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 .
DETAILED ACTION
This office action is in response to the claims filed on01/29/2026.
Claims 1, 3-7, 9-12, 15-18, 20-21 are presented for examination.
Response to Argument
In reference to applicant’s argument regrading rejections under 35 U.S.C. § 101:
Applicant’s Argument:
Amended claim 1 includes the features of "calculating a plurality of normalized data values using the identified historical spectral data associated with the initial step, the first subsequent step, and the second subsequent step, wherein: a first normalized data value of the plurality of normalized data values is calculated based on a difference between a baseline wave amplitude at an initial time period of the prior process indicated by the historical spectral data associated with the initial step and a first wave amplitude at a first subsequent time period of the prior process indicated by the historical spectral data associated with the first subsequent step, wherein the first normalized data value represents a change in a substrate feature associated with the prior substrate between the initial time period and the first subsequent time period, and a second normalized data value of the plurality of normalized data values is calculated based on a difference between the baseline wave amplitude and a second wave amplitude at a second subsequent time period indicated by the historical spectral data associated with the second subsequent step, wherein the second normalized data value represents an additional change in the substrate feature between the initial time period and the second subsequent time period." As described in the Specification, spectral data refers to "data associated with an intensity for a detected wave of energy for each wavelength of light reflected from a surface of the substrate." (Specification, [0023]). The calculation of normalized data values representing differences between wave amplitudes at different time periods of a manufacturing process involves processing complex spectral measurements that cannot practically be performed in the human mind. A human cannot mentally observe, retain, and calculate differences between wave amplitudes across multiple wavelengths of light reflected from a substrate surface during manufacturing processing steps.
Claim 1 further recites "generating a training input comprising at least a normalized set of historical spectral data comprising the plurality of normalized data values and an indication of one or more historical spectral features associated with a particular type of metrology measurement" and "providing the training data to train the machine learning model on (i) a set of training inputs comprising the training input and (ii) a set of target outputs comprising the target output." Training a machine learning model using normalized spectral data to correlate spectral amplitude changes with metrology measurements is not a mental process, as it requires computational processing that cannot be performed in the human mind.
Examiner’s Response:
Examiner respectfully disagrees to applicant’s argument regarding the 101 rejection based on the mental process, because these limitations were not rejected under abstract idea (mental process), however, these limitations were rejected under the step 2a prong 2 and step 2b, such as -“calculating a plurality of normalized data values based on the … wherein the second normalized data value represents an additional change in the substrate feature between the initial time period and the second subsequent time period.”, “generating a training input comprising at least a normalized set of historical spectral data comprising the plurality of normalized data values and an indication of one or more historical spectral features associated with a particular type of metrology measurement", This/these limitation(s) is/are amount to no more than generally linking the use of a judicial exception to a particular technological environment or field of use. As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not amount to significantly more than the exception itself, and cannot integrate a judicial exception into a practical application.
“providing the training data to train the machine learning model on (i) a set of training inputs comprising the training input and (ii) a set of target outputs comprising the target output." These/this additional element(s) are/is recited at a high-level of generality such that it amounts to necessary data gathering. As described in MPEP 2106.05(g), limitations that amount to merely adding insignificant extra-solution activity of data gathering to a judicial exception do not amount to significantly more than the judicial exception itself, and cannot integrate a judicial exception into a practical application.
Therefore, the applicant’s argument is not persuasive, the 101 rejection is still maintained.
Applicant’s Argument:
The Claims Integrate Any Alleged Abstract Idea into a Practical Application
Applicant respectfully submits that the claims are not merely directed to an abstract idea but rather integrate any alleged abstract idea into a practical application. As explained in the Specification "[t]he frequency collection of spectral data an estimation of metrology measurement values allows for frequency endpoint monitoring at the process chamber, which prevents the likelihood of under-processing or over-processing of the substrate." (Specification, [0026]). The claims provide a specific technical improvement to substrate manufacturing by enabling accurate endpoint detection through machine learning trained on normalized spectral data. Furthermore, "[t]he particular type of metrology measurement value for the substrate can be selected...as an endpoint metric that indicates the endpoint of the substrate process at a higher accuracy than other endpoint metrics associated with other types of metrology measurement values." (Specification, [0027]). Accordingly, the claims recite a specific technical solution that improves the accuracy of metrology measurements in semiconductor manufacturing, not a mere abstract concept.
Examiner’s Response:
Examiner respectfully disagrees applicant’s argument since the claim limitations are not integrated into the practical application, the claim does not recite the improvement of the machine learning model or the improvement of the technology in the field, as the claim only recite the generic computer component (machine learning model) to train on the normalized spectral data. Therefore, the applicant’s argument is not persuasive, the rejection is still maintained.
Applicant’s Argument :
The Amendments to Claim 1 Further Demonstrate Patent Eligibility
Applicant notes that claim 1 is further amended to recite "storing the trained machine learning model at a memory, wherein the trained machine learning model is configured to predict metrology measurements for the current substrate being processed according to the current process at the first manufacturing system." This feature cannot be performed in the human mind, as a human cannot store a trained machine learning model in computer memory. Storing the trained machine learning model involves specific computer hardware (e.g., memory) to store a specific technical artifact (e.g., a trained machine learning model) for a specific technical purpose (e.g., predicting metrology measurements for substrates being processed at a manufacturing system). Further, this feature integrates any alleged abstract idea into a practical application. The storing operation is not merely generic data storage but rather stores a trained model that is specifically "configured to predict the metrology measurements for the current substrate being processed according to the current process at the first manufacturing system." This reflects a specific technical implementation where the trained model is stored for subsequent use in a real-world manufacturing environment to provide metrology measurements during substrate processing. As described in the Specification and noted above "[t]he frequency collection of spectral data an estimation of metrology measurement values allows for frequency endpoint monitoring at the process chamber, which prevents the likelihood of under-processing or over-processing of the substrate."
Examiner’s Response:
Applicant’s argument regarding the 101-rejection based on the claim amendment, therefore, the further analysis will be provided as detail in the 101 rejection below.
Applicant’s Argument:
Further, independent claim 1 is analogous to the eligible claim in USPTO Subject Matter Eligibility Example 39 (Method for Training a Neural Network for Facial Detection). Example 39's claim was found to be eligible at Step 2A Prong One because "[t]he claim does not recite any of the judicial exceptions enumerated in the 2019 PEG.' (See USPTO Subject Matter Eligibility Example 39 Analysis re. Step 2A - Prong 1). Specifically, the USPTO found that "the claim does not recite a metal process because the steps are not practically performed in the human mind." Like Example 39, claim 1 recites a specific method for training a machine learning model that includes operations that cannot be practically performed in the human mind… Additionally, claim 1 recites "storing the trained machine learning model at a memory, wherein the trained machine learning model is configured to predict the metrology measurements for the current substrate being processed according to the current process at the first manufacturing system." This feature further ties the trained model to a specific technical application in semiconductor manufacturing.
Examiner’s Response:
Examiner respectfully disagrees to applicant’s argument because the applicant’s argument does not provide the detail of how the current claim limitations are related to the example 39, furthermore, the current claim limitations are not integrated into the practical application, as the claim does not recite the improvement of the machine learning model or the improvement of the technology in the field, such as the current claim limitation recite the genetic computer component (machine learning model) to train on the data. Therefore, the current claim and the example 39 are different.
Applicant’s Argument:
Analogy to USPTO Subject Matter Eligibility Example 48
Independent claim 12 is analogous to eligible claims 2 and 3 in USPTO Subject Matter Eligibility Example 48 (Speech Separation). Claim 2 of Example 48 was found eligible because, while it recited abstract ideas (mathematical concepts and mental processes), the claim as a whole integrated the exception into a practical application by improving speech-separation technology. The USPTO found that the claim "reflects theAppli
improvement discussed in the disclosure by reciting details of how the DNN aids in the cluster assignments to correspond to the sources identified in the mixed speech signal, which are then synthesized into separate speech waveforms in the time domain and converted into a mixed speech signal, excluding audio from the undesired source." (See USPTO Subject Matter Eligibility Example 48 Analysis re. Step (f) of claim 2). The claim was found to be "directed to an improvement to existing computer technology or to the technology of speech separation."… Similarly, claim 12 recites receiving spectral data during substrate processing, calculating normalized data values based on wave amplitude differences between an initial step and subsequent steps, providing these values to a trained machine learning model, and extracting metrology measurement data. While some of these steps may involve mathematical concepts, the claim as a whole integrates any such concepts into a practical application by improving semiconductor manufacturing metrology. The claim reflects the improvement by reciting the specific manner of calculating normalized data values (differences between wave amplitudes at an initial step and subsequent steps), providing these to a trained machine learning model, and extracting metrology measurement data with confidence levels. Like Example 48's Claim 2, claim 12 is directed to an improvement to existing technology, specifically, the technology of substrate metrology measurement.
Examiner’s Response:
Examiner respectfully disagrees to applicant’s argument because the applicant’s argument does not provide the detail of how the current claim limitations are related to the example 48, furthermore, the current claim limitations are not integrated into the practical application, as the claim does not recite the improvement of the machine learning model or the improvement of the technology in the field, such as the current claim limitation recite the genetic computer component (machine learning model) to train on the data. Therefore, the current claim and the example 48 are different.
Applicant’s Argument:
Consistency with Ex Parte Desjardins
Claims 1, 12, and 20, and their corresponding dependent claims, are also consistent with the precedential Appeals Review Panel decision in Ex Parte Desjardins, Appeal No. 2024-000567 (PTAB, September 26, 2025, Appeals Review Panel Decision). In
Desjardins, the Appeals Review Panel (ARP) found that claims directed to a method of training a machine learning model were patent eligible because the specification identified improvements as to how the machine learning model itself operates, and the claim reflected those improvements. The ARP credited benefits including reduced storage, reduced system complexity, and preservation of performance attributes as technological improvements. Similarly here, the specification identifies improvements as to how the machine learning model operations, specifically, training the model using normalized spectral data that represents cumulative feature changes from a baseline initial step to correlate spectral amplitude changes with metrology measurements. As highlighted above, the specification explains that this approach "allows for frequency endpoint monitoring at the process chamber, which prevents the likelihood of under-processing or over-processing of the substrate." (Specification, [0026]). The claims reflect these improvements by reciting the specific manner of calculating normalized data values (differences between wave amplitudes at an initial step and subsequent steps), generating training data comprising these normalized values, and storing the trained model configured to predict metrology measurements. As in Desjardins, the claims recite a specific technological solution, training a machine learning model using a particular normalization approach, that providesApplicatio
technological improvements to semiconductor manufacturing metrology, not merely an abstract mathematical concept.
Examiner’s Response:
Examiner respectfully disagrees to applicant’s argument since the current claim limitations are different compare to the example in the “Ex parte Desjardins”, the current claim recites the mental processes are implemented by the genetic computer component, on the other hand, the example in “Ex parte Desjardins” recites the improvement of the technology in the field .
Applicant’s Argument:
Consistency with Ex Parte Carmody
Claims 1, 12, and 20, and their corresponding dependent claims, are also consistent with the recent PTAB decision in Ex Parte Carmody, Appeal 2025-002843 (PTAB, December 31, 2025), which reversed a § 101 rejection of claims directed to AI-based orchestration of marketing strategies.
In Carmody, the Board agreed with the Examiner that the claims recited methods of organizing human activity and mental processes. However, the Board found that the claims recited an improvement in training of models for use by a recommendation engine, and therefore integrated the judicial exception into a practical application at Step 2A, Prong Two.
The Board in Carmody pointed to specific claim language reciting "train at least one of a plurality of modular plug-and-play tactic-specific models using machine learning with a second training dataset comprising labeled feature vectors." The Specification explained that this modular approach enables the model for each tactic to be updated and improved separately and independently from other tactic-specific models.
Examiner’s Response:
Examiner respectfully disagrees to applicant’s argument since the current claim limitations are different compare to the example in the” Ex Parte Carmody ”, the current claim recites the mental processes are implemented by the genetic computer component, on the other hand, the example in “Ex Parte Carmody ” recites the improvement of the technology in the field .
In reference to applicant’s argument regrading rejections under 35 U.S.C. § 103:
Applicant’s Argument:
The applicant’s argument regarding the 103 rejection based on the claim amendment filed on 01/29/2026.
Examiner’s Response:
The applicant’s argument regarding the 103 rejection based on the claim amendment filed on 01/29/2026, however, Yennie further teaches and storing the trained machine learning model at a memory, (Yennie , [Par.0021], “The plurality of trained models are stored, data indicating a characteristic of a substrate to be processed is received, one of the plurality of trained models is selected based on the data, and the selected trained model is passed to the processing system.”).
wherein the trained machine learning model is configured to predict the metrology measurements for the current substrate being processed according to the current process at the first manufacturing system. (Yennie, [Par.0021], “In another aspect, a method of operating a polishing system includes training a plurality of models using a machine learning algorithm to generate a plurality of trained models, each trained model configured to determine a characteristic value of a layer of a substrate based on a monitoring signal from an in-situ monitoring system of a semiconductor processing system. The plurality of trained models are stored, data indicating a characteristic of a substrate to be processed is received, one of the plurality of trained models is selected based on the data, and the selected trained model is passed to the processing system.” And [Par. 0071], “The in-situ monitoring system 70 can be a spectrographic monitoring system as discussed above, although other sensors can be used instead or in addition, such as eddy current monitoring, motor current or torque monitoring, cameras, temperature sensors, etc..” Examiner’s note, the model is trained on the data to predict character of the substrate, wherein the data include the current data.
Yennie in view of Goto further teaches a first normalized data value of the plurality of normalized data values is representing a difference between a baseline wave amplitude at an initial time period of the prior process indicated by the historical spectral data associated with the first step and a first wave amplitude at a first subsequent time period of the prior process indicated by the historical spectral data associated with the first subsequent step, and a second normalized data value representing a difference between the baseline wave amplitude and a second wave amplitude at a second subsequent time period indicated by the historical spectral data associated with the second subsequent step (GOTO, [Par.0050-0052], teaches the claim does not define what is the baseline wave amplitude, therefore, based on the Broadest Reasonable Interpretation, the first wave amplitude at an initial time period is considered as the baseline wave amplitude. Therefore, the Delta P is considered as the a first normalized data value represents a difference between a baseline wave amplitude at an initial time period of the prior process indicated by the historical spectral data associated with the initial step and a second wave amplitude at a first subsequent time period of the prior process indicated by the historical spectral data associated with the first subsequent step. The Delta t is considered as the second normalized data value representing a difference between the baseline wave amplitude and a second wave amplitude at a second subsequent time period indicated by the historical spectral data associated with the second subsequent step);
wherein the first normalized data value represents a change in a substrate feature associated with the prior substrate between the initial time period and the first subsequent time period (GOTO, [0051-0052] teaches the Delta P is considered as the a first normalized data value represents a difference between a first wave amplitude at an initial time period of the prior process indicated by the historical spectral data associated with the initial step and a second wave amplitude at a first subsequent time period of the prior process indicated by the historical spectral data associated with the first subsequent step. Therefore, the P/ first normalized data value represents the change of the spectrum data at the different time period.);
wherein the second normalized data value represents an additional change in the substrate feature between the initial time period and the second subsequent time period (GOTO, [0051-0052] teaches the Delta t is considered as the second normalized data value representing a difference between the first wave amplitude and a third wave amplitude at a second subsequent time period indicated by the historical spectral data associated with the second subsequent step, therefore, the delta t/second normalized data value representing the change of the spectrum data at the different time period.
Therefore, the applicant’s argument is not persuasive, the rejection is still maintained.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1, 3-7, 9-12, 15-18, 20-21 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1 analysis:
In the instant case, the claims are directed to a method (claims 1-11), system (claims 12-19, 21) and Non-transitory computer readable medium (claim 20). Thus, each of the claims falls within one of the four statutory categories (i.e., process, machine, manufacture, or composition of matter).
Step 2A analysis:
Based on the claims being determined to be within of the four categories (Step 1), it must be determined if the claims are directed to a judicial exception (i.e., law of nature, natural phenomenon, and abstract idea), in this case the claims fall within the judicial exception of an abstract idea. Specifically, the abstract idea of “Mental Processes/Concepts performed in the human mind (including an observation, evaluation, judgment, opinion)”.
The claim 1 recites :
Step 2A: prong 1 analysis:
“obtaining a plurality of historical spectral data” this is amental process, the human mind can obtain/receive the plurality set of spectra data (Observation)
“ identifying, from the plurality of historical spectral data, first historical spectral data associated with the initial step, the first subsequent step, and the second subsequent step”, this is a mental process, human can identify the first historical data associate with the initial step (Observation/Evaluation).
“generating training input”, this is a mental process, the human mind can generate the training data and training input (Observation).
-“providing the training data” This is a mental process, the human mind can providing the particular type of data, such as the training data, (Observation/Evaluation).
a) Step 2A: Prong 2 analysis:
-“the method for training a machine learning model to provide metrology measurements for a current substrate being processed according to a current process at a first manufacturing system,” This/these limitation is/are recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component (See MPEP 2106.05(f)).
-“calculating a plurality of normalized data values based on the identified historical spectral data associated with the initial step, the first subsequent step, and the second subsequent step, wherein each of the plurality of normalized data values comprises: a first normalized data value of the plurality of normalized data values is representing a difference between a baseline wave amplitude at an initial time period of the prior process indicated by the historical spectral data associated with the first step and a first wave amplitude at a first subsequent time period of the prior process indicated by the historical spectral data associated with the first subsequent step, wherein the first normalized data value represents a change in a substrate feature associated with the prior substrate between the initial time period and the first subsequent time period, and a second normalized data value representing a difference between the baseline wave amplitude and a second wave amplitude at a second subsequent time period indicated by the historical spectral data associated with the second subsequent step, wherein the second normalized data value represents and additional change in the substrate feature between the initial time period and the second subsequent time period”, “historical spectral data associated with a prior substrate processed at a second manufacturing system according to a prior process, wherein the plurality of historical spectral data comprises historical spectral data collected for a region of the prior substrate during each of a plurality of steps of the prior process, the plurality of steps comprising an initial step, a first subsequent step, and a second subsequent step;”, “wherein generating the training data comprises: generating a training input comprising at least a comprising the target output” This/these limitation(s) is/are amount to no more than generally linking the use of a judicial exception to a particular technological environment or field of use. As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not amount to significantly more than the exception itself, and cannot integrate a judicial exception into a practical application.
-“generating a target output for the training input” These/this additional element(s) are/is recited at a high-level of generality such that it amounts to necessary data outputting. As described in MPEP 2106.05(g), limitations that amount to merely adding insignificant extra-solution activity of data outputting to a judicial exception do not amount to significantly more than the judicial exception itself, and cannot integrate a judicial exception into a practical application.
-“And providing the training data to train the machine learning model on (i) a set of training inputs comprising the training input and (ii) a set of target outputs comprising the target output.” These/this additional element(s) are/is recited at a high-level of generality such that it amounts to necessary data gathering. As described in MPEP 2106.05(g), limitations that amount to merely adding insignificant extra-solution activity of data gathering to a judicial exception do not amount to significantly more than the judicial exception itself, and cannot integrate a judicial exception into a practical application.
-“and storing the trained machine learning model at a memory,” These/this additional element(s) are/is recited at a high-level of generality such that it amounts to necessary data storing. As described in MPEP 2106.05(g), limitations that amount to merely adding insignificant extra-solution activity of data storing to a judicial exception do not amount to significantly more than the judicial exception itself, and cannot integrate a judicial exception into a practical application.
-“a machine learning model” “ to train the machine learning model on (i) a set training inputs…and (ii) a set of target outputs …”, “wherein the trained machine learning model is configured to predict the metrology measurements for the current substrate being processed according to the current process at the first manufacturing system.” This/these limitation is/are recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component (See MPEP 2106.05(f)).
b) Step 2B analysis:
-“the method for training a machine learning model to provide metrology measurements for a current substrate being processed according to a current process at a first manufacturing system,” This/these limitation is/are recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component (See MPEP 2106.05(f)).
-“calculating a plurality of normalized data values based on the identified historical spectral data associated with the initial step, the first subsequent step, and the second subsequent step, wherein each of the plurality of normalized data values comprises: a first normalized data value of the plurality of normalized data values is representing a difference between a baseline wave amplitude at an initial time period of the prior process indicated by the historical spectral data associated with the first step and a first wave amplitude at a first subsequent time period of the prior process indicated by the historical spectral data associated with the first subsequent step, wherein the first normalized data value represents a change in a substrate feature associated with the prior substrate between the initial time period and the first subsequent time period, and a second normalized data value representing a difference between the baseline wave amplitude and a second wave amplitude at a second subsequent time period indicated by the historical spectral data associated with the second subsequent step, wherein the second normalized data value represents and additional change in the substrate feature between the initial time period and the second subsequent time period”, “historical spectral data associated with a prior substrate processed at a second manufacturing system according to a prior process, wherein the plurality of historical spectral data comprises historical spectral data collected for a region of the prior substrate during each of a plurality of steps of the prior process, the plurality of steps comprising an initial step, a first subsequent step, and a second subsequent step;”, “wherein generating the training data comprises: generating a training input comprising at least a value associated with the particular type of metrology measurement;”, “a set training inputs comprising the training input and (ii) a set of target outputs comprising the target output” This/these limitation(s) is/are amount to no more than generally linking the use of a judicial exception to a particular technological environment or field of use. As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not amount to significantly more than the exception itself.
-“generating a target output for the training input” These/this limitation(s) are/is recited at a high-level of generality such that it amounts to necessary data outputting. As described in MPEP 2106.05(g), limitations that amount to merely adding insignificant extra-solution activity of data outputting to a judicial exception do not amount to significantly more than the judicial exception itself.
The courts have similarly found limitations directed to displaying a result, recited at a high level of generality, to be well-understood, routine, and conventional. See (MPEP 2106.05(d)(II), "presenting offers and gathering statistics.", “determining an estimated outcome and setting a price”).
-“And providing the training data to train the machine learning model on (i) a set of training inputs comprising the training input and (ii) a set of target outputs comprising the target output.” These/this limitation(s) are/is recited at a high-level of generality such that it amounts to necessary data gathering. As described in MPEP 2106.05(g), limitations that amount to merely adding insignificant extra-solution activity of data gathering to a judicial exception do not amount to significantly more than the judicial exception itself.
The courts have found limitations directed to obtaining information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
-“and storing the trained machine learning model at a memory,” These/this limitation(s) are/is recited at a high-level of generality such that it amounts to necessary data storing. As described in MPEP 2106.05(g), limitations that amount to merely adding insignificant extra-solution activity of data storing to a judicial exception do not amount to significantly more than the judicial exception itself.
The courts have found limitations directed to obtaining information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
-“a machine learning model” “ to train the machine learning model on (i) a set training inputs…and (ii) a set of target outputs …”, “wherein the trained machine learning model is configured to predict the metrology measurements for the current substrate being processed according to the current process at the first manufacturing system.” This/these limitation is/are recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component (See MPEP 2106.05(f)).
The claim 3 recites:
Step 2A: prong 1 analysis:
-“wherein generating the training input” this is a mental process, the human mind can generating the training input (Observation),
-“determining a spectral feature associated with the particular type of metrology measurement” this is a mental process, the human mind can determine the spectral feature associated with particular type of the measurement, (Observation/Evaluation).
-“identifying, from the plurality normalized data values calculated for each of the plurality of steps of the prior process, respective historical spectral data comprising the indication of a historical spectral feature that corresponds to the determined spectral feature” this is a mental process, the human mind can identify the from the normalized data value, a respective historical spectral data (Observation/evaluation).
a) Step 2A: Prong 2 analysis:
- Training input comprising at least the normalized set of historical spectral data comprises”, “historical spectral data comprising the indication of a historical spectral feature that corresponds to the determined spectral feature and including the identified respective historical spectral data in the normalized set of historical spectral data” This/these limitation(s) is/are amount to no more than generally linking the use of a judicial exception to a particular technological environment or field of use. As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception and that it does not integrate the judicial exception into a practical application.
b) Step 2B analysis:
- “historical spectral data comprising the indication of a historical spectral feature that corresponds to the determined spectral feature and including the identified respective historical spectral data in the normalized set of historical spectral data” This/these limitation(s) is/are amount to no more than generally linking the use of a judicial exception to a particular technological environment or field of use. As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not amount to significantly more than the exception itself.
The claim 4 recites:
Step 2A: prong 1 analysis:
a) Step 2A: Prong 2 analysis:
- “the spectral feature associated with the particular type of metrology measurement corresponds to a portion of a substrate surface comprising a profile pattern that is distinct from profile patterns of other portions of the substrate surface” These/this limitation(s) amounts to no more than generally linking the use of a judicial exception to a particular technological environment or field of use. As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not amount to significantly more than the exception itself, and cannot integrate a judicial exception into a practical application.
b) Step 2B analysis:
- “the spectral feature associated with the particular type of metrology measurement corresponds to a portion of a substrate surface comprising a profile pattern that is distinct from profile patterns of other portions of the substrate surface” This/these limitation(s) is/are amount to no more than generally linking the use of a judicial exception to a particular technological environment or field of use. As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not amount to significantly more than the exception itself.
The claim 5 recites:
Step 2A: prong 1 analysis:
- “and selecting, from historical spectral data collected for the calibration substrate, one or more spectral features associated with the identified portion of the surface of the calibration substrate” this is a mental process, the human mind can select the one or more particular type of feature from the data set (historical spectral data), (Observation/Evaluation).
-“identifying, based on an outcome of the two-dimensional scan, a portion of the surface of the calibration substrate that comprise the profile pattern that is distinct from profile patterns of the other portions of the surface” This is a mental process, the human can identify the distinct the profile patterns of one portion of the surface with other portion of the surface (Observation/Evaluation).
a) Step 2A: Prong 2 analysis:
The claim recites additional limitation “performing a two-dimensional scan for a surface of a calibration substrate processed” These/this limitation(s) amounts to no more than generally linking the use of a judicial exception to a particular technological environment or field of use. As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not amount to significantly more than the exception itself, and cannot integrate a judicial exception into a practical application.
b) Step 2B analysis:
The claim recites additional limitation “performing a two-dimensional scan for a surface of a calibration substrate processed” T This/these limitation(s) is/are amount to no more than generally linking the use of a judicial exception to a particular technological environment or field of use. As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not amount to significantly more than the exception itself.
The claim 6 recites:
a) Step 2A: Prong 2 analysis:
-“ wherein the spectral feature associated with the particular type of metrology measurement corresponds to a range of spectral wavelengths that are determined to indicate a metrology measurement value associated with the particular type of metrology measurement that has a higher degree of accuracy than other spectral wavelengths that are outside of the range of spectral wavelengths.” This limitation is amount to no more than generally linking the use of a judicial exception to a particular technological environment or field of use. As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not amount to significantly more than the exception itself, and cannot integrate a judicial exception into a practical application.
b) Step 2B analysis:
-“ wherein the spectral feature associated with the particular type of metrology measurement corresponds to a range of spectral wavelengths that are determined to indicate a metrology measurement value associated with the particular type of metrology measurement that has a higher degree of accuracy than other spectral wavelengths that are outside of the range of spectral wavelengths.” This/these limitation(s) is/are amount to no more than generally linking the use of a judicial exception to a particular technological environment or field of use. As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not amount to significantly more than the exception itself.
The claim 7 recites:
Step 2A: prong 1 analysis:
-“provide spectral wavelengths that indicate the metrology measurement value associated with the particular type of metrology measurement that has a higher degree of accuracy than the other spectral wavelengths;” this is a mental process, the human can provide the spectral wavelength that indicate the metrology measurement value of one particular measurement which has a higher degree than other spectral wavelength (Observation/Evaluation).
-“and extract, from the one or more outputs, the range of spectral wavelengths” this is a mental process, the human mind can extract the range of spectral wavelengths based on one or more outputs, (Observation/Evaluation).
a) Step 2A: Prong 2 analysis:
-“providing one or more portions of the plurality of historical spectral data as input to a wave analysis model trained, “ obtain one or more outputs of the wave analysis model”, This/these limitation is/are recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component (See MPEP 2106.05(f)).
b) Step 2B analysis:
-“providing one or more portions of the set of historical spectral data as input to a wave analysis model trained, “ obtain one or more outputs of the wave analysis model”, This/these limitation is/are recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component (See MPEP 2106.05(f)).
The claim 9 recites:
a) Step 2A: Prong 2 analysis:
-“wherein the first manufacturing system is the same as the second manufacturing system” These/this limitation(s) are/is amount to more than generally linking the use of a judicial exception to a particular technological environment or field of use. As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not amount to significantly more than the exception itself, and cannot integrate a judicial exception into a practical application.
b) Step 2B analysis:
-“wherein the first manufacturing system is the same as the second manufacturing system” This/these limitation(s) is/are amount to no more than generally linking the use of a judicial exception to a particular technological environment or field of use. As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not amount to significantly more than the exception itself.
The claim 10 recites
Step 2A: prong 1 analysis:
a) Step 2A: Prong 2 analysis:
-“wherein the prior process comprises at least one of an etch process or a deposition process” These/this limitation(s) amount to no more than generally linking the use of a judicial exception to a particular technological environment or field of use. As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not amount to significantly more than the exception itself, and cannot integrate a judicial exception into a practical application.
b) Step 2B analysis:
-“wherein the prior process comprises at least one of an etch process or a deposition process” This/these limitation(s) is/are amount to no more than generally linking the use of a judicial exception to a particular technological environment or field of use. As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not amount to significantly more than the exception itself.
The claim 11 recites
a) Step 2A: Prong 2 analysis:
-“wherein the particular type of metrology measurement comprises at least one of: a thickness of a prior film deposited on a surface of the prior substrate after performance of the prior process, a property of one or more features etched into the prior film after the performance of the prior process, a rate of the performance of the prior process, or a uniformity of the rate of the performance of the prior process. These/this limitation(s) amount to no more than generally linking the use of a judicial exception to a particular technological environment or field of use. As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not amount to significantly more than the exception itself, and cannot integrate a judicial exception into a practical application.
b) Step 2B analysis:
-“wherein the particular type of metrology measurement comprises at least one of: a thickness of a prior film deposited on a surface of the prior substrate after performance of the prior process, a property of one or more features etched into the prior film after the performance of the prior process, a rate of the performance of the prior process, or a uniformity of the rate of the performance of the prior process. This/these limitation(s) is/are amount to no more than generally linking the use of a judicial exception to a particular technological environment or field of use. As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not amount to significantly more than the exception itself.
The claim 12 recites
Step 2A: prong 1 analysis:
“ identifying, from the plurality of historical spectral data, first historical spectral data associated with an initial step of the plurality of steps”, this is a mental process, human can identify the first historical data associate with the initial step (Observation/Evaluation).
-“ obtain one or more outputs” this is a mental process, the human mind can obtain the output (Observation/Evaluation)
-“and extract, from the one or more outputs, metrology measurement data identifying one or more metrology measurement values associated with the particular type of metrology measurement, the one or more metrology measurement values obtained for a prior substrate processed at the manufacturing system according to a prior process, and an indication of a level of confidence that each of the one or more metrology measurement values corresponds to the current substrate.” this is a mental process, the human mind can extract/identify the metrology measurement values associated with the particular type of metrology measurement based on the obtained data (output data), furthere more, the human can determine/indicate the level of confidence of each metrology measurement values of the current substrate,(Observation/Evaluation).
a) Step 2A: Prong 2 analysis:
-“ to store a trained machine learning model;” limitation(s) are/is recited at a high-level of generality such that it amounts to necessary data storing. As described in MPEP 2106.05(g), limitations that amount to merely adding insignificant extra-solution activity of data storing to a judicial exception do not amount to significantly more than the judicial exception itself, and cannot integrate a judicial exception into a practical application.
- “receive, during a current process performed for a current substrate at a manufacturing system, a plurality of spectral data associated with the current substrate”, limitation(s) are/is recited at a high-level of generality such that it amounts to necessary data gathering. As described in MPEP 2106.05(g), limitations that amount to merely adding insignificant extra-solution activity of data gathering to a judicial exception do not amount to significantly more than the judicial exception itself, and cannot integrate a judicial exception into a practical application.
-“Memory”, “ and a set of one or more processing devices coupled to the memory, the set of one or more processing devices”, “provide, as input to the trained machine learning model”, The additional limitation is recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component (See MPEP 2106.05(f)).
-“calculating a plurality of normalized data values based on the identified spectral data and the identified additional spectral data, wherein the plurality of normalized data values comprises: a first normalized data value of the plurality of normalized data values is representing a difference between a baseline wave amplitude at an initial time period of the prior process indicated by the historical spectral data associated with the first step and a first wave amplitude at a first subsequent time period of the prior process indicated by the historical spectral data associated with the first subsequent step, wherein the first normalized data value represents a change in a substrate feature associated with the prior substrate between the initial time period and the first subsequent time period, and a second normalized data value representing a difference between the baseline wave amplitude and a second wave amplitude at a second subsequent time period indicated by the historical spectral data associated with the second subsequent step, wherein the second normalized data value represents and additional change in the substrate feature between the initial time period and the second subsequent time period””, “ wherein the received plurality of spectral data is associated with a current step of the current process”, “and wherein a second normalized data value of the plurality of normalized data values represents a difference between the identified data associated with the initial step and respective historical spectral data collected during the current step of the current process”, “a normalized set of spectral data comprising the calculated normalized data value”, “wherein the normalized set of spectral data comprises an indication of one or more spectral features corresponding to a particular type of metrology measurement” These/this limitation(s) amount to no more than generally linking the use of a judicial exception to a particular technological environment or field of use. As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not amount to significantly more than the exception itself, and cannot integrate a judicial exception into a practical application.
-“to the trained machine learning model” This is generic machine learning because 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).
b) Step 2B analysis:
-“ to store a trained machine learning model;” These/this limitation(s) are/is recited at a high-level of generality such that it amounts to necessary data storing. As described in MPEP 2106.05(g), limitations that amount to merely adding insignificant extra-solution activity of data storing to a judicial exception do not amount to significantly more than the judicial exception itself .
The courts have found limitations directed to obtaining information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory")
“receive, during a current process performed for a current substrate at a manufacturing system, a plurality of spectral data associated with the current substrate”, These/this limitation(s) are/is recited at a high-level of generality such that it amounts to necessary data gathering. As described in MPEP 2106.05(g), limitations that amount to merely adding insignificant extra-solution activity of data gathering to a judicial exception do not amount to significantly more than the judicial exception itself .
The courts have found limitations directed to obtaining information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory")
--“Memory”, “ and a set of one or more processing devices coupled to the memory, the set of one or more processing devices”, “provide, as input to the trained machine learning model” The additional limitation is recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component (See MPEP 2106.05(f)).
-“calculating a plurality of normalized data values based on the identified spectral data and the identified additional spectral data, wherein the plurality of normalized data values comprises: a first normalized data value of the plurality of normalized data values is representing a difference between a baseline wave amplitude at an initial time period of the prior process indicated by the historical spectral data associated with the first step and a first wave amplitude at a first subsequent time period of the prior process indicated by the historical spectral data associated with the first subsequent step, wherein the first normalized data value represents a change in a substrate feature associated with the prior substrate between the initial time period and the first subsequent time period, and a second normalized data value representing a difference between the baseline wave amplitude and a second wave amplitude at a second subsequent time period indicated by the historical spectral data associated with the second subsequent step, wherein the second normalized data value represents and additional change in the substrate feature between the initial time period and the second subsequent time period””, “ wherein the received plurality of spectral data is associated with a current step of the current process”, “and wherein a second normalized data value of the plurality of normalized data values represents a difference between the identified data associated with the initial step and respective historical spectral data collected during the current step of the current process”, “a normalized set of spectral data comprising the calculated normalized data value”, “wherein the normalized set of spectral data comprises an indication of one or more spectral features corresponding to a particular type of metrology measurement” This/these limitation(s) is/are amount to no more than generally linking the use of a judicial exception to a particular technological environment or field of use. As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not amount to significantly more than the exception itself.
-“to the trained machine learning model” The additional limitation is recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component (See MPEP 2106.05(f)).
Regarding claim 15 is rejected for the same reason as the claim 3, because these claims recite the same limitations.
The claim 16 recites
a) Step 2A: Prong 2 analysis:
-“wherein the spectral feature associated with the particular type of metrology measurement corresponds to a portion of a surface of the current substrate that is expected to, at an endpoint of the current process, comprise a profile pattern that is distinct from profile patterns of other portions of the substrate surface.” These/this limitation(s) amount to no more than generally linking the use of a judicial exception to a particular technological environment or field of use. As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not amount to significantly more than the exception itself, and cannot integrate a judicial exception into a practical application.
b) Step 2B analysis:
-“wherein the spectral feature associated with the particular type of metrology measurement corresponds to a portion of a surface of the current substrate that is expected to, at an endpoint of the current process, comprise a profile pattern that is distinct from profile patterns of other portions of the substrate surface.” This/these limitation(s) is/are amount to no more than generally linking the use of a judicial exception to a particular technological environment or field of use. As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not amount to significantly more than the exception itself.
Regarding claim 17 is rejected for the same reason as the claim 6, because these claims recite the same limitations.
Regarding claim 18 is being rejected for the same reason as the claim 11, because these claims recite the same limitations.
Regarding claim 20 is for the same reason as the claim 12, because these claims recite the same limitations.
The claim 21 recites :
Step 2A: prong 1 analysis:
“modify at least one of the current process performed for the current substrate or a future process performed for the future substrate based on the extracted metrology measurement data.” this is a mental process, the human mind can modify the process based on the extract metrology measurement data (Observation/Evaluation) .
a) Step 2A: Prong 2 analysis:
-“ the set of one or more processing devices” The additional limitation is recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component to perform the mental process (See MPEP 2106.05(f)).
b) Step 2B analysis:
-“ the set of one or more processing devices” The additional limitation is recited at high level of generality and amounts to no more than mere instructions to apply the judicial exception using a generic computer component to perform the mental process (See MPEP 2106.05(f)).
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1, 3, 9, 10, 12, 15, 20, 21 are rejected under 35 U.S.C. 103 as being unpatentable over Yennie et al. (Pub. No. US20190286111– hereinafter, Yennie) and further in view of GOTO et al . (Pub. No. US 20130169958-hereinafter, GOTO) .
Regarding claim 1, Yennie teaches a method for training a machine learning model to provide metrology measurements for a current substrate being processed according to a current process at a first manufacturing system, the method comprising: (Yennie, [Abstract], “method of operating a polishing system includes training a plurality of models using a machine learning algorithm to generate a plurality of trained models, each trained model configured to determine a characteristic value of a layer of a substrate based on a monitoring signal from an in-situ monitoring system of a semiconductor processing system” Examiner’s note, the characteristic value of a layer of a substrate is considered as the metrology measurement, the polishing system is considered as the first manufacturing system),
obtaining a plurality of historical spectral data associated with a prior substrate processed at a second manufacturing system according to a prior process, (Yennie, [par.0008], “Each set of training data includes a plurality of training spectra, a timestamp for each training spectrum from the plurality of training spectra, and a starting characterizing value and/or an ending characterizing value for the plurality of training spectra. Each machine learning model provides at least one different hyperparameter. Each physical process model provides a different function to generate characterizing values as a different function of time and/or a different physical process parameter. The characterizing value is calculated based on the timestamp for the training spectrum, the starting characterizing value and/or ending characterizing value for the set of training data, and the selected physical process model.” and [par.0014], “A plurality of training spectra generated during polishing of the training substrate and a timestamp for each training spectrum from the plurality of training spectra is received, for each training substrate, from the in-situ monitoring system of one or more of the plurality of polishing systems used to polish the training substrate. The starting characterizing value and/or an ending characterizing value for the training substrate is received, for each training substrate, from the in-line or stand-alone metrology system. A plurality of sets of training data is stored. Each set of training data includes the plurality of training spectra from the training substrate, the timestamp for each training spectrum from the plurality of training spectra, and the starting characterizing value and/or an ending characterizing value for the training substrate.”, Examiner’s note, the training spectra is considered as the historical spectral data associated with the prior substrate process. The training substrate is considered as the prior substrate process because the training data includes the training substrates data received from one or more of plurality of polishing systems, the one or more of polishing systems include first and second polishing systems (manufacturing systems). Therefore, the training data (training substrates data) is also received from second polishing system (another polishing systems/second manufacturing systems) .).
wherein the plurality of historical spectral data comprises historical spectral data collected for a region of the prior substrate during each of a plurality of steps of the prior process (Yennie, [par.0008], “Each set of training data includes a plurality of training spectra, a timestamp for each training spectrum from the plurality of training spectra, and a starting characterizing value and/or an ending characterizing value for the plurality of training spectra. Each machine learning model provides at least one different hyperparameter. Each physical process model provides a different function to generate characterizing values as a different function of time and/or a different physical process parameter. The characterizing value is calculated based on the timestamp for the training spectrum, the starting characterizing value and/or ending characterizing value for the set of training data, and the selected physical process model.” and [par.0014], “A plurality of training spectra generated during polishing of the training substrate and a timestamp for each training spectrum from the plurality of training spectra is received, for each training substrate, from the in-situ monitoring system of one or more of the plurality of polishing systems used to polish the training substrate. The starting characterizing value and/or an ending characterizing value for the training substrate is received, for each training substrate, from the in-line or stand-alone metrology system. A plurality of sets of training data is stored. Each set of training data includes the plurality of training spectra from the training substrate, the timestamp for each training spectrum from the plurality of training spectra, and the starting characterizing value and/or an ending characterizing value for the training substrate.”);
identifying, from the plurality of historical spectral data, (Yennie, [Par.0037], “As another issue, the raw data obtained from various tools in the semiconductor fabrication plant might not include a characterizing value for each measurement. For example, an in-situ optical monitoring system in a processing tool could be used to generate a sequence of spectra to be used as training data. However, the only ground truth measurement available may be the starting and/or ending thickness obtained from an in-line or stand-alone metrology system. The starting and/or ending thickness would be associated with the first and/or last spectrum in the sequence” Examiner’s note, identifying/calculating the staring characterizing value for each of training data set, therefore, the training data associated with the staring characterizing value, which is considered as the first historical spectral data ( first spectrum in the sequence). The first historical spectral data collected from the initial step of prior process.);
generating training data for the machine learning model, wherein generating the training data comprises generating a training input comprising at least a normalized set of the historical spectral data (Yennie, [Par.0014], “For each training spectrum in each set of training data, a characterizing value is calculated based on the timestamp for the training spectrum, the starting characterizing value and/ or ending characterizing value for the set of training data, the physical parameter value, and the selected physical process model, thereby generating a plurality of training characterizing values with each training characterizing value associated with one of the plurality of training spectra. The implemented machine learning model is trained using the plurality of training characterizing values and plurality of training spectra to generate a trained machine learning model, and the trained machine learning model is passed to the controller of the one or more polishing systems for control of polishing of the device substrates.” Examiner’s note, the machine learning model is trained using the plurality of training characterizing value and plurality of training spectra (input), wherein, each training spectral is associated with the characterizing values, therefore, the training spectral (training input) comprising the set of normalized value (first and characterizing valua).),
wherein the normalized set of historical spectral data comprises an indication of one or more historical spectral features associated with a particular type of metrology measurement (Yennie, [Par.0014], “For each training spectrum in each set of training data, a characterizing value is calculated based on the timestamp for the training spectrum, the starting characterizing value and/ or ending characterizing value for the set of training data, the physical parameter value, and the selected physical process model, thereby generating a plurality of training characterizing values with each training characterizing value associated with one of the plurality of training spectra. The implemented machine learning model is trained using the plurality of training characterizing values and plurality of training spectra to generate a trained machine learning model, and the trained machine learning model is passed to the controller of the one or more polishing systems for control of polishing of the device substrates.” And [Par.0066-0068], “However, neural network 120 may optionally include one or more other input nodes (e.g., node 122a) to receive other data. This other data could be from a prior measurement of the substrate by the in-situ monitoring system, e.g., spectra collected from earlier in the processing of the substrate, from a measurement of a prior substrate, e.g., spectra collected during processing of another substrate, from another sensor in the polishing system, e.g., a measurement of temperature of the pad or substrate by a temperature sensor, from a polishing recipe stored by the controller that is used to control the polishing system, e.g., a polishing parameter such as carrier head pressure or platen rotation rate use for polishing the substrate, from a variable tracked by the controller, e.g., a number of substrates since the pad was changed, or from a sensor that is not part of the polishing system, e.g., a measurement of a thickness of an underlying films by a metrology station. This permits the neural network 120 to take into account these other processing or environmental variables in calculation of the characterizing value…[0068] As part of a configuration procedure for the dimensional reduction module 110, the controller 90 can receive a plurality of reference spectra and a characterizing value, e.g., thickness, associated with each reference spectrum of the plurality of reference spectra. For example, reference spectra can be measured at particular locations on one or more test substrates. In addition, measurements of the thickness at the particular locations can be performed with metrology equipment, e.g., a contact profilometer or ellipsometer. A thickness measurement can thus be associated with the reference spectrum from the same location on a substrate. The plurality of reference spectra can include, for example, five to ten reference spectra.” And [Par.0076-0077], “In particular, the algorithm generation platform 18 can receive and store a plurality of sets of training data in the data store 18a. Each set of training data can correspond to a single processing operation on a single substrate. The substrate can be a substrate intentionally used for training, or a device substrate being monitoring in the usual course of fabrication of integrated circuits and for which a starting thickness value and/or an ending thickness value were measured by the metrology system.[0077] For example, as or after a polishing system 20 polishes a substrate and the metrology system 14 measures the layer thickness of the substrate, data can be collected to form a set of training data. The collected data can include the spectra measured during polishing, the time in the polishing operation at which the spectrum was measured (a “timestamp”), and the ground truth measurement(s) made by metrology system. Thus, each set of training data can include a plurality of training spectra as measured by the spectrographic monitoring system, a timestamp for each training spectrum from the plurality of training spectra, and a starting thickness value and/or an ending thickness value for the plurality of training spectra.” Examiner’s note, the spectral data set (each training dataset) associates with the normalized characterizing values. The normalized characterizing values indicates the starting thickness value and/or an ending thickness value for the plurality of training spectra, therefore, the thickness of the layer are considered as the historical spectral features associate with the particular type of the metrology measurement data (thickness measurement)) ;
and generating a target output for the training input, wherein the target output comprises a historical metrology measurement value for the prior substrate (Yennie, [Par: 0096-0098], “Once the physical process model builder 18d has received the selection of the type of physical process model and, if necessary, any process parameter values, the physical process model builder 18d can calculate a characteristic value, e.g., a thickness value, for each training spectrum that does not already have a characteristic value. That is, the various values, e.g., timestamp of the training spectrum, starting value, and ending value, are fed into the physical process model, which calculates a characteristic value for that training spectrum. [0097] Once an instance of the physical process model has been created, the physical process model can be used to generate a characteristic value, e.g., a thickness value, for each training spectrum in the training data that does not already have a characterizing value. Training can be performed by the model trainer application 18f using conventional techniques. For example, for a neural network, training can be performed by backpropagation using the sequence of measurements and the characteristic values generated by the physical process model. For example, for training of a neural network can be performed by backpropagation using the sequence of spectra and the characteristic values, e.g., thickness values, generated by the polishing process model. [0098] Once the training has been performed, the trained instantiation of the machine learning model can be passed to the process control system, which can then use the trained machine learning model as described above.” Examiner’s note, using the machine learning model to train on the training data to measure the thickness of the layer of the training data (historical spectral data), the thickness value is considered as the target output comprises a historical metrology measurement value for the prior substrate.”),
the historical metrology measurement value associated with the particular type of metrology measurement (Yennie, [Par.0058], “The characterizing value is typically the thickness of the outer layer, but can be a related characteristic such as thickness removed. In addition, the characterizing value can be a more generic representation of the progress of the substrate through the polishing process, e.g., an index value representing the time or number of platen rotations at which the measurement would be expected to be observed in a polishing process that follows a predetermined progress.”, Examiner’s note, the characterizing values is the thickness measurement of the layer, therefore, the thickness is considered as the particular type of metrology measurement. );
and providing the training data to train the machine learning model on (i) a set of training inputs comprising the training input and (ii) a set of target outputs comprising the target output (Yennie, [Par.0077], “For example, as or after a polishing system 20 polishes a substrate and the metrology system 14 measures the layer thickness of the substrate, data can be collected to form a set of training data. The collected data can include the spectra measured during polishing, the time in the polishing operation at which the spectrum was measured (a “timestamp”), and the ground truth measurement(s) made by metrology system. Thus, each set of training data can include a plurality of training spectra as measured by the spectrographic monitoring system, a timestamp for each training spectrum from the plurality of training spectra, and a starting thickness value and/or an ending thickness value for the plurality of training spectra.” Examiner’s note, the measurement values are generated by training the machine learning model on the training data (input), therefore, the ground truth measurement values are considered as the set of target outputs.).
and storing the trained machine learning model at a memory, (Yennie , [Par.0021], “The plurality of trained models are stored, data indicating a characteristic of a substrate to be processed is received, one of the plurality of trained models is selected based on the data, and the selected trained model is passed to the processing system.”).
wherein the trained machine learning model is configured to predict the metrology measurements for the current substrate being processed according to the current process at the first manufacturing system. (Yennie, [Par.0021], “In another aspect, a method of operating a polishing system includes training a plurality of models using a machine learning algorithm to generate a plurality of trained models, each trained model configured to determine a characteristic value of a layer of a substrate based on a monitoring signal from an in-situ monitoring system of a semiconductor processing system. The plurality of trained models are stored, data indicating a characteristic of a substrate to be processed is received, one of the plurality of trained models is selected based on the data, and the selected trained model is passed to the processing system.” And [Par. 0071], “The in-situ monitoring system 70 can be a spectrographic monitoring system as discussed above, although other sensors can be used instead or in addition, such as eddy current monitoring, motor current or torque monitoring, cameras, temperature sensors, etc..”
However, Yennie does not teach, the plurality of steps comprising an initial step, a first subsequent step, and a second subsequent step; historical spectral data associated with the initial step, the first subsequent step, and the second subsequent step; calculating a plurality of normalized data values based on the identified historical spectral data associated with the initial step, the first subsequent step, and the second subsequent step, wherein the plurality of normalized data values comprises: a first normalized data value of the plurality of normalized data values is representing a difference between a baseline wave amplitude at an initial time period of the prior process indicated by the historical spectral data associated with the first step and a first wave amplitude at a first subsequent time period of the prior process indicated by the historical spectral data associated with the first subsequent step, wherein the first normalized data value represents a change in a substrate feature associated with the prior substrate between the initial time period and the first subsequent time period, and a second normalized data value representing a difference between the baseline wave amplitude and a second wave amplitude at a second subsequent time period indicated by the historical spectral data associated with the second subsequent step, wherein the second normalized data value represents anadditional change in the substrate feature between the initial time period and the second subsequent time period;
On the other hand, GOTO teaches the plurality of steps comprising an initial step, a first subsequent step, and a second subsequent step (GOTO, [Par.0051. .Fig.3, Fig.4], “For example, when the measurement of the hole depth is initiated simultaneously with the beginning of etching, the data processor 4 acquires spectrum data covering a predetermined wavelength range obtained by the array detector 32 of the light-dispersing unit 3 at a predetermined point in time, and stores the data in the spectrum memory 41 (Step S1). The spectrum data is repeatedly acquired at predetermined intervals of time .DELTA.p by Steps S1 and S7 until it is determined in Step S6 that the measurement has been completed. In the present example, .DELTA.p is set at one third of .DELTA.t, which will be mentioned later, However, its value is not limited to this example.” Examiner’s note, each of the Delta p, Delta t are different spectrum data are calculated at the time priors, such as P1, P2 and P4) ;
historical spectral data associated with the initial step, the first subsequent step, and the second subsequent step (GOTO, [Par.0051. 0052. Fig.4], “0051, For example, when the measurement of the hole depth is initiated simultaneously with the beginning of etching, the data processor 4 acquires spectrum data covering a predetermined wavelength range obtained by the array detector 32 of the light-dispersing unit 3 at a predetermined point in time, and stores the data in the spectrum memory 41 (Step S1). The spectrum data is repeatedly acquired at predetermined intervals of time .DELTA.p by Steps S1 and S7 until it is determined in Step S6 that the measurement has been completed. In the present example, .DELTA.p is set at one third of .DELTA.t, which will be mentioned later, However, its value is not limited to this example.” And “0052, After a spectrum data is acquired in Step S1, the difference spectrum calculator 42 determines whether or not a spectrum data obtained at a point in time earlier than the current point in time by .DELTA.t is stored in the spectrum memory 41 (Step S2). If no such data is stored, the optical distance calculation process (which will be described later) cannot be performed, so that the operation proceeds to Step S7. As the acquisition and storage of spectrum data are repeated at intervals of .DELTA.p as shown in FIG. 4, the result of determination in Step S2 becomes "Yes" at a certain point in time. Suppose that a spectrum data P1 was acquired at time t0 and another spectrum data P4 was acquired at time t1 after the lapse of .DELTA.t from t0. The observed spectrum obtained at time t1 (graph (c) of FIG. 5) resulted from the superposition of a reflection spectrum containing no interference (the base spectrum; graph (a) of FIG. 5) and a spectral interference pattern (graph (b) of FIG. 5) created by interference due to the trench hole 52 (the measurement target).” The observed spectrum data is store in the memory is considered as the historical spectra data.);
calculating a plurality of normalized data values based on the identified historical spectral data associated with the initial step, the first subsequent step, and the second subsequent step, wherein the plurality of normalized data values comprises: a a first normalized data value of the plurality of normalized data values is representing a difference between a baseline wave amplitude at an initial time period of the prior process indicated by the historical spectral data associated with the first step and a first wave amplitude at a first subsequent time period of the prior process indicated by the historical spectral data associated with the first subsequent step, and a second normalized data value representing a difference between the baseline wave amplitude and a second wave amplitude at a second subsequent time period indicated by the historical spectral data associated with the second subsequent step (GOTO, [Par.0050-0052], “An operation of the surface processing progress monitoring system of the present embodiment is hereinafter described by means of FIGS. 3-5, primarily focusing on the data processing performed by the data processor 4 characteristic of the present system. FIG. 3 is a flowchart showing the measuring operations by the surface processing progress monitoring system of the present embodiment. FIG. 4 is a schematic timing chart showing the timing of each of the operations. FIG. 5 shows one example of the acquisition and processing of spectra. The example shown in FIG. 5 is the result of an experiment in which the depth of a trench hole was measured using a light source 1 having a central wavelength of 800 nm and a full width at half maximum (FWHM) of 15 nm. Accordingly, the following description illustrates the case of measuring the depth of a trench hole created by etching. However, the same description is applicable to the case of measuring the thickness of a substrate or thin layer.[0051] For example, when the measurement of the hole depth is initiated simultaneously with the beginning of etching, the data processor 4 acquires spectrum data covering a predetermined wavelength range obtained by the array detector 32 of the light-dispersing unit 3 at a predetermined point in time, and stores the data in the spectrum memory 41 (Step S1). The spectrum data is repeatedly acquired at predetermined intervals of time .DELTA.p by Steps S1 and S7 until it is determined in Step S6 that the measurement has been completed. In the present example, .DELTA.p is set at one third of .DELTA.t, which will be mentioned later, However, its value is not limited to this example. [0052] After a spectrum data is acquired in Step S1, the difference spectrum calculator 42 determines whether or not a spectrum data obtained at a point in time earlier than the current point in time by .DELTA.t is stored in the spectrum memory 41 (Step S2). If no such data is stored, the optical distance calculation process (which will be described later) cannot be performed, so that the operation proceeds to Step S7. As the acquisition and storage of spectrum data are repeated at intervals of .DELTA.p as shown in FIG. 4, the result of determination in Step S2 becomes "Yes" at a certain point in time. Suppose that a spectrum data P1 was acquired at time t0 and another spectrum data P4 was acquired at time t1 after the lapse of .DELTA.t from t0.” Examiner’s note, the claim does not define what is the baseline wave amplitude, therefore, based on the Broadest Reasonable Interpretation, the first wave amplitude at an initial time period is considered as the baseline wave amplitude. Therefore, the Delta P is considered as the a first normalized data value represents a difference between a baseline wave amplitude at an initial time period of the prior process indicated by the historical spectral data associated with the initial step and a second wave amplitude at a first subsequent time period of the prior process indicated by the historical spectral data associated with the first subsequent step. The Delta t is considered as the second normalized data value representing a difference between the baseline wave amplitude and a second wave amplitude at a second subsequent time period indicated by the historical spectral data associated with the second subsequent step);
wherein the first normalized data value represents a change in a substrate feature associated with the prior substrate between the initial time period and the first subsequent time period (GOTO, [0051] For example, when the measurement of the hole depth is initiated simultaneously with the beginning of etching, the data processor 4 acquires spectrum data covering a predetermined wavelength range obtained by the array detector 32 of the light-dispersing unit 3 at a predetermined point in time, and stores the data in the spectrum memory 41 (Step S1). The spectrum data is repeatedly acquired at predetermined intervals of time .DELTA.p by Steps S1 and S7 until it is determined in Step S6 that the measurement has been completed. In the present example, .DELTA.p is set at one third of .DELTA.t, which will be mentioned later, However, its value is not limited to this example. [0052] After a spectrum data is acquired in Step S1, the difference spectrum calculator 42 determines whether or not a spectrum data obtained at a point in time earlier than the current point in time by .DELTA.t is stored in the spectrum memory 41 (Step S2). If no such data is stored, the optical distance calculation process (which will be described later) cannot be performed, so that the operation proceeds to Step S7. As the acquisition and storage of spectrum data are repeated at intervals of .DELTA.p as shown in FIG. 4, the result of determination in Step S2 becomes "Yes" at a certain point in time. Suppose that a spectrum data P1 was acquired at time t0 and another spectrum data P4 was acquired at time t1 after the lapse of .DELTA.t from t0.” Examiner’s note, the Delta P is considered as the a first normalized data value represents a difference between a first wave amplitude at an initial time period of the prior process indicated by the historical spectral data associated with the initial step and a second wave amplitude at a first subsequent time period of the prior process indicated by the historical spectral data associated with the first subsequent step. Therefore, the P/ first normalized data value represents the change of the spectrum data at the different time period.);
wherein the second normalized data value represents an additional change in the substrate feature between the initial time period and the second subsequent time period (GOTO, [0051] For example, when the measurement of the hole depth is initiated simultaneously with the beginning of etching, the data processor 4 acquires spectrum data covering a predetermined wavelength range obtained by the array detector 32 of the light-dispersing unit 3 at a predetermined point in time, and stores the data in the spectrum memory 41 (Step S1). The spectrum data is repeatedly acquired at predetermined intervals of time .DELTA.p by Steps S1 and S7 until it is determined in Step S6 that the measurement has been completed. In the present example, .DELTA.p is set at one third of .DELTA.t, which will be mentioned later, However, its value is not limited to this example. [0052] After a spectrum data is acquired in Step S1, the difference spectrum calculator 42 determines whether or not a spectrum data obtained at a point in time earlier than the current point in time by .DELTA.t is stored in the spectrum memory 41 (Step S2). If no such data is stored, the optical distance calculation process (which will be described later) cannot be performed, so that the operation proceeds to Step S7. As the acquisition and storage of spectrum data are repeated at intervals of .DELTA.p as shown in FIG. 4, the result of determination in Step S2 becomes "Yes" at a certain point in time. Suppose that a spectrum data P1 was acquired at time t0 and another spectrum data P4 was acquired at time t1 after the lapse of .DELTA.t from t0.” Examiner’s note, the Delta t is considered as the second normalized data value representing a difference between the first wave amplitude and a third wave amplitude at a second subsequent time period indicated by the historical spectral data associated with the second subsequent step, therefore, the delta t/second normalized data value representing the change of the spectrum data at the different time period.
Yennie and GOTO are analogous in arts because they have the same filed of endeavor of generating the spectrum data.
Accordingly, it would have been obvious to one of the ordinary skills in the art before the effective filing date of the claimed invention to modify the identifying, from the plurality of historical spectral data, first historical spectral data associated with an initial step of the plurality of steps, generating training data for the machine learning model, wherein generating the training data comprises generating a training input comprising at least a normalized set of the historical spectral data, as taught by Yennie, to include the the plurality of steps comprising an initial step, a first subsequent step, and a second subsequent step; historical spectral data associated with the initial step, the first subsequent step, and the second subsequent step; calculating a plurality of normalized data values based on the identified historical spectral data associated with the initial step, the first subsequent step, and the second subsequent step, wherein the plurality of normalized data values comprises: a first normalized data value representing a difference between a first wave amplitude at an initial time period of the prior process indicated by the historical spectral data associated with the initial step and a second wave amplitude at a first subsequent time period of the prior process indicated by the historical spectral data associated with the first subsequent step, and a second normalized data value representing a difference between the first wave amplitude and a third wave amplitude at a second subsequent time period indicated by the historical spectral data associated with the second subsequent step, as taught by GOTO. The modification would have been obvious because one of the ordinary skills in art would be motivated to accurately extracted the observed spectrum, (GOTO, [Par.0037], “By the surface processing progress monitoring system according to the first or second aspect of the present invention, an interference pattern indicating the depth of an etched hole, the thickness of a thin layer, substrate or similar target structure can be accurately extracted from an observed spectrum containing the interference, without being affected by the spectral distortion due to the temporal change of the light source, the spectral distortion due to the temporal change of a measurement optical system, or by the spectral distortion due to interference or scattering of light originating from a structure present on the substrate being measured that is not related to the processing work, such as etching, grinding or polishing.”).
Regarding claim 3, Yennie teaches the method of claim 1, wherein generating the training input comprising at least the normalized set of historical spectral data comprises: determining a spectral feature associated with the particular type of metrology measurement data (Yennie, [Par.0014], “Foreach training spectrum in each set of training data, a characterizing value is calculated based on the timestamp for the training spectrum, the starting characterizing value and/ or ending characterizing value for the set of training data, the physical parameter value, and the selected physical process model, thereby generating a plurality of training characterizing values with each training characterizing value associated with one of the plurality of training spectra. The implemented machine learning model is trained using the plurality of training characterizing values and plurality of training spectra to generate a trained machine learning model, and the trained machine learning model is passed to the controller of the one or more polishing systems for control of polishing of the device substrates.” And [[Par.0066-0068], “However, neural network 120 may optionally include one or more other input nodes (e.g., node 122a) to receive other data. This other data could be from a prior measurement of the substrate by the in-situ monitoring system, e.g., spectra collected from earlier in the processing of the substrate, from a measurement of a prior substrate, e.g., spectra collected during processing of another substrate, from another sensor in the polishing system, e.g., a measurement of temperature of the pad or substrate by a temperature sensor, from a polishing recipe stored by the controller that is used to control the polishing system, e.g., a polishing parameter such as carrier head pressure or platen rotation rate use for polishing the substrate, from a variable tracked by the controller, e.g., a number of substrates since the pad was changed, or from a sensor that is not part of the polishing system, e.g., a measurement of a thickness of an underlying films by a metrology station. This permits the neural network 120 to take into account these other processing or environmental variables in calculation of the characterizing value…[0068] As part of a configuration procedure for the dimensional reduction module 110, the controller 90 can receive a plurality of reference spectra and a characterizing value, e.g., thickness, associated with each reference spectrum of the plurality of reference spectra. For example, reference spectra can be measured at particular locations on one or more test substrates. In addition, measurements of the thickness at the particular locations can be performed with metrology equipment, e.g., a contact profilometer or ellipsometer. A thickness measurement can thus be associated with the reference spectrum from the same location on a substrate. The plurality of reference spectra can include, for example, five to ten reference spectra.” Examiner’s note, The spectral data set (each training dataset) associates with the normalized characterizing values. The normalized characterizing values indicates the thickness value and/or an ending thickness value for the plurality of training spectra, therefore, the thickness of the layer are considered as the historical spectral features associate with the particular type of the metrology measurement data (thickness measurement)).;
identifying, from the plurality of normalized data values, respective historical spectral data comprising the indication of a historical spectral feature that corresponds to the determined spectral feature data and including the identified respective historical spectral data in the normalized set of historical spectral data (Yennie, [Par.0014], “For each training spectrum in each set of training data, a characterizing value is calculated based on the timestamp for the training spectrum, the starting characterizing value and/ or ending characterizing value for the set of training data, the physical parameter value, and the selected physical process model, thereby generating a plurality of training characterizing values with each training characterizing value associated with one of the plurality of training spectra. The implemented machine learning model is trained using the plurality of training characterizing values and plurality of training spectra to generate a trained machine learning model, and the trained machine learning model is passed to the controller of the one or more polishing systems for control of polishing of the device substrates.” And [Par.0058], “The characterizing value is typically the thickness of the outer layer, but can be a related characteristic such as thickness removed. In addition, the characterizing value can be a more generic representation of the progress of the substrate through the polishing process, e.g., an index value representing the time or number of platen rotations at which the measurement would be expected to be observed in a polishing process that follows a predetermined progress.” Examiner’s note, the characterizing value is generated, wherein the characterizing values are considered as the historical spectral data, the thickness of the layer is considered as the historical spectral features associated with a particular type of the metrology measurement data (thickness measurement)).;
However, Yennie does not teach data values calculated for each of the plurality of step of the prior process
On the other hand, Hsiung teaches data values calculated for each of the plurality of step of the prior process (Hsiung, [Par.0053], “In some implementations, the training spectral data may include historical spectra measured at different times (e.g., periodically at a series of time steps) during an earlier performance of the manufacturing process. For example, the training spectral data may include spectra measured at a start time of the earlier performance of the manufacturing process (herein referred to as time to) and spectra measured at an end time of the earlier performance of the manufacturing process (herein referred to as time t.sub.e)” Examiner’s note, the training data include the historical spectra measured data at the different times such as, the staring time and ending time, therefore, a measuring data is considered as the normalized data value represent the performance at the start time and the performance at the ending time of the plurality step of a prior process.).
Yennie and Hsiung are analogous in arts because they have the same filed of endeavor of generating the spectrum data by using the machine learning model.
Accordingly, it would have been obvious to one of the ordinary skills in the art before the effective filing date of the claimed invention to modify the identifying, from the plurality of normalized data values, respective historical spectral data comprising the indication of a historical spectral feature that corresponds to the determined spectral feature data and including the identified respective historical spectral data in the normalized set of historical spectral data, as taught by Yennie, to include the data values calculated for each of the plurality of step of the prior process, as taught by Hsiung. The modification would have been obvious because one of the ordinary skills in art would be motivated to improve the efficiency and optimize the manufacturing process, (Hsiung, [Par.0015], “to improve efficiency and/or optimize the manufacturing process, the manufacturing process should be monitored in order to determine (e.g., in real-time or near real-time) when the manufacturing process has reached the steady state. A possible technique for detecting a state of the manufacturing process is a model that uses a univariate technique that detects the state of the manufacturing process based on a single variable associated with the manufacturing process, such as a total spectral intensity. Another possible technique for detecting the state of the manufacturing process is a model that uses a principal component analysis (PCA) technique to identify a set of variables (i.e., principal components) for detecting the state of the manufacturing process, and detecting when the manufacturing process has reached the steady state based on monitoring the set of variables.”).
Regarding claim 9, Yennie teaches the method of claim 1, wherein the first manufacturing system is the same as the second manufacturing system (Yennie, [Abstract, Par.0014], ], “method of operating a polishing system includes training a plurality of models using a machine learning algorithm to generate a plurality of trained models, each trained model configured to determine a characteristic value of a layer of a substrate based on a monitoring signal from an in-situ monitoring system of a semiconductor processing system” and [Par. 0014], “A plurality of training spectra generated during polishing of the training substrate and a timestamp for each training spectrum from the plurality of training spectra is received, for each training substrate, from the in-situ monitoring system of one or more of the plurality of polishing systems used to polish the training substrate. The starting characterizing value and/or an ending characterizing value for the training substrate is received, for each training substrate, from the in-line or stand-alone metrology system. A plurality of sets of training data is stored. Each set of training data includes the plurality of training spectra from the training substrate, the timestamp for each training spectrum from the plurality of training spectra, and the starting characterizing value and/or an ending characterizing value for the training substrate.”, Examiner’s note, the polishing system determines the character values is considered as the metrology measurement, the polishing system is considered as the first manufacturing system, the training data is received from one or more polishing systems, therefore, the first manufacturing system and second manufacturing system are the same, because they are polishing systems).
Regarding claim 10, Yennie teaches the method of claim 1, wherein the prior process comprises at least one of an etch process or a deposition process (Yennie, [Par. 0105], “Although the description above has focused on chemical mechanical polishing, the control system can be adapted to other semiconductor processing techniques, e.g., etching or deposition, e.g., chemical vapor deposition. In addition, the technique can be applied to an in-line or stand-alone metrology system rather than in-situ monitoring.”).
Regarding claim 12, Yennie teaches a system comprising: a memory to store a trained machine learning model; and as set one or more processing device coupled to the memory, the processing device to (Yennie, [Par.0009], “In another aspect, a computer program product for controlling processing of a substrate is tangibly embodied in a computer readable media and includes instructions for causing a processor to receive a plurality of sets of training data, store a plurality of machine learning models, store a plurality of physical process models, receive a selection of a machine learning model from the plurality of machine learning models and a selection of a physical process model from the plurality of physical process models to provide a combination of a selected machine learning model and a selected physical process model, generate an implemented machine learning model according to the selected machine learning model, calculate a characterizing value for each training spectrum in each set of training data thereby generating a plurality of training characterizing values with each training characterizing value associated with one of the plurality of training spectra, train the implemented machine learning model using the plurality of training characterizing values and plurality of training spectra to generate a trained machine learning model, and pass the trained machine learning model to a processing control system of a substrate processing system.”):
Receive during a current process performed for a current substrate at a manufacturing system, a plurality of spectral data associated with a current substrate (Yennie, [par.0014-0016], “A plurality of training spectra generated during polishing of the training substrate and a timestamp for each training spectrum from the plurality of training spectra is received, for each training substrate, from the in-situ monitoring system of one or more of the plurality of polishing systems used to polish the training substrate. The starting characterizing value and/or an ending characterizing value for the training substrate is received, for each training substrate, from the in-line or stand-alone metrology system. A plurality of sets of training data is stored. Each set of training data includes the plurality of training spectra from the training substrate, the timestamp for each training spectrum from the plurality of training spectra, and the starting characterizing value and/or an ending characterizing value for the training substrate. [0016], The substrate processing system may include a chemical mechanical polishing system. A substrate may be polished in the polishing system. During polishing of the substrate, the substrate may be monitored with an in-situ spectrographic monitoring system to generate the plurality of measured spectra. The plurality of measured spectra may be passed to the trained machine learning model to generate a plurality of characterizing values. At least one processing parameter of the polishing system may be controlled based on the plurality of characterizing values, e.g., polishing may be halted and/or a carrier head pressure may be adjusted.” Examiner’s note, the spectral data associate with different timestamp are received from the plurality of polishing systems, therefore, the spectral data associate with different timestamp include the data of the current process. The data includes the current data, (Yennie, [Par.0071], “he fab tools also include the in situ monitoring system 70, although the monitoring system can be considered part of the processing system itself (shown by phantom box). The in-situ monitoring system 70 can be a spectrographic monitoring system as discussed above, although other sensors can be used instead or in addition, such as eddy current monitoring, motor current or torque monitoring, cameras, temperature sensors, etc.”),
wherein the received plurality of spectral data is associated with a current step of the current process (Yennie, [par.0008], “Each set of training data includes a plurality of training spectra, a timestamp for each training spectrum from the plurality of training spectra, and a starting characterizing value and/or an ending characterizing value for the plurality of training spectra. Each machine learning model provides at least one different hyperparameter. Each physical process model provides a different function to generate characterizing values as a different function of time and/or a different physical process parameter. The characterizing value is calculated based on the timestamp for the training spectrum, the starting characterizing value and/or ending characterizing value for the set of training data, and the selected physical process model.” Examiner’s note, the plurality of training spectral at the different timestamp, therefore, the plurality of training spectral includes the spectral data of current process. The data includes the current data , (Yennie, [Par.0071], “he fab tools also include the in situ monitoring system 70, although the monitoring system can be considered part of the processing system itself (shown by phantom box). The in-situ monitoring system 70 can be a spectrographic monitoring system as discussed above, although other sensors can be used instead or in addition, such as eddy current monitoring, motor current or torque monitoring, cameras, temperature sensors, etc.”);
identify, from the plurality of spectral data, spectral data associated with an initial step of a plurality of steps of the current process (Yennie, [Par.0037], “As another issue, the raw data obtained from various tools in the semiconductor fabrication plant might not include a characterizing value for each measurement. For example, an in-situ optical monitoring system in a processing tool could be used to generate a sequence of spectra to be used as training data. However, the only ground truth measurement available may be the starting and/or ending thickness obtained from an in-line or stand-alone metrology system. The starting and/or ending thickness would be associated with the first and/or last spectrum in the sequence” and the data includes the current data , (Yennie, [Par.0071], “he fab tools also include the in situ monitoring system 70, although the monitoring system can be considered part of the processing system itself (shown by phantom box). The in-situ monitoring system 70 can be a spectrographic monitoring system as discussed above, although other sensors can be used instead or in addition, such as eddy current monitoring, motor current or torque monitoring, cameras, temperature sensors, etc.”)
provide, as input to the trained machine learning model, a normalized set of the spectral data (Yennie, [Par.0014], “For each training spectrum in each set of training data, a characterizing value is calculated based on the timestamp for the training spectrum, the starting characterizing value and/ or ending characterizing value for the set of training data, the physical parameter value, and the selected physical process model, thereby generating a plurality of training characterizing values with each training characterizing value associated with one of the plurality of training spectra. The implemented machine learning model is trained using the plurality of training characterizing values and plurality of training spectra to generate a trained machine learning model, and the trained machine learning model is passed to the controller of the one or more polishing systems for control of polishing of the device substrates.” Examiner’s note, the machine learning model is trained using the plurality of training characterizing value and plurality of training spectra (input), wherein, the characterizing values are calculated/normalized based on timestamp for the training spectra (training data) and the characterizing value associates with one of training spectra. Each training dataset associates with the normalized characterizing values, that is considered as the subset of the normalized set of historical spectral data (training data), because the characterizing value of each training spectrum of each training data set, that is calculated/normalized based on each timestamp.),
wherein the normalized set of spectral data comprises an indication of one or more spectral features associated with a particular type of metrology measurement (Yennie, [Par.0066-0068], “However, neural network 120 may optionally include one or more other input nodes (e.g., node 122a) to receive other data. This other data could be from a prior measurement of the substrate by the in-situ monitoring system, e.g., spectra collected from earlier in the processing of the substrate, from a measurement of a prior substrate, e.g., spectra collected during processing of another substrate, from another sensor in the polishing system, e.g., a measurement of temperature of the pad or substrate by a temperature sensor, from a polishing recipe stored by the controller that is used to control the polishing system, e.g., a polishing parameter such as carrier head pressure or platen rotation rate use for polishing the substrate, from a variable tracked by the controller, e.g., a number of substrates since the pad was changed, or from a sensor that is not part of the polishing system, e.g., a measurement of a thickness of an underlying films by a metrology station. This permits the neural network 120 to take into account these other processing or environmental variables in calculation of the characterizing value…[0068] As part of a configuration procedure for the dimensional reduction module 110, the controller 90 can receive a plurality of reference spectra and a characterizing value, e.g., thickness, associated with each reference spectrum of the plurality of reference spectra. For example, reference spectra can be measured at particular locations on one or more test substrates. In addition, measurements of the thickness at the particular locations can be performed with metrology equipment, e.g., a contact profilometer or ellipsometer. A thickness measurement can thus be associated with the reference spectrum from the same location on a substrate. The plurality of reference spectra can include, for example, five to ten reference spectra.” And [Par.0071-0072], “The fab tools also include the in situ monitoring system 70, although the monitoring system can be considered part of the processing system itself (shown by phantom box). The in-situ monitoring system 70 can be a spectrographic monitoring system as discussed above, although other sensors can be used instead or in addition, such as eddy current monitoring, motor current or torque monitoring, cameras, temperature sensors, etc..[0072] The fab tools can also include a process controller, e.g., the controller 90, although the process controller can be considered part of the processing system itself (again shown by phantom box). The process controller receives data from the in-situ monitoring system 70 and controls the processing system 20. This control can be done generally in real time, e.g., as the substrate is being processed. For example, the process controller 90 can detect whether to halt processing, whether to adjust a process control parameter, or whether to start a new stage of a processing recipe. Adjusting the polishing parameter can include feeding new control parameter values to the processing system. For example, in a polishing system, the process control system can determine whether to adjust one or more pressures applied by the carrier head; the adjusted values can be passed to the processing system which then implements the adjusted process, e.g., applies the adjusted pressure.”) ;
obtain one or more outputs of the trained machine learning model (Yennie, [Par: 0096-0098], “Once the physical process model builder 18d has received the selection of the type of physical process model and, if necessary, any process parameter values, the physical process model builder 18d can calculate a characteristic value, e.g., a thickness value, for each training spectrum that does not already have a characteristic value. That is, the various values, e.g., timestamp of the training spectrum, starting value, and ending value, are fed into the physical process model, which calculates a characteristic value for that training spectrum. [0097] Once an instance of the physical process model has been created, the physical process model can be used to generate a characteristic value, e.g., a thickness value, for each training spectrum in the training data that does not already have a characterizing value. Training can be performed by the model trainer application 18f using conventional techniques. For example, for a neural network, training can be performed by backpropagation using the sequence of measurements and the characteristic values generated by the physical process model. For example, for training of a neural network can be performed by backpropagation using the sequence of spectra and the characteristic values, e.g., thickness values, generated by the polishing process model. [0098] Once the training has been performed, the trained instantiation of the machine learning model can be passed to the process control system, which can then use the trained machine learning model as described above.” Examiner’s note, using the machine learning model to train on the training data to measure the thickness of the layer of the training data (historical spectral data), the thickness value is considered as the output.);
and extract, from the one or more outputs, metrology measurement data identifying one or more metrology measurement values associated with the particular type of metrology measurement (Yennie, [Par: 0096-0098], “Once the physical process model builder 18d has received the selection of the type of physical process model and, if necessary, any process parameter values, the physical process model builder 18d can calculate a characteristic value, e.g., a thickness value, for each training spectrum that does not already have a characteristic value. That is, the various values, e.g., timestamp of the training spectrum, starting value, and ending value, are fed into the physical process model, which calculates a characteristic value for that training spectrum. [0097] Once an instance of the physical process model has been created, the physical process model can be used to generate a characteristic value, e.g., a thickness value, for each training spectrum in the training data that does not already have a characterizing value. Training can be performed by the model trainer application 18f using conventional techniques. For example, for a neural network, training can be performed by backpropagation using the sequence of measurements and the characteristic values generated by the physical process model. For example, for training of a neural network can be performed by backpropagation using the sequence of spectra and the characteristic values, e.g., thickness values, generated by the polishing process model. [0098] Once the training has been performed, the trained instantiation of the machine learning model can be passed to the process control system, which can then use the trained machine learning model as described above.”, Examiner’s note, using the machine learning model to train on the training data to measure the thickness of the layer of the training data (historical spectral data), the thickness value is considered as the output. The output associates with the particular type of metrology measurement (thickness measurement).)
the one or more metrology measurement values obtained for a prior substrate processed at the manufacturing system according to a prior process (Yennie, [Par: 0066-0068], “However, neural network 120 may optionally include one or more other input nodes (e.g., node 122a) to receive other data. This other data could be from a prior measurement of the substrate by the in-situ monitoring system, e.g., spectra collected from earlier in the processing of the substrate, from a measurement of a prior substrate, e.g., spectra collected during processing of another substrate, from another sensor in the polishing system, e.g., a measurement of temperature of the pad or substrate by a temperature sensor, from a polishing recipe stored by the controller that is used to control the polishing system, e.g., a polishing parameter such as carrier head pressure or platen rotation rate use for polishing the substrate, from a variable tracked by the controller, e.g., a number of substrates since the pad was changed, or from a sensor that is not part of the polishing system, e.g., a measurement of a thickness of an underlying films by a metrology station. This permits the neural network 120 to take into account these other processing or environmental variables in calculation of the characterizing value. [0067] Before being used for, e.g., device wafers, the machine learning system 112 needs to be configured. [0068] As part of a configuration procedure for the dimensional reduction module 110, the controller 90 can receive a plurality of reference spectra and a characterizing value, e.g., thickness, associated with each reference spectrum of the plurality of reference spectra. For example, reference spectra can be measured at particular locations on one or more test substrates. In addition, measurements of the thickness at the particular locations can be performed with metrology equipment, e.g., a contact profilometer or ellipsometer. A thickness measurement can thus be associated with the reference spectrum from the same location on a substrate. The plurality of reference spectra can include, for example, five to ten reference spectra.” Examiner’s note, the measurement value is collected/obtained from earlier in the processing of the substrate, therefore, the measurement value is considered as the measurement value associates with the prior substrate processed.),
and an indication of a level of confidence that each of the one or more metrology measurement values corresponds to the current substrate (Yennie, [Par.0040], “The plant 12 can also include an in-line or stand-alone metrology system capable of generating accurate measurements of a characteristic of interest for the substrate, e.g., a thickness of a layer on the substrate. This accurate measurement of the substrate characteristic can be termed a “ground truth measure.” Examples of systems that can be used to generate the ground truth measure include a four-point probe, an ellipsometry sensor, or a transmission electron microscope.” Examiner’s note, a particular thickness value of a layer on the substrate is considered as the level of confidence of each of metrology measurement values).
However, Yennie does not teach identify additional spectral data associated with the current substrate and collected during a respective subsequent step between the initial step and the current step;calculating a plurality of normalized data values based on the identified spectral data and the identified additional spectral data, wherein the plurality of normalized data values comprises: a first normalized data value representing a difference between a first wave amplitude at an initial time period of the current process indicated by the historical spectral data associated with the initial step and a second wave amplitude at an intermediate time period of the current process indicated by the historical spectral data associated with the respective subsequent step, and the identified spectral data associated with the initial step of the plurality of steps and respective historical spectral data collected during are spective subsequent step between the initial step and the current step of the current process, and wherein a second normalized data value of the plurality of normalized data values representing a difference between the first wave amplitude and a third wave amplitude at a current time period of the current process indicated by the historical data associated with the current step the identified data associated with the initial step and respective historical spectral data collected during the current step of the current process; comprising the plurality of calculated normalized data values
On the other hand, GOTO teaches identify additional spectral data associated with the current substrate and collected during a respective subsequent step between the initial step and the current step (GOTO, [Par.0057], “After the hole depth is thus determined, the operation proceeds to Step S6. If the measurement is not completed, the operation further proceeds to Step S7, where a new spectrum, which changes with the progress of the etching, is acquired. Every time a new spectrum is acquired, a difference spectrum between the new spectrum and a spectrum obtained at a point in time earlier than the current point in time by .DELTA.t is created (see FIG. 4). From this new difference spectrum, the optical path length corresponding to the depth of the trench hole is calculated. Accordingly, every time a new spectrum is acquired, the latest depth of the trench hole at that point in time can be calculated and shown on the display unit 45.”),
calculating a plurality of normalized data values based on the identified spectral data and the identified additional spectral data (GOTO, [Par.0057], “After the hole depth is thus determined, the operation proceeds to Step S6. If the measurement is not completed, the operation further proceeds to Step S7, where a new spectrum, which changes with the progress of the etching, is acquired. Every time a new spectrum is acquired, a difference spectrum between the new spectrum and a spectrum obtained at a point in time earlier than the current point in time by .DELTA.t is created (see FIG. 4). From this new difference spectrum, the optical path length corresponding to the depth of the trench hole is calculated. Accordingly, every time a new spectrum is acquired, the latest depth of the trench hole at that point in time can be calculated and shown on the display unit 45.”),
calculating a plurality of normalized data values based on the identified historical spectral data associated with the initial step, the first subsequent step, and the second subsequent step (GOTO, [Par.0051. 0052. Fig.4], “0051, For example, when the measurement of the hole depth is initiated simultaneously with the beginning of etching, the data processor 4 acquires spectrum data covering a predetermined wavelength range obtained by the array detector 32 of the light-dispersing unit 3 at a predetermined point in time, and stores the data in the spectrum memory 41 (Step S1). The spectrum data is repeatedly acquired at predetermined intervals of time .DELTA.p by Steps S1 and S7 until it is determined in Step S6 that the measurement has been completed. In the present example, .DELTA.p is set at one third of .DELTA.t, which will be mentioned later, However, its value is not limited to this example.” And “0052, After a spectrum data is acquired in Step S1, the difference spectrum calculator 42 determines whether or not a spectrum data obtained at a point in time earlier than the current point in time by .DELTA.t is stored in the spectrum memory 41 (Step S2). If no such data is stored, the optical distance calculation process (which will be described later) cannot be performed, so that the operation proceeds to Step S7. As the acquisition and storage of spectrum data are repeated at intervals of .DELTA.p as shown in FIG. 4, the result of determination in Step S2 becomes "Yes" at a certain point in time. Suppose that a spectrum data P1 was acquired at time t0 and another spectrum data P4 was acquired at time t1 after the lapse of .DELTA.t from t0. The observed spectrum obtained at time t1 (graph (c) of FIG. 5) resulted from the superposition of a reflection spectrum containing no interference (the base spectrum; graph (a) of FIG. 5) and a spectral interference pattern (graph (b) of FIG. 5) created by interference due to the trench hole 52 (the measurement target).” Examiner’s note, the observed spectrum data is store in the memory is considered as the historical spectra data.),
wherein the plurality of normalized data values comprises: a first normalized data value representing a difference between a baseline wave amplitude at an initial time period of the prior process indicated by the historical spectral data associated with the initial step and a second wave amplitude at a first subsequent time period of the prior process indicated by the historical spectral data associated with the first subsequent step, and a second normalized data value representing a difference between the baseline wave amplitude and a second wave amplitude at a second subsequent time period indicated by the historical spectral data associated with the second subsequent step associated with the current step (GOTO, [Par.0050-0052], “An operation of the surface processing progress monitoring system of the present embodiment is hereinafter described by means of FIGS. 3-5, primarily focusing on the data processing performed by the data processor 4 characteristic of the present system. FIG. 3 is a flowchart showing the measuring operations by the surface processing progress monitoring system of the present embodiment. FIG. 4 is a schematic timing chart showing the timing of each of the operations. FIG. 5 shows one example of the acquisition and processing of spectra. The example shown in FIG. 5 is the result of an experiment in which the depth of a trench hole was measured using a light source 1 having a central wavelength of 800 nm and a full width at half maximum (FWHM) of 15 nm. Accordingly, the following description illustrates the case of measuring the depth of a trench hole created by etching. However, the same description is applicable to the case of measuring the thickness of a substrate or thin layer.[0051] For example, when the measurement of the hole depth is initiated simultaneously with the beginning of etching, the data processor 4 acquires spectrum data covering a predetermined wavelength range obtained by the array detector 32 of the light-dispersing unit 3 at a predetermined point in time, and stores the data in the spectrum memory 41 (Step S1). The spectrum data is repeatedly acquired at predetermined intervals of time .DELTA.p by Steps S1 and S7 until it is determined in Step S6 that the measurement has been completed. In the present example, .DELTA.p is set at one third of .DELTA.t, which will be mentioned later, However, its value is not limited to this example. [0052] After a spectrum data is acquired in Step S1, the difference spectrum calculator 42 determines whether or not a spectrum data obtained at a point in time earlier than the current point in time by .DELTA.t is stored in the spectrum memory 41 (Step S2). If no such data is stored, the optical distance calculation process (which will be described later) cannot be performed, so that the operation proceeds to Step S7. As the acquisition and storage of spectrum data are repeated at intervals of .DELTA.p as shown in FIG. 4, the result of determination in Step S2 becomes "Yes" at a certain point in time. Suppose that a spectrum data P1 was acquired at time t0 and another spectrum data P4 was acquired at time t1 after the lapse of .DELTA.t from t0.” Examiner’s note, the claim does not define what is the baseline wave amplitude, therefore, based on the Broadest Reasonable Interpretation, the first wave amplitude at an initial time period is considered as the baseline wave amplitude. Therefore, the Delta P is considered as the a first normalized data value represents a difference between a baseline wave amplitude at an initial time period of the prior process indicated by the historical spectral data associated with the initial step and a second wave amplitude at a first subsequent time period of the prior process indicated by the historical spectral data associated with the first subsequent step. The Delta t is considered as the second normalized data value representing a difference between the baseline wave amplitude and a second wave amplitude at a second subsequent time period indicated by the historical spectral data associated with the second subsequent step. The Delta t is considered as the second normalized data value representing a difference between the first wave amplitude and a third wave amplitude at a second subsequent time period indicated by the historical spectral data associated with the second subsequent step);
wherein the first normalized data value represents a change in a substrate feature associated with the prior substrate between the initial time period and the first subsequent time period (GOTO, [0051] For example, when the measurement of the hole depth is initiated simultaneously with the beginning of etching, the data processor 4 acquires spectrum data covering a predetermined wavelength range obtained by the array detector 32 of the light-dispersing unit 3 at a predetermined point in time, and stores the data in the spectrum memory 41 (Step S1). The spectrum data is repeatedly acquired at predetermined intervals of time .DELTA.p by Steps S1 and S7 until it is determined in Step S6 that the measurement has been completed. In the present example, .DELTA.p is set at one third of .DELTA.t, which will be mentioned later, However, its value is not limited to this example. [0052] After a spectrum data is acquired in Step S1, the difference spectrum calculator 42 determines whether or not a spectrum data obtained at a point in time earlier than the current point in time by .DELTA.t is stored in the spectrum memory 41 (Step S2). If no such data is stored, the optical distance calculation process (which will be described later) cannot be performed, so that the operation proceeds to Step S7. As the acquisition and storage of spectrum data are repeated at intervals of .DELTA.p as shown in FIG. 4, the result of determination in Step S2 becomes "Yes" at a certain point in time. Suppose that a spectrum data P1 was acquired at time t0 and another spectrum data P4 was acquired at time t1 after the lapse of .DELTA.t from t0.” Examiner’s note, the Delta P is considered as the a first normalized data value represents a difference between a first wave amplitude at an initial time period of the prior process indicated by the historical spectral data associated with the initial step and a second wave amplitude at a first subsequent time period of the prior process indicated by the historical spectral data associated with the first subsequent step. Therefore, the P/ first normalized data value represents the change of the spectrum data at the different time period.);
a normalized set of spectral data comprising the plurality of calculated normalized data value (GOTO, [Par.0051], “or example, when the measurement of the hole depth is initiated simultaneously with the beginning of etching, the data processor 4 acquires spectrum data covering a predetermined wavelength range obtained by the array detector 32 of the light-dispersing unit 3 at a predetermined point in time, and stores the data in the spectrum memory 41 (Step S1). The spectrum data is repeatedly acquired at predetermined intervals of time .DELTA.p by Steps S1 and S7 until it is determined in Step S6 that the measurement has been completed. In the present example, .DELTA.p is set at one third of .DELTA.t, which will be mentioned later, However, its value is not limited to this example.”),
wherein the second normalized data value represents an additional change in the substrate feature between the initial time period and the current time period (GOTO, [0051] For example, when the measurement of the hole depth is initiated simultaneously with the beginning of etching, the data processor 4 acquires spectrum data covering a predetermined wavelength range obtained by the array detector 32 of the light-dispersing unit 3 at a predetermined point in time, and stores the data in the spectrum memory 41 (Step S1). The spectrum data is repeatedly acquired at predetermined intervals of time .DELTA.p by Steps S1 and S7 until it is determined in Step S6 that the measurement has been completed. In the present example, .DELTA.p is set at one third of .DELTA.t, which will be mentioned later, However, its value is not limited to this example. [0052] After a spectrum data is acquired in Step S1, the difference spectrum calculator 42 determines whether or not a spectrum data obtained at a point in time earlier than the current point in time by .DELTA.t is stored in the spectrum memory 41 (Step S2). If no such data is stored, the optical distance calculation process (which will be described later) cannot be performed, so that the operation proceeds to Step S7. As the acquisition and storage of spectrum data are repeated at intervals of .DELTA.p as shown in FIG. 4, the result of determination in Step S2 becomes "Yes" at a certain point in time. Suppose that a spectrum data P1 was acquired at time t0 and another spectrum data P4 was acquired at time t1 after the lapse of .DELTA.t from t0.” Examiner’s note, the Delta t is considered as the second normalized data value representing a difference between the first wave amplitude and a third wave amplitude at a second subsequent time period indicated by the historical spectral data associated with the second subsequent step, therefore, the delta t/second normalized data value representing the change of the spectrum data at the different time period.
Yennie and GOTO are analogous in arts because they have the same filed of endeavor of generating the spectrum data.
Accordingly, it would have been obvious to one of the ordinary skills in the art before the effective filing date of the claimed invention to modify the identifying, from the plurality of spectral data, first spectral data associated with an initial step of the plurality of steps of the current process, generating training data for the machine learning model, wherein generating the training data comprises generating a training input comprising at least a normalized set of the spectral data, as taught by Yennie, to include identify additional spectral data associated with the current substrate and collected during a respective subsequent step between the initial step and the current step; calculating a plurality of normalized data values based on the identified spectral data and the identified additional spectral data, wherein the plurality of normalized data values comprises: a first normalized data value representing a difference between a first wave amplitude at an initial time period of the current process indicated by the historical spectral data associated with the initial step and a second wave amplitude at an intermediate time period of the current process indicated by the historical spectral data associated with the respective subsequent step, and the identified spectral data associated with the initial step of the plurality of steps and respective historical spectral data collected during are spective subsequent step between the initial step and the current step of the current process, and wherein a second normalized data value of the plurality of normalized data values representing a difference between the first wave amplitude and a third wave amplitude at a current time period of the current process indicated by the historical data associated with the current step the identified data associated with the initial step and respective historical spectral data collected during the current step of the current process; comprising the plurality of calculated normalized data values and, wherein the first normalized data value represents a change in a substrate feature associated with the prior substrate between the initial time period and the first subsequent time period, wherein the second normalized data value represents an additional change in the substrate feature between the initial time period and the current time period as taught by GOTO. T The modification would have been obvious because one of the ordinary skills in art would be motivated to accurately extracted the observed spectrum, (GOTO, [Par.0037], “By the surface processing progress monitoring system according to the first or second aspect of the present invention, an interference pattern indicating the depth of an etched hole, the thickness of a thin layer, substrate or similar target structure can be accurately extracted from an observed spectrum containing the interference, without being affected by the spectral distortion due to the temporal change of the light source, the spectral distortion due to the temporal change of a measurement optical system, or by the spectral distortion due to interference or scattering of light originating from a structure present on the substrate being measured that is not related to the processing work, such as etching, grinding or polishing.”).
Regarding claim 15 is being rejected for the same reason as the claim 3, because these claims recite the same limitations.
Regarding claim 20 is being rejected for the same reason as the claim 12, because these claims recite the same limitations.
Regarding claim 21, Yennie teaches the system of claim 12, but it does not teach wherein the set of one or more processing devices is further to:modify at least one of the current process performed for the current substrate or a future process performed for the future substrate based on the extracted metrology measurement data
On the other hand, GOTO teaches wherein the set of one or more processing devices is further to:modify at least one of the current process performed for the current substrate or a future process performed for the future substrate based on the extracted metrology measurement data (GOTO, [Par.0057], “After the hole depth is thus determined, the operation proceeds to Step S6. If the measurement is not completed, the operation further proceeds to Step S7, where a new spectrum, which changes with the progress of the etching, is acquired. Every time a new spectrum is acquired, a difference spectrum between the new spectrum and a spectrum obtained at a point in time earlier than the current point in time by .DELTA.t is created (see FIG. 4). From this new difference spectrum, the optical path length corresponding to the depth of the trench hole is calculated. Accordingly, every time a new spectrum is acquired, the latest depth of the trench hole at that point in time can be calculated and shown on the display unit 45.” ).
Yennie and GOTO are analogous in arts because they have the same filed of endeavor of generating the spectrum data.
Accordingly, it would have been obvious to one of the ordinary skills in the art before the effective filing date of the claimed invention to modify the generating the spectra data, as taught by Yennie, to include wherein the set of one or more processing devices is further to:modify at least one of the current process performed for the current substrate or a future process performed for the future substrate based on the extracted metrology measurement data, as taught by GOTO. The modification would have been obvious because one of the ordinary skills in art would be motivated to accurately extracted the observed spectrum, (GOTO, [Par.0037], “By the surface processing progress monitoring system according to the first or second aspect of the present invention, an interference pattern indicating the depth of an etched hole, the thickness of a thin layer, substrate or similar target structure can be accurately extracted from an observed spectrum containing the interference, without being affected by the spectral distortion due to the temporal change of the light source, the spectral distortion due to the temporal change of a measurement optical system, or by the spectral distortion due to interference or scattering of light originating from a structure present on the substrate being measured that is not related to the processing work, such as etching, grinding or polishing.”).
Claims 4, 11 are rejected under 35 U.S.C. 103 as being unpatentable over Yennie et al. (Pub. No. US20190286111– hereinafter, Yennie) in view of GOTO et al . (Pub. No. US 20130169958-hereinafter, GOTO) and further in view of (Pub. No. US 20180322399-hereinafter, Hsiung) and further in view of Kim et al (Pub. No. US 20220065618 – hereinafter, Kim).
Regarding claim 4, Yennie teaches the method of claim 3, wherein the spectral feature associated with the particular type of metrology measurement (Yennie, [[[Par.0066-0068], “However, neural network 120 may optionally include one or more other input nodes (e.g., node 122a) to receive other data. This other data could be from a prior measurement of the substrate by the in-situ monitoring system, e.g., spectra collected from earlier in the processing of the substrate, from a measurement of a prior substrate, e.g., spectra collected during processing of another substrate, from another sensor in the polishing system, e.g., a measurement of temperature of the pad or substrate by a temperature sensor, from a polishing recipe stored by the controller that is used to control the polishing system, e.g., a polishing parameter such as carrier head pressure or platen rotation rate use for polishing the substrate, from a variable tracked by the controller, e.g., a number of substrates since the pad was changed, or from a sensor that is not part of the polishing system, e.g., a measurement of a thickness of an underlying films by a metrology station. This permits the neural network 120 to take into account these other processing or environmental variables in calculation of the characterizing value…[0068] As part of a configuration procedure for the dimensional reduction module 110, the controller 90 can receive a plurality of reference spectra and a characterizing value, e.g., thickness, associated with each reference spectrum of the plurality of reference spectra. For example, reference spectra can be measured at particular locations on one or more test substrates. In addition, measurements of the thickness at the particular locations can be performed with metrology equipment, e.g., a contact profilometer or ellipsometer. A thickness measurement can thus be associated with the reference spectrum from the same location on a substrate. The plurality of reference spectra can include, for example, five to ten reference spectra.”)
However, Yennie does not teach the particular type of metrology measurement corresponds to a portion of a substrate surface comprising a profile pattern that is distinct from profile patterns of other portions of the substrate surface
On the other hand Kim teaches the particular type of metrology measurement corresponds to a portion of a substrate surface comprising a profile pattern that is distinct from profile patterns of other portions of the substrate surface (KIM, (Par.0115], “ Referring to FIG. 15, the examination device that performs the thickness estimation method according to the exemplary embodiment in the present disclosure may estimate the thickness of the target layer over the entire area of the semiconductor substrate. Meanwhile, the estimated thickness of the target layer on the semiconductor substrate may be non-uniform over the entire area. Further, estimated thickness distribution of the target layer on the semiconductor substrate may be different from the measured thickness distribution of the test layer on the test substrate illustrated in FIG. 7. As an example, the thickness of the target layer at a third coordinate P3 of the semiconductor substrate, which corresponds to the first coordinate P1 of the test substrate, may be in a range of approximately 90 nm to 91.5 nm. Meanwhile, the thickness of the target layer at a fourth coordinate P4 of the semiconductor substrate, which corresponds to the second coordinate P2 of the test substrate, may be in a range of approximately 84 nm to 85.5 nm.” Examiner’s note, the thickness measurement of the target layer is different with the test layer (another portion of the substrate surface)).
Yennie, and Kim are analogous in arts because they have the same filed of endeavor of measurement of the material use during the manufacturing processing.
Accordingly, it would have been obvious to one of the ordinary skills in the art before the effective filing date of the claimed invention to modify the spectral feature associated with the particular type of metrology measurement, as taught by Yennie, to include the particular type of metrology measurement corresponds to a portion of a substrate surface comprising a profile pattern that is distinct from profile patterns of other portions of the substrate surface, as taught by Kim. The modification would have been obvious because one of the ordinary skills in art would be motivated to improve the accuracy of thickness measurement (Kim, [Par.0116], “Meanwhile, the image of the semiconductor substrate may be captured and RGB values of pixels may be used to estimate the thickness of the target layer formed on the semiconductor substrate. In a case of applying the thickness estimation method according to the exemplary embodiment o ofhe present disclosure, accuracy may be improved by approximately 15% to 25%, as compared with a case in which the thickness of the target layer is estimated using thickness data of the test layer that are obtained from the test substrate and RGB data of image pixels.”).
Regarding claim 11, Yennie teaches the method of claim 1, wherein the particular type of metrology measurement comprises at least one of. a thickness of a prior film deposited on a surface of the prior substrate after performance of the prior process (Yennie, [Par.0066], “However, neural network 120 may optionally include one or more other input nodes (e.g., node 122a) to receive other data. This other data could be from a prior measurement of the substrate by the in-situ monitoring system, e.g., spectra collected from earlier in the processing of the substrate, from a measurement of a prior substrate, e.g., spectra collected during processing of another substrate, from another sensor in the polishing system, e.g., a measurement of temperature of the pad or substrate by a temperature sensor, from a polishing recipe stored by the controller that is used to control the polishing system, e.g., a polishing parameter such as carrier head pressure or platen rotation rate use for polishing the substrate, from a variable tracked by the controller, e.g., a number of substrates since the pad was changed, or from a sensor that is not part of the polishing system, e.g., a measurement of a thickness of an underlying films by a metrology station. This permits the neural network 120 to take into account these other processing or environmental variables in calculation of the characterizing value.”),
However, Yennie does not teach a property of one or more features etched into the prior film after the performance of the prior process, a rate of the performance of the prior process, or a uniformity of the rate of the performance of the prior process
On the other hand, Kim teaches a property of one or more features etched into the prior film after the performance of the prior process (Kim, [par.0055], “The thickness estimation method according to the exemplary embodiment in the present disclosure may include measuring the thickness of the test layer (e.g., thin film) at a plurality of positions on the test substrate to generate the regression analysis model (S120). According to an exemplary embodiment, the thickness of the test layer formed on the upper surface of the test substrate may be measured using a spectrum-based non-destructive optical measurement method using a spectroscopic ellipsometer (SE).),
a rate of the performance of the prior process, or a uniformity of the rate of the performance of the prior process (Kim, [Par.0121], “In the processing control method according to the exemplary embodiment in the present disclosure. S410 to S430 may be repeated for a plurality of semiconductor substrates. As an example, S410 to S430 may be repeated, such that accuracy in determining the optimal processing control parameter using the regression analysis model may be improved. As an example, the second processing control parameter may be the optimal processing control parameter, and the second processing control parameter may be determined using the previously updated regression analysis model (S440).” ).
Yennie, Hsiung and Kim are analogous in arts because they have the same filed of endeavor of measurement of the material use during the manufacturing processing.
Accordingly, it would have been obvious to one of the ordinary skills in the art before the effective filing date of the claimed invention to have modified the particular type of metrology measurement comprises at least one of. a thickness of a prior film deposited on a surface of the prior substrate after performance of the prior process, as taught by Yennie, to include, a property of one or more features etched into the prior film after the performance of the prior process, a rate of the performance of the prior process, or a uniformity of the rate of the performance of the prior process, as taught by Kim. The modification would have been obvious because one of the ordinary skills in art would be motivated to improve the efficiently control the subsequent processing, (Kim, [Par.0123], “In a case in which the semiconductor processing is not normally performed due to an inappropriate processing control, a semiconductor device to be manufactured using the semiconductor substrate may have a defect. The examination device that performs the processing control method according to the exemplary embodiment in the present disclosure may update the regression analysis model using the processing control parameter for the processing, and may efficiently control the subsequent processing to be normally performed.”).
Claim 5 is/are rejected under 35 U.S.C. 103 as being unpatentable over Yennie et al. (Pub. No. US20190286111– hereinafter, Yennie) in view of GOTO et al . (Pub. No. US 20130169958-hereinafter, GOTO) and further in view of Hsiung et al . (Pub. No. US 20180322399-hereinafter, Hsiung) and further in view of Kim et al (Pub. No. US 20220065618 – hereinafter, Kim) and further in view of Emil et al (Pub. No. US 20180173118 – hereinafter, Emil).
Regarding claim 5, Yennie teaches determining the spectral feature associated with the particular type of metrology measurement comprise (Yennie, [Par.0058], “The characterizing value is typically the thickness of the outer layer, but can be a related characteristic such as thickness removed. In addition, the characterizing value can be a more generic representation of the progress of the substrate through the polishing process, e.g., an index value representing the time or number of platen rotations at which the measurement would be expected to be observed in a polishing process that follows a predetermined progress.”),
However, Yennie does not teach performing a two-dimensional scan for a surface of a calibration substrate processed according to the prior process at the second manufacturing system, identifying, based on an outcome of the two-dimensional scan, a portion of the surface of the calibration substrate that comprise the profile pattern that is distinct from profile patterns of the other portions of the surface, and selecting, from historical spectral data collected for the calibration substrate, one or more spectral features associated with the identified portion of the surface of the calibration substrate
On the other hand, Emil teaches performing a two-dimensional scan for a surface of a calibration substrate processed according to the prior process at the second manufacturing system (Emil, [Abstract], “A first substrate (2002) has a calibration pattern applied to a first plurality of fields (2004) by a lithographic apparatus. Further substrates (2006, 2010) have calibration patterns applied to further pluralities of fields (2008, 2012). The different pluralities of fields have different sizes and/or shapes and/or positions. Calibration measurements are performed on the patterned substrates (2002, 2006, 2010) and used to obtain corrections for use in controlling the apparatus when applying product patterns to subsequent substrates. Measurement data representing the performance of the apparatus on fields of two or more different dimensions (2004, 2008, 2012) is gathered together in a database (2013) and used to synthesize the information needed to calibrate the apparatus for a new size. Calibration data is also obtained for different scan and step directions.”) ;
identifying, based on an outcome of the two-dimensional scan, a portion of the surface of the calibration substrate that comprise the profile pattern that is distinct from profile patterns of the other portions of the surface (Emil, [Par.0049-0050], “[0049] FIG. 2 shows the principle of an exemplary method of calibration according to an aspect of the present disclosure. A first substrate 2002 has a calibration pattern applied to a first plurality of fields 2004. In the present example, the substrate is a calibration substrate on which a calibration pattern is applied to a plurality of equally sized and spaced fields. A second substrate 2006 has a calibration pattern applied to a plurality of fields 2008. A third substrate 2010 has a calibration pattern applied to a plurality of fields 2012. While the present example describes the use of dedicated calibration patterns and dedicated calibration substrates, the terms “calibration pattern” and “calibration substrate” are not intended to exclude the use of actual product patterns for the purposes of calibration. [0050] The fields 2004, 2008, 2012 on the first, second and third substrates have different sizes and shapes, as shown in the FIG. 2. Each field has, for example, a height in a Y direction and a width in an X direction. (It will be understood that these terms refer only to the appearance of the pattern in the plane of the substrate, and not to height relative to earth or gravity). In other words, each field 2004 on the first substrate has a first set of field dimensions, each field in the second plurality has a second set of unique field dimensions, and each field in the third plurality has a third set of unique field dimensions. Substrates 2002, 2006 and 2010 are shown in FIG. 2 as separate substrates, which may be a convenient implementation. Different field sizes could in principle be mixed on a single substrate, provided that the performance of the apparatus in applying patterns with these different field sizes can be measured separately.” Examiner’s note, each set of substrate has an unique field of dimensions.);
and selecting, from historical spectral data collected for the calibration substrate, one or more spectral features associated with the identified portion of the surface of the calibration substrate (Emil, [Par.0049-0050], “[0049] FIG. 2 shows the principle of an exemplary method of calibration according to an aspect of the present disclosure. A first substrate 2002 has a calibration pattern applied to a first plurality of fields 2004. In the present example, the substrate is a calibration substrate on which a calibration pattern is applied to a plurality of equally sized and spaced fields. A second substrate 2006 has a calibration pattern applied to a plurality of fields 2008. A third substrate 2010 has a calibration pattern applied to a plurality of fields 2012. While the present example describes the use of dedicated calibration patterns and dedicated calibration substrates, the terms “calibration pattern” and “calibration substrate” are not intended to exclude the use of actual product patterns for the purposes of calibration. [0050] The fields 2004, 2008, 2012 on the first, second and third substrates have different sizes and shapes, as shown in the FIG. 2. Each field has, for example, a height in a Y direction and a width in an X direction. (It will be understood that these terms refer only to the appearance of the pattern in the plane of the substrate, and not to height relative to earth or gravity). In other words, each field 2004 on the first substrate has a first set of field dimensions, each field in the second plurality has a second set of unique field dimensions, and each field in the third plurality has a third set of unique field dimensions. Substrates 2002, 2006 and 2010 are shown in FIG. 2 as separate substrates, which may be a convenient implementation. Different field sizes could in principle be mixed on a single substrate, provided that the performance of the apparatus in applying patterns with these different field sizes can be measured separately.” Examiner’s note, each of the calibration is associates with a particular substrate of a particular field.).
Yennie, Hsiung Kim and Emil are analogous in arts because they have the same filed of endeavor of measurement of the material use during the manufacturing processing.
Accordingly, it would have been obvious to one of the ordinary skills in the art before the effective filing date of the claimed invention to have modified determining the spectral feature associated with the particular type of metrology measurement, as taught by Yennie, to include, performing a two-dimensional scan for a surface of a calibration substrate processed according to the prior process at the second manufacturing system, identifying, based on an outcome of the two-dimensional scan, a portion of the surface of the calibration substrate that comprise the profile pattern that is distinct from profile patterns of the other portions of the surface, and selecting, from historical spectral data collected for the calibration substrate, one or more spectral features associated with the identified portion of the surface of the calibration substrate, as taught by Emil. The modification would have been obvious because one of the ordinary skills in art would be motivated to improve o improve performance when exposing product fields on real product substrates, (Emil, [Par.0053], “As an example, a designed product field layout for a product substrate comprises a number of fields 2016. In this example, each field has a particular set of field dimensions which is different to the dimensions of the fields 2004, 2008, 2012. The designed product field layout is used as input for the prediction function 2015. The resulting output of the prediction function is a specific performance model 2018 for predicting the performance of the lithographic apparatus when patterning a substrate using the product field size. The predicted behavior can be used as input for a correction model in a lithographic apparatus, such as an alignment model to improve overlay performance. Metrology apparatus 240 of FIG. 1 can be used to make the measurements. The measurement data can be delivered as data 242 to database 2014 that lies within the supervisory control system, or it may lie within the lithographic apparatus control unit LACU. In any case, the control unit LACU in due course receives the information it requires for correcting any performance errors predicted by the specific performance model, and uses the information to improve performance when exposing product fields on real product substrates.”).
Claim 6 is rejected under 35 U.S.C. 103 as being unpatentable over Yennie et al. (Pub. No. US20190286111– hereinafter, Yennie) in view of GOTO et al . (Pub. No. US 20130169958-hereinafter, GOTO)and further in view of Ohkawa et al (Pub. No. US 20020173084 – hereinafter, Ohkawa).
Regarding claim 6, Yennie teaches the spectral feature associated with the particular type of metrology measurement comprise (Yennie, [Par.0058], “The characterizing value is typically the thickness of the outer layer, but can be a related characteristic such as thickness removed. In addition, the characterizing value can be a more generic representation of the progress of the substrate through the polishing process, e.g., an index value representing the time or number of platen rotations at which the measurement would be expected to be observed in a polishing process that follows a predetermined progress.”)
However, Yennie does not teach the spectral feature associated with the particular type of metrology measurement corresponds to a range of spectral wavelengths that are determined to indicate a metrology measurement value associated with the particular type of metrology measurement that has a higher degree of accuracy than other spectral wavelengths that are outside of the range of spectral wavelengths
On the other hand, Ohkawa teaches the spectral feature associated with the particular type of metrology measurement corresponds to a range of spectral wavelengths that are determined to indicate a metrology measurement value associated with the particular type of metrology measurement that has a higher degree of accuracy than other spectral wavelengths that are outside of the range of spectral wavelengths (Ohkawa, [Par.0079], “FIG. 15 shows the wavelength dependence of the optical absorption constant .alpha. of the active layer 6a, or silicon. This figure shows that the longer the wavelength, the smaller the absorption constant. alpha., or the higher the film transparency. A study of the relationship between the optical interference and transmittance, which was conducted based on the transmittance of the active layer 6a and which resulted in FIG. 12 and FIG. 13, shows that optical interference can be clearly captured when the transmittance is 10%. FIG. 16 shows the relationship between wavelength and thickness of the active layer 6a when the transmittance is 10%. Optical interference can be captured clearly across the shaded area in this figure. In other words, the film thickness can be measured. When the thickness of the active layer 6a is 25 .mu.m (in FIG. 12), the optical interference is clearly captured for wavelengths of 820 nm or greater. When the thickness of the active layer 6a is 5 .mu.m (in FIG. 13), the optical interference is captured for wavelengths of 880 nm or longer. These results match with the results in FIG. 16. These results show that optical interference can be captured accurately by choosing the ranges of wavelengths at which optical transmittance through the active layer 6a is 10% or more for accurate film thickness measurements” Examiner’s note, the thickness measurement is considered as the metrology measurement, the wavelengths of the layer is 10% or more for accurate film thickness measurement, therefore, the wavelength of the layer less than 10% (out site range) is less accurate.).
Yennie, GOTO and Ohkawa are analogous in arts because they have the same filed of endeavor of measurement of the material use during the manufacturing processing.
Accordingly, it would have been obvious to one of the ordinary skills in the art before the effective filing date of the claimed invention to have modified the spectral feature associated with the particular type of metrology measurement, as taught by Yennie, to include, the spectral feature associated with the particular type of metrology measurement that corresponds to a range of spectral wavelengths that are determined to indicate a metrology measurement value associated with the particular type of metrology measurement that has a higher degree of accuracy than other spectral wavelengths that are outside of the range of spectral wavelengths, as taught by Ohkawa. The modification would have been obvious because one of the ordinary skills in art would be motivated to improve thickness measurement (Ohkawa, [Par.0079], “FIG. 15 shows the wavelength dependence of the optical absorption constant. alpha. of the active layer 6a, or silicon. This figure shows that the longer the wavelength, the smaller the absorption constant. alpha., or the higher the film transparency. A study of the relationship between the optical interference and transmittance, which was conducted based on the transmittance of the active layer 6a and which resulted in FIG. 12 and FIG. 13, shows that optical interference can be clearly captured when the transmittance is 10%. FIG. 16 shows the relationship between wavelength and thickness of the active layer 6a when the transmittance is 10%. Optical interference can be captured clearly across the shaded area in this figure. In other words, the film thickness can be measured. When the thickness of the active layer 6a is 25 .mu.m (in FIG. 12), the optical interference is clearly captured for wavelengths of 820 nm or greater. When the thickness of the active layer 6a is 5 .mu.m (in FIG. 13), the optical interference is captured for wavelengths of 880 nm or longer. These results match with the results in FIG. 16. These results show that optical interference can be captured accurately by choosing the ranges of wavelengths at which optical transmittance through the active layer 6a is 10% or more for accurate film thickness measurement”.).
Claim 7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Yennie et al. (Pub. No. US20190286111– hereinafter, Yennie) in view of GOTO et al . (Pub. No. US 20130169958-hereinafter, GOTO) and further in view of Ohkawa et al (Pub. No. US 20020173084 – hereinafter, Ohkawa) and further in view of Kim et al (Pub. No. US 20220065618 – hereinafter, Kim).
Regarding claim 7, Yennie teaches determining the spectral feature associated with the particular type of metrology measurement comprise (Yennie, [Par.0058], “The characterizing value is typically the thickness of the outer layer, but can be a related characteristic such as thickness removed. In addition, the characterizing value can be a more generic representation of the progress of the substrate through the polishing process, e.g., an index value representing the time or number of platen rotations at which the measurement would be expected to be observed in a polishing process that follows a predetermined progress.”),
However, Yennie does not teach: providing one or more portions of the plurality of historical spectral data as input to a wave analysis model trained to provide spectral wavelengths that indicate the metrology measurement value associated with the particular type of metrology measurement that has a higher degree of accuracy than the other spectral wavelengths, obtain one or more outputs of the wave analysis model, and extract, from the one or more outputs, the range of spectral wavelengths
On the other hand, Kim teaches providing one or more portions of the set of historical spectral data as input to a wave analysis model trained to provide spectral wavelengths that indicate the metrology measurement value associated with the particular type of metrology measurement (Kim, [Par.0098-0099], “Therefore, spectrum data corresponding to each coordinate of the semiconductor substrate may be obtained from the corrected spectrum image. Spectrum data included in a predetermined wavelength band may be obtained by applying the PCA technique to the obtained spectrum data (S330). [0099] With the thickness estimation method according to the exemplary embodiment in the present disclosure, the thickness of the target layer formed on the semiconductor substrate may be estimated over the entire area by applying the spectrum data obtained in S330 to the regression analysis model that is generated in advance (S340).” Examiner’s note, using the machine learning model to train on the spectrum data (input) to determine the thickness measurement based on the predetermined wavelengths.),
obtain one or more outputs of the wave analysis model (Kim, [Par. 0099] With the thickness estimation method according to the exemplary embodiment in the present disclosure, the thickness of the target layer formed on the semiconductor substrate may be estimated over the entire area by applying the spectrum data obtained in S330 to the regression analysis model that is generated in advance (S340).”);
Yennie, GOTO and Kim are analogous in arts because they have the same filed of endeavor of measurement of the material use during the manufacturing processing.
Accordingly, it would have been obvious to one of the ordinary skills in the art before the effective filing date of the claimed invention to have modified the determining the spectral feature associated with the particular type of metrology measurement, as taught by Yennie, to include, providing one or more portions of the set of historical spectral data as input to a wave analysis model trained to provide spectral wavelengths that indicate the metrology measurement value associated with the particular type of metrology measurement, obtain one or more outputs of the wave analysis model, as taught by Kim. The modification would have been obvious because one of the ordinary skills in art would be motivated to improve the accuracy of thickness measurement (Kim, [Par.0116], “Meanwhile, the image of the semiconductor substrate may be captured and RGB values of pixels may be used to estimate the thickness of the target layer formed on the semiconductor substrate. In a case of applying the thickness estimation method according to the exemplary embodiment of the present disclosure, accuracy may be improved by approximately 15% to 25%, as compared with a case in which the thickness of the target layer is estimated using thickness data of the test layer that are obtained from the test substrate and RGB data of image pixels.”).
However, neither Yennie nor Kim teaches that has a higher degree of accuracy than the other spectral wavelengths, and extract, from the one or more outputs, the range of spectral wavelengths
On the other hand, Ohkawa teaches that has a higher degree of accuracy than the other spectral wavelengths; (Ohkawa, [Par.0079], “FIG. 15 shows the wavelength dependence of the optical absorption constant. alpha. of the active layer 6a, or silicon. This figure shows that the longer the wavelength, the smaller the absorption constant. alpha., or the higher the film transparency. A study of the relationship between the optical interference and transmittance, which was conducted based on the transmittance of the active layer 6a and which resulted in FIG. 12 and FIG. 13, shows that optical interference can be clearly captured when the transmittance is 10%. FIG. 16 shows the relationship between wavelength and thickness of the active layer 6a when the transmittance is 10%. Optical interference can be captured clearly across the shaded area in this figure. In other words, the film thickness can be measured. When the thickness of the active layer 6a is 25 .mu.m (in FIG. 12), the optical interference is clearly captured for wavelengths of 820 nm or greater. When the thickness of the active layer 6a is 5 .mu.m (in FIG. 13), the optical interference is captured for wavelengths of 880 nm or longer. These results match with the results in FIG. 16. These results show that optical interference can be captured accurately by choosing the ranges of wavelengths at which optical transmittance through the active layer 6a is 10% or more for accurate film thickness measurements”),
and extract, from the one or more outputs, the range of spectral wavelengths (Ohkawa, [Par.0079], “FIG. 15 shows the wavelength dependence of the optical absorption constant. alpha. of the active layer 6a, or silicon. This figure shows that the longer the wavelength, the smaller the absorption constant. alpha., or the higher the film transparency. A study of the relationship between the optical interference and transmittance, which was conducted based on the transmittance of the active layer 6a and which resulted in FIG. 12 and FIG. 13, shows that optical interference can be clearly captured when the transmittance is 10%. FIG. 16 shows the relationship between wavelength and thickness of the active layer 6a when the transmittance is 10%. Optical interference can be captured clearly across the shaded area in this figure. In other words, the film thickness can be measured. When the thickness of the active layer 6a is 25 .mu.m (in FIG. 12), the optical interference is clearly captured for wavelengths of 820 nm or greater. When the thickness of the active layer 6a is 5 .mu.m (in FIG. 13), the optical interference is captured for wavelengths of 880 nm or longer. These results match with the results in FIG. 16. These results show that optical interference can be captured accurately by choosing the ranges of wavelengths at which optical transmittance through the active layer 6a is 10% or more for accurate film thickness measurements”).
Yennie, GOTO, Kim and Ohkawa are analogous in arts because they have the same filed of endeavor of measurement of the material use during the manufacturing processing.
Accordingly, it would have been obvious to one of the ordinary skills in the art before the effective filing date of the claimed invention to have modified the combined teaching of Yennie and Kim of the determining the spectral feature associated with the particular type of metrology measurement, and providing one or more portions of the set of historical spectral data as input to a wave analysis model trained to provide spectral wavelengths that indicate the metrology measurement value associated with the particular type of metrology measurement, obtain one or more outputs of the wave analysis model, as set forth above, to include, that has a higher degree of accuracy than the other spectral wavelengths, and extract, from the one or more outputs, the range of spectral wavelengths as taught by Ohkawa. The modification would have been obvious because one of the ordinary skills in art would be motivated to improve thickness measurement (Ohkawa, [Par.0079], “FIG. 15 shows the wavelength dependence of the optical absorption constant. alpha. of the active layer 6a, or silicon. This figure shows that the longer the wavelength, the smaller the absorption constant. alpha., or the higher the film transparency. A study of the relationship between the optical interference and transmittance, which was conducted based on the transmittance of the active layer 6a and which resulted in FIG. 12 and FIG. 13, shows that optical interference can be clearly captured when the transmittance is 10%. FIG. 16 shows the relationship between wavelength and thickness of the active layer 6a when the transmittance is 10%. Optical interference can be captured clearly across the shaded area in this figure. In other words, the film thickness can be measured. When the thickness of the active layer 6a is 25 .mu.m (in FIG. 12), the optical interference is clearly captured for wavelengths of 820 nm or greater. When the thickness of the active layer 6a is 5 .mu.m (in FIG. 13), the optical interference is captured for wavelengths of 880 nm or longer. These results match with the results in FIG. 16. These results show that optical interference can be captured accurately by choosing the ranges of wavelengths at which optical transmittance through the active layer 6a is 10% or more for accurate film thickness measurement”.).
Claims 16, 18 are rejected under 35 U.S.C. 103 as being unpatentable over Yennie et al. (Pub. No. US20190286111– hereinafter, Yennie) in view of GOTO et al . (Pub. No. US 20130169958-hereinafter, GOTO) and further in view of Donnelly at al . (patent. No. US 76308860-hereinafter, Donnelly) and further in view of Kim et al (Pub. No. US 20220065618 – hereinafter, Kim).
Regarding claim 16, Yennie teaches the method of claim 15, wherein the spectral feature associated with the particular type of metrology measurement (Yennie, [[[Par.0066-0068], “However, neural network 120 may optionally include one or more other input nodes (e.g., node 122a) to receive other data. This other data could be from a prior measurement of the substrate by the in-situ monitoring system, e.g., spectra collected from earlier in the processing of the substrate, from a measurement of a prior substrate, e.g., spectra collected during processing of another substrate, from another sensor in the polishing system, e.g., a measurement of temperature of the pad or substrate by a temperature sensor, from a polishing recipe stored by the controller that is used to control the polishing system, e.g., a polishing parameter such as carrier head pressure or platen rotation rate use for polishing the substrate, from a variable tracked by the controller, e.g., a number of substrates since the pad was changed, or from a sensor that is not part of the polishing system, e.g., a measurement of a thickness of an underlying films by a metrology station. This permits the neural network 120 to take into account these other processing or environmental variables in calculation of the characterizing value…[0068] As part of a configuration procedure for the dimensional reduction module 110, the controller 90 can receive a plurality of reference spectra and a characterizing value, e.g., thickness, associated with each reference spectrum of the plurality of reference spectra. For example, reference spectra can be measured at particular locations on one or more test substrates. In addition, measurements of the thickness at the particular locations can be performed with metrology equipment, e.g., a contact profilometer or ellipsometer. A thickness measurement can thus be associated with the reference spectrum from the same location on a substrate. The plurality of reference spectra can include, for example, five to ten reference spectra.”)
However, Yennie does not teach the particular type of metrology measurement corresponds to a portion of a substrate surface comprising a profile pattern that is distinct from profile patterns of other portions of the substrate surface
On the other hand Kim teaches the particular type of metrology measurement corresponds to a portion of a substrate surface comprising a profile pattern that is distinct from profile patterns of other portions of the substrate surface (KIM, (Par.0115], “ Referring to FIG. 15, the examination device that performs the thickness estimation method according to the exemplary embodiment in the present disclosure may estimate the thickness of the target layer over the entire area of the semiconductor substrate. Meanwhile, the estimated thickness of the target layer on the semiconductor substrate may be non-uniform over the entire area. Further, estimated thickness distribution of the target layer on the semiconductor substrate may be different from the measured thickness distribution of the test layer on the test substrate illustrated in FIG. 7. As an example, the thickness of the target layer at a third coordinate P3 of the semiconductor substrate, which corresponds to the first coordinate P1 of the test substrate, may be in a range of approximately 90 nm to 91.5 nm. Meanwhile, the thickness of the target layer at a fourth coordinate P4 of the semiconductor substrate, which corresponds to the second coordinate P2 of the test substrate, may be in a range of approximately 84 nm to 85.5 nm.” Examiner’s note, the thickness measurement of the target layer is different with the test layer (another portion of the substrate surface)).
Yennie, and Kim are analogous in arts because they have the same filed of endeavor of measurement of the material use during the manufacturing processing.
Accordingly, it would have been obvious to one of the ordinary skills in the art before the effective filing date of the claimed invention to modify the spectral feature associated with the particular type of metrology measurement, as taught by Yennie, to include the particular type of metrology measurement corresponds to a portion of a substrate surface comprising a profile pattern that is distinct from profile patterns of other portions of the substrate surface, as taught by Kim. The modification would have been obvious because one of the ordinary skills in art would be motivated to improve the accuracy of thickness measurement (Kim, [Par.0116], “Meanwhile, the image of the semiconductor substrate may be captured and RGB values of pixels may be used to estimate the thickness of the target layer formed on the semiconductor substrate. In a case of applying the thickness estimation method according to the exemplary embodiment o ofhe present disclosure, accuracy may be improved by approximately 15% to 25%, as compared with a case in which the thickness of the target layer is estimated using thickness data of the test layer that are obtained from the test substrate and RGB data of image pixels.”).
Regarding claim 18, Yennie teaches the method of claim 12, wherein the particular type of metrology measurement comprises at least one of. a thickness of a prior film deposited on a surface of the prior substrate after performance of the prior process (Yennie, [Par.0066], “However, neural network 120 may optionally include one or more other input nodes (e.g., node 122a) to receive other data. This other data could be from a prior measurement of the substrate by the in-situ monitoring system, e.g., spectra collected from earlier in the processing of the substrate, from a measurement of a prior substrate, e.g., spectra collected during processing of another substrate, from another sensor in the polishing system, e.g., a measurement of temperature of the pad or substrate by a temperature sensor, from a polishing recipe stored by the controller that is used to control the polishing system, e.g., a polishing parameter such as carrier head pressure or platen rotation rate use for polishing the substrate, from a variable tracked by the controller, e.g., a number of substrates since the pad was changed, or from a sensor that is not part of the polishing system, e.g., a measurement of a thickness of an underlying films by a metrology station. This permits the neural network 120 to take into account these other processing or environmental variables in calculation of the characterizing value.”),
However, Yennie does not teach a property of one or more features etched into the prior film after the performance of the prior process, a rate of the performance of the prior process, or a uniformity of the rate of the performance of the prior process
On the other hand, Kim teaches a property of one or more features etched into the prior film after the performance of the prior process (Kim, [par.0055], “The thickness estimation method according to the exemplary embodiment in the present disclosure may include measuring the thickness of the test layer (e.g., thin film) at a plurality of positions on the test substrate to generate the regression analysis model (S120). According to an exemplary embodiment, the thickness of the test layer formed on the upper surface of the test substrate may be measured using a spectrum-based non-destructive optical measurement method using a spectroscopic ellipsometer (SE).),
a rate of the performance of the prior process, or a uniformity of the rate of the performance of the prior process (Kim, [Par.0121], “In the processing control method according to the exemplary embodiment in the present disclosure. S410 to S430 may be repeated for a plurality of semiconductor substrates. As an example, S410 to S430 may be repeated, such that accuracy in determining the optimal processing control parameter using the regression analysis model may be improved. As an example, the second processing control parameter may be the optimal processing control parameter, and the second processing control parameter may be determined using the previously updated regression analysis model (S440).” ).
Yennie, Hsiung and Kim are analogous in arts because they have the same filed of endeavor of measurement of the material use during the manufacturing processing.
Accordingly, it would have been obvious to one of the ordinary skills in the art before the effective filing date of the claimed invention to have modified the particular type of metrology measurement comprises at least one of. a thickness of a prior film deposited on a surface of the prior substrate after performance of the prior process, as taught by Yennie, to include, a property of one or more features etched into the prior film after the performance of the prior process, a rate of the performance of the prior process, or a uniformity of the rate of the performance of the prior process, as taught by Kim. The modification would have been obvious because one of the ordinary skills in art would be motivated to improve the efficiently control the subsequent processing, (Kim, [Par.0123], “In a case in which the semiconductor processing is not normally performed due to an inappropriate processing control, a semiconductor device to be manufactured using the semiconductor substrate may have a defect. The examination device that performs the processing control method according to the exemplary embodiment in the present disclosure may update the regression analysis model using the processing control parameter for the processing, and may efficiently control the subsequent processing to be normally performed.”).
Claim 17 is rejected under 35 U.S.C. 103 as being unpatentable over Yennie et al. (Pub. No. US20190286111– hereinafter, Yennie) in view of GOTO et al . (Pub. No. US 20130169958-hereinafter, GOTO) and further in view of Ohkawa et al (Pub. No. US 20020173084 – hereinafter, Ohkawa).
Regarding claim 17, Yennie teaches the system of claim 15, wherein the spectral feature associated with the particular type of metrology measurement comprise (Yennie, [Par.0058], “The characterizing value is typically the thickness of the outer layer, but can be a related characteristic such as thickness removed. In addition, the characterizing value can be a more generic representation of the progress of the substrate through the polishing process, e.g., an index value representing the time or number of platen rotations at which the measurement would be expected to be observed in a polishing process that follows a predetermined progress.”)
However, Yennie does not teach the spectral feature associated with the particular type of metrology measurement corresponds to a range of spectral wavelengths that are determined to indicate a metrology measurement value associated with the particular type of metrology measurement that has a higher degree of accuracy than other spectral wavelengths that are outside of the range of spectral wavelengths
On the other hand, Ohkawa teaches the spectral feature associated with the particular type of metrology measurement corresponds to a range of spectral wavelengths that are determined to indicate a metrology measurement value associated with the particular type of metrology measurement that has a higher degree of accuracy than other spectral wavelengths that are outside of the range of spectral wavelengths (Ohkawa, [Par.0079], “FIG. 15 shows the wavelength dependence of the optical absorption constant .alpha. of the active layer 6a, or silicon. This figure shows that the longer the wavelength, the smaller the absorption constant. alpha., or the higher the film transparency. A study of the relationship between the optical interference and transmittance, which was conducted based on the transmittance of the active layer 6a and which resulted in FIG. 12 and FIG. 13, shows that optical interference can be clearly captured when the transmittance is 10%. FIG. 16 shows the relationship between wavelength and thickness of the active layer 6a when the transmittance is 10%. Optical interference can be captured clearly across the shaded area in this figure. In other words, the film thickness can be measured. When the thickness of the active layer 6a is 25 .mu.m (in FIG. 12), the optical interference is clearly captured for wavelengths of 820 nm or greater. When the thickness of the active layer 6a is 5 .mu.m (in FIG. 13), the optical interference is captured for wavelengths of 880 nm or longer. These results match with the results in FIG. 16. These results show that optical interference can be captured accurately by choosing the ranges of wavelengths at which optical transmittance through the active layer 6a is 10% or more for accurate film thickness measurements” Examiner’s note, the thickness measurement is considered as the metrology measurement, the wavelengths of the layer is 10% or more for accurate film thickness measurement, therefore, the wavelength of the layer less than 10% (out site range) is less accurate.).
Yennie, GOTO and Ohkawa are analogous in arts because they have the same filed of endeavor of measurement of the material use during the manufacturing processing.
Accordingly, it would have been obvious to one of the ordinary skills in the art before the effective filing date of the claimed invention to have modified the spectral feature associated with the particular type of metrology measurement, as taught by Yennie, to include, the spectral feature associated with the particular type of metrology measurement that corresponds to a range of spectral wavelengths that are determined to indicate a metrology measurement value associated with the particular type of metrology measurement that has a higher degree of accuracy than other spectral wavelengths that are outside of the range of spectral wavelengths, as taught by Ohkawa. The modification would have been obvious because one of the ordinary skills in art would be motivated to improve thickness measurement (Ohkawa, [Par.0079], “FIG. 15 shows the wavelength dependence of the optical absorption constant. alpha. of the active layer 6a, or silicon. This figure shows that the longer the wavelength, the smaller the absorption constant. alpha., or the higher the film transparency. A study of the relationship between the optical interference and transmittance, which was conducted based on the transmittance of the active layer 6a and which resulted in FIG. 12 and FIG. 13, shows that optical interference can be clearly captured when the transmittance is 10%. FIG. 16 shows the relationship between wavelength and thickness of the active layer 6a when the transmittance is 10%. Optical interference can be captured clearly across the shaded area in this figure. In other words, the film thickness can be measured. When the thickness of the active layer 6a is 25 .mu.m (in FIG. 12), the optical interference is clearly captured for wavelengths of 820 nm or greater. When the thickness of the active layer 6a is 5 .mu.m (in FIG. 13), the optical interference is captured for wavelengths of 880 nm or longer. These results match with the results in FIG. 16. These results show that optical interference can be captured accurately by choosing the ranges of wavelengths at which optical transmittance through the active layer 6a is 10% or more for accurate film thickness measurement”.).
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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.
The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure is provide below.
Cho et al. (Pub. No.: US 20200193290-hereinafter, Cho) teaches the thickness prediction of the semiconductor during the manufacturing processing.
Sawlani et al. (Pub. No.: Us 2022/0270237-hereinafter, Sawlani) teaches the defect classification and source analysis for the semiconductor equipment.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to EM N TRIEU whose telephone number is (571)272-5747. The examiner can normally be reached on Mon-Fri from 9:00-5:00.
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, Omar Fernandez Rivas can be reached on (571) 272-2589. 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.
/E.T./Examiner, Art Unit 2128
/OMAR F FERNANDEZ RIVAS/Supervisory Patent Examiner, Art Unit 2128