained by: (Liu, Par. [0039], “the substrate may be irradiated by a light beam; the transmittance of the active layer pattern is sensed and measured; and the transmittance is taken as the transmittance reference value of the active layer. In order to guarantee the etching uniformity of the entire substrate, a plurality of data values at different positions of the active layer may be monitored, for instance, the data values at 9 to 25 points are measured”, & Par. [0057], “In the etching process, the transmittance of 9 to 25 points is monitored by same method in the step S302 and compared with data recorded in the step S302”, thus […] and a plurality of sets position light transmittance values […] wherein the plurality of sets of position-light transmittance values are obtained by: is disclosed, because Liu teaches irradiating the substrate with light and sensing and measuring light transmittance values at 9 to 25 different positions during etching. Liu’s measured transmittance values correspond to the position light transmittance values, and Liu’s repeated measurements at multiple positions correspond to the plurality of sets of position-light transmittance values)
performing an optical measurement at […] to obtain one set of light transmittance values corresponding […] after the one of [… plurality of semiconductor products…] is etched (Liu, Par. [0039], “the substrate may be irradiated by a light beam; the transmittance of the active layer pattern is sensed and measured; and the transmittance is taken as the transmittance reference value of the active layer. In order to guarantee the etching uniformity of the entire substrate, a plurality of data values at different positions of the active layer may be monitored, for instance, the data values at 9 to 25 points are measured”, & Par. [0057], “In the etching process, the transmittance of 9 to 25 points is monitored by same method in the step S302 and compared with data recorded in the step S302, namely the etching degree of the active layer is monitored by determining the variation between the transmittance present value and the transmittance reference value of the active layer, monitored in real time”, & Par. [0058], “when the transmittance is 100 to 120 percent of the previously recorded transmittance reference value, it indicates that the polysilicon layer (the active layer) has been just etched, and hence the etching process can be stopped”, thus performing an optical measurement to obtain one set of light-transmittance values after the semiconductor product is etched is disclosed, because Liu teaches irradiating the substrate with a light beam and sensing and measuring transmittance values at 9 to 25 positions, monitoring those transmittance values during the etching process, and determining from the measured values when the active layer has been just etched. Liu’s irradiation and sensing correspond to the optical measurement, Liu’s transmittance measurements at the 9 to 25 positions correspond to the one set of light-transmittance values, and Liu’s determination that the active layer has been just etched corresponds to obtaining the light-transmittance values after etching)
[…] a plurality of light transmittance values in […] of position light transmittance values […] (Liu, Par. [0039], “the substrate may be irradiated by a light beam; the transmittance of the active layer pattern is sensed and measured; and the transmittance is taken as the transmittance reference value of the active layer. In order to guarantee the etching uniformity of the entire substrate, a plurality of data values at different positions of the active layer may be monitored, for instance, the data values at 9 to 25 points are measured”, & Par. [0057], “In the etching process, the transmittance of 9 to 25 points is monitored by same method in the step S302 and compared with data recorded in the step S302, namely the etching degree of the active layer is monitored by determining the variation between the transmittance present value and the transmittance reference value of the active layer, monitored in real time”, thus, […] a plurality of light transmittance values in […] of position light transmittance values […] is disclosed, because Liu teaches sensing and measuring a plurality of transmittance values at 9 to 25 different positions of the active layer. Liu’s measured transmittance at each point corresponds to a light transmittance value, and Liu’s transmittance values measured at the different positions correspond to the position light transmittance values)
[…] including a position-optical parameter […] (Liu, Par. [0039], “the substrate may be irradiated by a light beam; the transmittance of the active layer pattern is sensed and measured; and the transmittance is taken as the transmittance reference value of the active layer. In order to guarantee the etching uniformity of the entire substrate, a plurality of data values at different positions of the active layer may be monitored, for instance, the data values at 9 to 25 points are measured”, thus […] including a position-optical parameter […] is disclosed, because Liu teaches measuring an optical transmittance reference value at each of a plurality of different positions of the active layer. Liu’s measured transmittance corresponds to the optical parameter, and the location at which each transmittance value is measured corresponds to the position associated with the position-optical parameter)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to combine Pack’s teaching of using supervised machine learning to analyze etching recipe parameters and corresponding performance data to predict and select an optimized etching recipe with Liu’s teaching of measuring light transmittance at a plurality of substrate positions during etching. Pack teaches using metrology and performance data corresponding to historical etching recipes to train a predicting model and determine an optimized recipe for processing a semiconductor substrate. Liu teaches optical measurements taken at multiple positions that provide information regarding the etching degree and uniformity of the substrate. Therefore, a POSITA would have been motivated to incorporate Liu’s position light transmittance measurements as performance data in Pack’s machine learning recipe optimization system so that the predicting model could account for etching degree and spatial uniformity when predicting and selecting an etching recipe, thereby improving control of the etching operation, preventing excessive etching, protecting the active layer, and improving substrate uniformity and product yield (Liu, Par. [0073], “the etching degree can be simply and effectively controlled; the etching process can be stopped in time when the active layer has been just etched; and the performance of the active layer is guaranteed not to be damaged. Moreover, with the arrangement of a plurality of monitoring points, the etching uniformity of the entire substrate can be guaranteed and the yield of prepared large area polysilicon substrates can be improved”, and Par. [0074], “can effectively monitor the etching degree of the film by comparing the transmittance of the film on different states, so as to guarantee that the film is not over etched, guarantee the performance of the film, and hence improve the yield of products”)
Pack combined with Liu does not explicitly teach dividing a surface […] into a two- dimensional coordinate system with a plurality of position coordinates (X0, Y0)-(Xi, Yj) on the surface, […] each of the plurality of position coordinates (X0, Y0)-(Xi, Yj) […] the plurality of position coordinates (X0, Y0)-(Xi, Yj), […].
However, Kooiman teaches:
dividing a surface […] into a two- dimensional coordinate system with a plurality of position coordinates (X0, Y0)-(Xi, Yj) on the surface (Kooiman, Page 52, “The two-dimensional electron beam image can be obtained by, for example, the two-dimensional scanning of the electron beam by the beam deflector EBD1 in the X or Y direction or the repeated scanning of the electron beam EBP by the beam deflector EBD1 Groundly detect the electrons generated from the sample, and continuously move the substrate PSub by the substrate stage ST in the other of the X or Y directions”, & 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)”, thus Kooiman teaches dividing or representing a surface of a semiconductor substrate using a two-dimensional coordinate system having a plurality of position coordinates, because Kooiman obtains a two-dimensional image by scanning the substrate in the X and Y directions and identifies features located at specific coordinates on the substrate)
[…] each of the plurality of position coordinates (X0, Y0)-(Xi, Yj) […] the plurality of position coordinates (X0, Y0)-(Xi, Yj), […] (Kooiman, Page 52, “The two-dimensional electron beam image can be obtained by, for example, the two-dimensional scanning of the electron beam by the beam deflector EBD1 in the X or Y direction or the repeated scanning of the electron beam EBP by the beam deflector EBD1 Groundly detect the electrons generated from the sample, and continuously move the substrate PSub by the substrate stage ST in the other of the X or Y directions”, & Page 15, “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)”, thus each of the plurality of position coordinates (X0, Y0)-(Xi, Yj) and the plurality of position coordinates (X0, Y0)-(Xi, Yj) are disclosed, because Kooiman teaches generating a two-dimensional image of the substrate by scanning in the X and Y directions and identifies features within an array at specific GDS coordinates. Kooiman’s X- and Y-direction scanning corresponds to the two-dimensional coordinate system, and Kooiman’s specific GDS coordinates correspond to the plurality of position coordinates (X0, Y0)-(Xi, Yj))
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to further combine Pack and Liu with Kooiman’s teaching of identifying substrate measurement locations using a two dimensional coordinate system and specific position coordinates. Pack teaches using recipe parameters and corresponding performance data to train a predicting model, while Liu teaches measuring light transmittance at a plurality of positions to evaluate etching uniformity. Kooiman teaches that measurements should be associated with particular substrate locations because different locations may require different etching conditions. Therefore, a POSITA would have been motivated to associate each of Liu’s position light transmittance values with Kooiman’s specific two dimensional position coordinates and provide the position associated measurements to Pack’s predicting model so that the model could account for variations in etching conditions across the substrate, control the etching recipe according to the spatial measurements, improve etching uniformity, and increase the number of substrate dies within the specification range (Kooiman, Page 18, “Generally, even if the pattern density is the same, different etching conditions may be required at different positions on the substrate due to the thickness distribution of the substrate, the drift associated with the etching equipment, and so on”&Page 18-19, “the correlation can be used to monitor and control the performance of the patterning process by controlling the etching recipe and etching conditions (for example, tuning parameters), so that the correlation is kept within the target range. For example, the etching processing chamber is monitored based on the uniformity of the critical dimensions across the entire substrate or the CD difference between different features at different radii across the entire substrate. In one example, control involves not only determining the impact on CD based on selectable etching knobs (e.g., etching knobs). Air pressure, power, DC, temperature, etc. are also related. Then, the required performance can be monitored (for example, whether the correlation remains within the target range). The benefit of doing so is that in the final yield test, there will be more substrate die within the specification range”)
Regarding Claim 8, Pack and Liu combined with Kooiman teaches all 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 […] to serve as a plurality of eigenvector eigenvalues (Kooiman, Page 43, “the following correlation R² equation can be used to calculate the correlation 2310: In the above formula, cov and var represent the covariance and variance of the variables”, & Pages 43 - 44, “The first equation (A) is to determine the eigenvalues and eigenvectors of R² [using] the eigenvalue equation”, & Page 44, “the number of non zero eigenvalues is at most a vector and the minimum length. Among these non zero eigenvalues, only a limited number of eigenvalues correspond to R²”, thus, extracting a plurality of statistical parameters and/or a plurality of histogram equalization parameters of […] to serve as a plurality of eigenvector eigenvalues is disclosed, because Kooiman teaches calculating multiple statistical parameters, including covariance and variance, from sets of measured variables and applying an eigenvalue equation to determine multiple eigenvalues and corresponding eigenvectors. Kooiman’s covariance and variance correspond to the plurality of statistical parameters, and Kooiman’s multiple eigenvalues and corresponding eigenvectors correspond to the plurality of eigenvector eigenvalues)
and allocating each of […] a category label corresponding to the plurality of eigenvector eigenvalues respectively, for carrying out the supervised learning training (Kooiman, Page 14, “A set of training data can be used to train the neural network. The training data may include or consist of a training sample set. Each sample may include an input object, usually a vector, which may be called a feature vector, and a desired output value, also called a supervisory signal”, & Page 14, “xᵢ [is] the feature vector of the i th instance and yᵢ is the supervision signal”, & Pages 43 - 44, “The first equation (A) is to determine the eigenvalues and eigenvectors of R² [using] the eigenvalue equation”, & Page 28, “the first set of points P1, P2, P3, P4, and P6 represent the judgment of the trained machine learning model, that is, the feature will be defective after etching. The second point P10, P11, P12, P13, ..., P20 represents the judgment of the trained machine learning model, that is, the feature will not be defective after etching”, thus, and allocating each of […] a category label corresponding to the plurality of eigenvector eigenvalues respectively, for carrying out the supervised learning training is disclosed, because Kooiman teaches determining a plurality of eigenvalues and corresponding eigenvectors, providing each feature vector in a training sample with a corresponding desired output or supervisory signal, and using categories indicating that a feature will be defective or will not be defective. Kooiman’s desired output or supervisory signal corresponds to the category label, Kooiman’s defective and will not be defective judgments correspond to different category labels, and Kooiman’s corresponding eigenvalues and eigenvectors correspond to the plurality of eigenvector eigenvalues used as the labeled feature vectors for supervised learning training)
Liu further teaches:
[…] a plurality of optical measurement light transmittance values in each of the plurality sets of position-optical measurement light transmittance values […] (Liu, Par. [0039], “the substrate may be irradiated by a light beam; the transmittance of the active layer pattern is sensed and measured; and the transmittance is taken as the transmittance reference value of the active layer. In order to guarantee the etching uniformity of the entire substrate, a plurality of data values at different positions of the active layer may be monitored, for instance, the data values at 9 to 25 points are measured”, thus, […] a plurality of optical measurement light transmittance values in each of the plurality sets of position-optical measurement light transmittance values […] is disclosed, because Liu teaches optically measuring multiple light transmittance values at multiple positions of the active layer. Liu’s measured transmittance values correspond to the plurality of optical measurement light transmittance values, and Liu’s measurements at 9 to 25 different positions correspond to the plurality sets of position-optical measurement light transmittance values)
[…] the plurality of position-optical measurement light transmittance values […] (Liu, Par. [0039], “the substrate may be irradiated by a light beam; the transmittance of the active layer pattern is sensed and measured; and the transmittance is taken as the transmittance reference value of the active layer. In order to guarantee the etching uniformity of the entire substrate, a plurality of data values at different positions of the active layer may be monitored, for instance, the data values at 9 to 25 points are measured”, thus, […] the plurality of position-optical measurement light transmittance values […] is disclosed, because Liu teaches measuring light transmittance values at a plurality of different positions of the active layer. Liu’s measured transmittance values correspond to the optical measurement light transmittance values, and Liu’s different measurement positions correspond to the position associated with each position-optical measurement light transmittance value)
Regarding Claim 9, Pack and Liu combined with Kooiman teaches all 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 11, Pack and Liu combined with Kooiman teaches all 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 light transmittance 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. 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 statistics of the plurality of position light transmittance values is disclosed, because Kooiman teaches extracting statistical features from a fitted probability distribution, expressly including an average value, standard deviation, skewness, and other statistics. Kooiman’s average value corresponds to the mean, Kooiman’s standard deviation corresponds to the standard deviation, Kooiman’s skewness corresponds to the skewness coefficient, and Kooiman’s other distribution based statistics correspond to the remaining recited statistical parameters)
Regarding Claim 12, Pack and Liu combined with Kooiman teaches all 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 light transmittance values (Kooiman, Page 43, “In one embodiment, the relevant determination 2310 involves optimization of mutual information. 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”, thus the plurality of histogram equalization parameters being plurality of probability values obtained by normalizing each of the plurality of position light transmittance values is disclosed, because Kooiman teaches determining probability information from measured variable combinations using a spatial probability density function and using a normalized histogram when the probability density is not directly calculated. Kooiman’s normalized histogram corresponds to the plurality of histogram equalization parameters, and the normalized values represented by the histogram correspond to the plurality of probability values obtained by normalizing the plurality of position light transmittance values)
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
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
Prosecution Insights