Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 9-10 and 22-23 rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
The term “adequately similar and inadequately dissimilar” in claim’s 9-10 and 22-23 is a relative term which renders the claim indefinite. The term “adequately similar and inadequately dissimilar” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention.
The following is a quotation of 35 U.S.C. 112(d):
(d) REFERENCE IN DEPENDENT FORMS.—Subject to subsection (e), a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
The following is a quotation of pre-AIA 35 U.S.C. 112, fourth paragraph:
Subject to the following paragraph [i.e., the fifth paragraph of pre-AIA 35 U.S.C. 112], a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
Claim 6, 8, 19, 21 rejected under 35 U.S.C. 112(d) or pre-AIA 35 U.S.C. 112, 4th paragraph, as being of improper dependent form for failing to further limit the subject matter of the claim upon which it depends, or for failing to include all the limitations of the claim upon which it depends. Applicant may cancel the claim(s), amend the claim(s) to place the claim(s) in proper dependent form, rewrite the claim(s) in independent form, or present a sufficient showing that the dependent claim(s) complies with the statutory requirements.
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.
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
Claims 1-28 are rejected 101 being directed to an abstract idea without significantly more
Regarding Claim 1
Step 1: “A metrology method” falls under one of four categories of statutory subject matter (machine/products/apparatus, process/method, manufactures and compositions of mater).
Step 2A Prong 1: wafer to provide a prediction output of one or more metrology metrics for the wafer based on the measurement data from plurality of sites of the wafer is a mental process that can be done with the aid of pen and paper, a person can come up with a prediction based on data
applying a triggering algorithm to monitor effectiveness of the machine learning model, wherein the triggering algorithm performs two or more distance calculations to determine a distance between the measurement data and the training data set, wherein the two or more distance calculations comprise applying a statistical distance analysis technique to determine a first distance calculation between the measurement data and the training data set and applying a machine learning algorithm to determine a second distance between the measurement data and the training data set is the abstract idea of a mathematical relationship, as directed to “a mathematical relationship is a relationship between variables or numbers. A mathematical relationship may be expressed in words or using mathematical symbols”. See MPEP § 2106.04(a)(2)(I)(A).
identifying, with the triggering algorithm, a failed machine learning model state when the first distance exceeds a first threshold or the second distance exceeds a second threshold is a mental process that can be done with the aid of pen and paper a person can observe when a distance exceeds a threshold
wherein the adjusted training data set is generated by adding the measurement data from the wafer to the training data set is the abstract idea of a mathematical relationship, as directed to “a mathematical relationship is a relationship between variables or numbers. A mathematical relationship may be expressed in words or using mathematical symbols”. See MPEP § 2106.04(a)(2)(I)(A).
Step 2A Prong 2: The additional limitations acquiring metrology measurement data from a plurality of sites of a wafer is an additional element that amounts to adding insignificant extra-solution activity to the judicial exception. See MPEP §§ 2106.04(d), 2106.05(g) – examiners note acquiring metrology measurements amounts to nothing more than mere data gathering
applying a machine learning model to the measurement data acquired from the…wherein the machine learning model is trained using a training data set are an additional element that amounts to adding the words “apply it” (or an equivalent) with the judicial exception and reciting only the idea of a solution or outcome, i.e., the claim fails to recite details of how a solution to a problem is accomplished because it is unclear how the “AI system” or “machine learning” is used nor the specification makes it clear how these actions are performed. Thus, these additional elements are recited in a manner that represent no more than mere instructions to apply the judicial exceptions on a computer. See MPEP § 2106.05(f) and § 2106.04(d – examiners note: training a machine learning model on a dataset
are an additional element that amounts to adding the words “apply it” (or an equivalent) with the judicial exception and reciting only the idea of a solution or outcome, i.e., the claim fails to recite details of how a solution to a problem is accomplished because it is unclear how the “AI system” or “machine learning” is used nor the specification makes it clear how these actions are performed. Thus, these additional elements are recited in a manner that represent no more than mere instructions to apply the judicial exceptions on a computer. See MPEP § 2106.05(f) and § 2106.04(d) – examiners note: high level recitation of using a threshold to identify a failed machine learning model state
retraining the machine learning model using an adjusted training data set to generate a retrained machine learning model, are an additional element that amounts to adding the words “apply it” (or an equivalent) with the judicial exception and reciting only the idea of a solution or outcome, i.e., the claim fails to recite details of how a solution to a problem is accomplished because it is unclear how the “AI system” or “machine learning” is used nor the specification makes it clear how these actions are performed. Thus, these additional elements are recited in a manner that represent no more than mere instructions to apply the judicial exceptions on a computer. See MPEP § 2106.05(f) and § 2106.04(d) – examiners note: high level recitation of retraining a model on new measurement data
and applying the retrained machine learning model to a second wafer to provide a prediction output of one or more metrology metrics for the second measured wafer. are an additional element that amounts to adding the words “apply it” (or an equivalent) with the judicial exception and reciting only the idea of a solution or outcome, i.e., the claim fails to recite details of how a solution to a problem is accomplished because it is unclear how the “AI system” or “machine learning” is used nor the specification makes it clear how these actions are performed. Thus, these additional elements are recited in a manner that represent no more than mere instructions to apply the judicial exceptions on a computer. See MPEP § 2106.05(f) and § 2106.04(d) – examiners note: high level recitation of using a retrained model to generate a predication
Step 2B: The additional elements, taken either alone or in combination with other limitations of the claim, do not amount to significantly more than the abstract idea itself. The additional limitations acquiring metrology measurement data from a plurality of sites of a wafer is an additional element that amounts to adding insignificant extra-solution activity to the judicial exception. See MPEP §§ 2106.04(d), 2106.05(g). Furthermore, the additional element is directed to receiving data over a network, which the courts have recognized as well‐understood, routine, and conventional when they are claimed in a generic manner. See MPEP § 2106.05(d)(II) – examiners note acquiring metrology measurements amounts to nothing more than mere data gathering
applying a machine learning model to the measurement data acquired from the…wherein the machine learning model is trained using a training data set are an additional element that amounts to adding the words “apply it” (or an equivalent) with the judicial exception and reciting only the idea of a solution or outcome, i.e., the claim fails to recite details of how a solution to a problem is accomplished because it is unclear how the “AI system” or “machine learning” is used nor the specification makes it clear how these actions are performed. Thus, these additional elements are recited in a manner that represent no more than mere instructions to apply the judicial exceptions on a computer. See MPEP § 2106.05(f) and § 2106.04(d – examiners note: training a machine learning model on a dataset
identifying, with the triggering algorithm, a failed machine learning model state when the first distance exceeds a first threshold or the second distance exceeds a second threshold; are an additional element that amounts to adding the words “apply it” (or an equivalent) with the judicial exception and reciting only the idea of a solution or outcome, i.e., the claim fails to recite details of how a solution to a problem is accomplished because it is unclear how the “AI system” or “machine learning” is used nor the specification makes it clear how these actions are performed. Thus, these additional elements are recited in a manner that represent no more than mere instructions to apply the judicial exceptions on a computer. See MPEP § 2106.05(f) and § 2106.04(d) – examiners note: high level recitation of using a threshold to identify a failed machine learning model state
retraining the machine learning model using an adjusted training data set to generate a retrained machine learning model, are an additional element that amounts to adding the words “apply it” (or an equivalent) with the judicial exception and reciting only the idea of a solution or outcome, i.e., the claim fails to recite details of how a solution to a problem is accomplished because it is unclear how the “AI system” or “machine learning” is used nor the specification makes it clear how these actions are performed. Thus, these additional elements are recited in a manner that represent no more than mere instructions to apply the judicial exceptions on a computer. See MPEP § 2106.05(f) and § 2106.04(d) – examiners note: high level recitation of retraining a model on new measurement data
and applying the retrained machine learning model to a second wafer to provide a prediction output of one or more metrology metrics for the second measured wafer. are an additional element that amounts to adding the words “apply it” (or an equivalent) with the judicial exception and reciting only the idea of a solution or outcome, i.e., the claim fails to recite details of how a solution to a problem is accomplished because it is unclear how the “AI system” or “machine learning” is used nor the specification makes it clear how these actions are performed. Thus, these additional elements are recited in a manner that represent no more than mere instructions to apply the judicial exceptions on a computer. See MPEP § 2106.05(f) and § 2106.04(d) – examiners note: high level recitation of using a retrained model to generate a predication
Regarding Claim 2
Step 1: “The method” falls under one of four categories of statutory subject matter (machine/products/apparatus, process/method, manufactures and compositions of mater).
Step 2A Prong 1: wherein the statistical distance analysis of the triggering algorithm comprises applying a Mahalanobis distance analysis and a maximum difference analysis is the abstract idea of a mathematical relationship, as directed to “a mathematical relationship is a relationship between variables or numbers. A mathematical relationship may be expressed in words or using mathematical symbols”. See MPEP § 2106.04(a)(2)(I)(A).
Step 2A Prong 2 and Step 2B: There are no additional elements recited so the claim does not provide a practical application and is not considered to be significantly more. As such, the claim is patent ineligible.
Regarding Claim 3
Step 1: “The method” falls under one of four categories of statutory subject matter (machine/products/apparatus, process/method, manufactures and compositions of mater).
Step 2A Prong 1: wherein the maximum distance analysis comprises a Kolmogorov-Smirnov test is the abstract idea of a mathematical relationship, as directed to “a mathematical relationship is a relationship between variables or numbers. A mathematical relationship may be expressed in words or using mathematical symbols”. See MPEP § 2106.04(a)(2)(I)(A).
Step 2A Prong 2 and Step 2B: There are no additional elements recited so the claim does not provide a practical application and is not considered to be significantly more. As such, the claim is patent ineligible.
Regarding Claim 4
Step 1: “The method” falls under one of four categories of statutory subject matter (machine/products/apparatus, process/method, manufactures and compositions of mater).
Step 2A Prong 1: Recites the abstract ideas of claim 2
Step 2A Prong 2: The additional limitation wherein the one or more machine learning algorithms of the triggering algorithm comprise one or more one-class unsupervised machine learning algorithms is an additional element that generally links the use of the judicial exception to a particular technological environment or field of use. See MPEP §§ 2106.04(d), 2106.05(h).
Step 2B: The additional elements, taken either alone or in combination with other limitations of the claim, do not amount to significantly more than the abstract idea itself. The additional limitation wherein the one or more machine learning algorithms of the triggering algorithm comprise one or more one-class unsupervised machine learning algorithms is an additional element that generally links the use of the judicial exception to a particular technological environment or field of use. See MPEP §§ 2106.04(d), 2106.05(h).
Regarding Claim 5
Step 1: “The method” falls under one of four categories of statutory subject matter (machine/products/apparatus, process/method, manufactures and compositions of mater).
Step 2A Prong 1: Recites the abstract ideas of Claim 4
Step 2A Prong 2: The additional limitation wherein the one or more one-class unsupervised machine learning algorithms comprise a one-class support vector machine. is an additional element that generally links the use of the judicial exception to a particular technological environment or field of use. See MPEP §§ 2106.04(d), 2106.05(h).
Step 2B: The additional elements, taken either alone or in combination with other limitations of the claim, do not amount to significantly more than the abstract idea itself. The additional limitation wherein the one or more one-class unsupervised machine learning algorithms comprise a one-class support vector machine. is an additional element that generally links the use of the judicial exception to a particular technological environment or field of use. See MPEP §§ 2106.04(d), 2106.05(h).
Regarding Claim 6
Step 1: “The method” falls under one of four categories of statutory subject matter (machine/products/apparatus, process/method, manufactures and compositions of mater).
Step 2A Prong 1: See the analysis of Claim 5
Step 2A Prong 2: See the analysis of Claim 5
Step 2B: See the analysis of Claim 5
Regarding Claim 7
Step 1: “The method” falls under one of four categories of statutory subject matter (machine/products/apparatus, process/method, manufactures and compositions of mater).
Step 2A Prong 1: wherein the first threshold comprises a selected percentage of measurement data that does not overlap with the training data set is a mental process that can be done with the aid of pen and paper, a person can make a threshold that that is only a percentage of data that does not overlap with a training data set.
Step 2A Prong 2 and Step 2B: There are no additional elements recited so the claim does not provide a practical application and is not considered to be significantly more. As such, the claim is patent ineligible.
Regarding Claim 8
Step 1: “The method” falls under one of four categories of statutory subject matter (machine/products/apparatus, process/method, manufactures and compositions of mater).
Step 2A Prong 1: See the analysis of Claim 7
Step 2A Prong 2: See the analysis of Claim 7
Step 2B: See the analysis of Claim 7
Regarding Claim 9
Step 1: “The method” falls under one of four categories of statutory subject matter (machine/products/apparatus, process/method, manufactures and compositions of mater).
Step 2A Prong 1: determining whether a mean value of predictions from the one or more machine learning algorithms on the measurement data from wafer sites is positive or negative, wherein a positive result indicates the measurement data is adequately similar to the training data set, wherein a negative result indicates the measurement data is inadequately dissimilar from the training data set is a mental process that can be done with the aid of pen and paper, a person can look at values in data and see if the value is positive or negative
Step 2A Prong 2 and Step 2B: There are no additional elements recited so the claim does not provide a practical application and is not considered to be significantly more. As such, the claim is patent ineligible.
Regarding Claim 10
Step 1: “The method” falls under one of four categories of statutory subject matter (machine/products/apparatus, process/method, manufactures and compositions of mater).
Step 2A Prong 1: determining whether a percentage of positive predictions from the one or more machine learning algorithms on the measurement data from wafer sites is greater than a selected percentage, wherein a percentage above the selected percentage indicates the measurement data is adequately similar to the training data set, wherein a percentage below the selected percentage indicates the measurement data is inadequately dissimilar from the training data set. is a mental process that can be done with the aid of pen and paper, a person can look at percentages in data and see if the percentage is above a selected percentage
Step 2A Prong 2 and Step 2B: There are no additional elements recited so the claim does not provide a practical application and is not considered to be significantly more. As such, the claim is patent ineligible.
Regarding Claim 11
Step 2A Prong 1: recites the abstract ideas of Claim 1
Step 2A Prong 2: The additional limitation wherein the one or more metrics comprise tool induced shift (TIS) is an additional element that generally links the use of the judicial exception to a particular technological environment or field of use. See MPEP § 2106.05(h).
Step 2B: The additional elements, taken either alone or in combination with other limitations of the claim, do not amount to significantly more than the abstract idea itself. The additional limitation wherein the one or more metrics comprise tool induced shift (TIS) is an additional element that generally links the use of the judicial exception to a particular technological environment or field of use. See MPEP § 2106.05(h).
Regarding Claim 12
Step 1: “The method” falls under one of four categories of statutory subject matter (machine/products/apparatus, process/method, manufactures and compositions of mater).
Step 2A Prong 1: Recites the abstract ideas of Claim 1
Step 2A Prong 2: The additional limitation wherein the wafer comprises a semiconductor wafer is an additional element that generally links the use of the judicial exception to a particular technological environment or field of use. See MPEP § 2106.05(h).
Step 2B: The additional elements, taken either alone or in combination with other limitations of the claim, do not amount to significantly more than the abstract idea itself. The additional limitation wherein the wafer comprises a semiconductor wafer is an additional element that generally links the use of the judicial exception to a particular technological environment or field of use. See MPEP § 2106.05(h).
Regarding Claim 13
Step 1: “The method” falls under one of four categories of statutory subject matter (machine/products/apparatus, process/method, manufactures and compositions of mater).
Step 2A Prong 1: Recites the abstract ideas of Claim 1
Step 2A Prong 2: The additional limitation wherein the wafer comprises a 3D NAND wafer is an additional element that generally links the use of the judicial exception to a particular technological environment or field of use. See MPEP § 2106.05(h).
Step 2B: The additional elements, taken either alone or in combination with other limitations of the claim, do not amount to significantly more than the abstract idea itself. The additional limitation wherein the wafer comprises a 3D NAND wafer is an additional element that generally links the use of the judicial exception to a particular technological environment or field of use. See MPEP § 2106.05(h).
Regarding Claim 14
Step 1: “A system” falls under one of four categories of statutory subject matter (machine/products/apparatus, process/method, manufactures and compositions of mater).
Step 2A Prong 1: See the analysis of Claim 1
Step 2A Prong 2: See the analysis of Claim 1
Step 2B: See the analysis of Claim 1
Regarding Claim 15
Step 1: “The system” falls under one of four categories of statutory subject matter (machine/products/apparatus, process/method, manufactures and compositions of mater).
Step 2A Prong 1: See the analysis of Claim 2
Step 2A Prong 2: See the analysis of Claim 2
Step 2B: See the analysis of Claim 2
Regarding Claim 16
Step 1: “The system” falls under one of four categories of statutory subject matter (machine/products/apparatus, process/method, manufactures and compositions of mater).
Step 2A Prong 1: See the analysis of Claim 3
Step 2A Prong 2: See the analysis of Claim 3
Step 2B: See the analysis of Claim 3
Regarding Claim 17
Step 1: “The system” falls under one of four categories of statutory subject matter (machine/products/apparatus, process/method, manufactures and compositions of mater).
Step 2A Prong 1: See the analysis of Claim 4
Step 2A Prong 2: See the analysis of Claim 4
Step 2B: See the analysis of Claim 4
Regarding Claim 18
Step 1: “The system” falls under one of four categories of statutory subject matter (machine/products/apparatus, process/method, manufactures and compositions of mater).
Step 2A Prong 1: See the analysis of Claim 5
Step 2A Prong 2: See the analysis of Claim 5
Step 2B: See the analysis of Claim 5
Regarding Claim 19
Step 1: “The system” falls under one of four categories of statutory subject matter (machine/products/apparatus, process/method, manufactures and compositions of mater).
Step 2A Prong 1: See the analysis of Claim 6
Step 2A Prong 2: See the analysis of Claim 6
Step 2B: See the analysis of Claim 6
Regarding Claim 20
Step 1: “The system” falls under one of four categories of statutory subject matter (machine/products/apparatus, process/method, manufactures and compositions of mater).
Step 2A Prong 1: See the analysis of Claim 7
Step 2A Prong 2: See the analysis of Claim 7
Step 2B: See the analysis of Claim 7
Regarding Claim 21
Step 1: “The system” falls under one of four categories of statutory subject matter (machine/products/apparatus, process/method, manufactures and compositions of mater).
Step 2A Prong 1: See the analysis of Claim 8
Step 2A Prong 2: See the analysis of Claim 8
Step 2B: See the analysis of Claim 8
Regarding Claim 22
Step 1: “The system” falls under one of four categories of statutory subject matter (machine/products/apparatus, process/method, manufactures and compositions of mater).
Step 2A Prong 1: See the analysis of Claim 9
Step 2A Prong 2: See the analysis of Claim 9
Step 2B: See the analysis of Claim 9
Regarding Claim 23
Step 1: “The system” falls under one of four categories of statutory subject matter (machine/products/apparatus, process/method, manufactures and compositions of mater).
Step 2A Prong 1: See the analysis of Claim 10
Step 2A Prong 2: See the analysis of Claim 10
Step 2B: See the analysis of Claim 10
Regarding Claim 24
Step 1: “The system” falls under one of four categories of statutory subject matter (machine/products/apparatus, process/method, manufactures and compositions of mater).
Step 2A Prong 1: See the analysis of Claim 11
Step 2A Prong 2: See the analysis of Claim 11
Step 2B: See the analysis of Claim 11
Regarding Claim 25
Step 1: “The system” falls under one of four categories of statutory subject matter (machine/products/apparatus, process/method, manufactures and compositions of mater).
Step 2A Prong 1: See the analysis of Claim 12
Step 2A Prong 2: See the analysis of Claim 12
Step 2B: See the analysis of Claim 12
Regarding Claim 26
Step 1: “The system” falls under one of four categories of statutory subject matter (machine/products/apparatus, process/method, manufactures and compositions of mater).
Step 2A Prong 1: See the analysis of Claim 13
Step 2A Prong 2: See the analysis of Claim 13
Step 2B: See the analysis of Claim 13
Regarding Claim 27
Step 1: “A metrology system” falls under one of four categories of statutory subject matter (machine/products/apparatus, process/method, manufactures and compositions of mater).
Step 2A Prong 1: See the analysis of Claim 1
Step 2A Prong 2: See the analysis of Claim 1
Step 2B: See the analysis of Claim 1
Regarding Claim 28
Step 1: “The system” falls under one of four categories of statutory subject matter (machine/products/apparatus, process/method, manufactures and compositions of mater).
Step 2A Prong 1: recites the abstract ideas of Claim 27
Step 2A Prong 2: The additional limitation wherein the metrology sub-system is configured for tool-induced-shift measurements. is an additional element that generally links the use of the judicial exception to a particular technological environment or field of use. See MPEP § 2106.05(h).
Step 2B: The additional elements, taken either alone or in combination with other limitations of the claim, do not amount to significantly more than the abstract idea itself. The additional limitation wherein the metrology sub-system is configured for tool-induced-shift measurements. is an additional element that generally links the use of the judicial exception to a particular technological environment or field of use. See MPEP § 2106.05(h).
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim’s 1-2, 12-15, 25-26 are rejected under U.S.C. 103 as being unpatentable over Stilian Pandev, (US11415898B2) (“Pandev”), in view of Hendler et al (US20070129836A1) (“Hendler”) and Wang et al (US20220276563A1) (“Wang”)
Regarding Claim 1, Pandev teaches A metrology method comprising: acquiring metrology measurement data from a plurality of sites of a wafer ([Column 6: Lines 5-9] teaches a plurality of instances of the device area on one or more wafers as metrology targets for their metrology data teaching this limitation)
applying a machine learning model to the measurement data acquired from the wafer to provide a prediction output of one or more metrology metrics for the wafer based on the measurement data from plurality of sites of the wafer, wherein the machine learning model is trained using a training data set ([Column 1: Lines 51-60] teaches a machine learning model being trained to predict metrology data through using the metrology data. The different metrology datasets they are using are being interpreted as a training data set teaching this limitation)
and applying the retrained machine learning model to a second wafer to provide a prediction output of one or more metrology metrics for the second measured wafer ([Abstract] teaches training a model to predict metrology data and using that trained model to predict metrology data based on the previous metrology data)
Pandev does not teach applying a triggering algorithm to monitor effectiveness of the machine learning model, wherein the triggering algorithm performs two or more distance calculations to determine a distance between the measurement data and the training data set, wherein the two or more distance calculations comprise applying a statistical distance analysis technique to determine a first distance calculation between the measurement data and the training data set and applying a machine learning algorithm to determine a second distance between the measurement data and the training data set;
Hendler does teach applying a triggering algorithm to monitor effectiveness of the machine learning model, wherein the triggering algorithm performs two or more distance calculations to determine a distance between the measurement data and the training data set, wherein the two or more distance calculations comprise applying a statistical distance analysis technique to determine a first distance calculation between the measurement data and the training data set and applying a machine learning algorithm to determine a second distance between the measurement data and the training data set ([0009] - [0011] teaches using distance formulas to between two different data samples with the distance being calculated by the Euclidean distance, Mahalanobis distance, or the Manhattan distance method teaching the two or more distance calculations. The distance being calculated by the plurality of data samples is being interpreted as the measurement data and the training data set. Teaching this limitation)
Pandev and Handler are analogous art because they are both centered around data collected from the manufacturing process including semiconductors
It would have been obvious to a person skilled in the art before the effective filling date of the
claimed invention to combine Pandev with the distance calculations of Handler. Doing so would lead to improved performance for identifying defects associated with the manufacturing process ([Handler-0006]
Pandev and Handler do not teach identifying, with the triggering algorithm, a failed machine learning model state when the first distance exceeds a first threshold or the second distance exceeds a second threshold;
retraining the machine learning model using an adjusted training data set to generate a retrained machine learning model, wherein the adjusted training data set is generated by adding the measurement data from the wafer to the training data set;
However, Wang does teach identifying, with the triggering algorithm, a failed machine learning model state when the first distance exceeds a first threshold or the second distance exceeds a second threshold ([0011] teaches a model error threshold based on determining predication data and recalibrating those predictions until the model converges and breaches the threshold. [0078] teaches that the prediction data comprises the predicted pattern parameter values with those parameter values including geometrical features like distance teaching this limitation)
retraining the machine learning model using an adjusted training data set to generate a retrained machine learning model, wherein the adjusted training data set is generated by adding the measurement data from the wafer to the training data set ([0042] teaches recalibrating a prediction model based on patterning process data which included the measurements made on a physical wafer. The recalibrating of the model is being interpreted as retraining the model teaching this limitation.)
Wang, Pandev, and Handler are analogous art because they are both centered around data collected from the manufacturing process including semiconductors
It would have been obvious to a person skilled in the art before the effective filling date of the claimed invention to combine Pandev with the distance calculations of Handler and the error and retrain handling of Wang. Doing so would lead to more efficient model predictions ([Wang-Abstract])
Regarding Claim 2, Wang, Pandev, and Handler teaches all the limitations of Claim 1
Handler also teaches wherein the statistical distance analysis of the triggering algorithm comprises applying a Mahalanobis distance analysis and a maximum difference analysis. ([0009] teaches mahalonbis distance analysis and the Manhattan distance method which is being interpreted as a maximum difference analysis)
Regarding Claim 12, Wang, Pandev, and Handler teaches all the limitations of Claim 1
Wang also teaches wherein the wafer comprises a semiconductor wafer ([0005] teaches a semiconductor wafer)
Regarding Claim 13, wherein the wafer comprises a 3D NAND wafer. ([0005] teaches semiconductor devices that typically involve processing a substrate, it can be interpreted that that includes 3D NAND wafers teaching this limitation
Regarding Claim 14, see the analysis of Claim 1
Regarding Claim 15, see the analysis of Claim 2
Regarding Claim 25, see the analysis of Claim 12
Regarding Claim 26, see the analysis of Claim 13
Regarding Claim 27, See the analysis of Claim 1
Claim’s 3 and 16 are rejected under U.S.C. 103 as being unpatentable over Stilian Pandev (US11415898B2) (“Pandev”), in view of Hendler et al (US20070129836A1) (“Hendler”), Wang et al (US20220276563A1) (“Wang”), and Reda et al (NPL: Accurate Spatial Estimation and Decomposition Techniques for Variability Characterization) (“Reda”)
Regarding Claim 3, Pandev, Hendler, and Wang teaches all the limitations of Claim 2
Pandev does not teach wherein the maximum distance analysis comprises a Kolmogorov-Smirnov test.
However, Reda teaches wherein the maximum distance analysis comprises a Kolmogorov-Smirnov test. ([Page 5-Column 1: 24-27 teaches using the Kolmogorov Smirnov test to measure maximum distance)
Pandev, Handler, Wang, and Reda are analogous art because they are both centered around data collected from the manufacturing process including semiconductors
It would have been obvious to a person skilled in the art before the effective filling date of the claimed invention to combine Pandev with the distance calculations of Handler and the error and retrain handling of Wang and the Kolmogorov Smirnov test in Reda. Doing so would lead to more efficient spatial estimations ([Reda-Abstract])
Regarding Claim 16, See the analysis of Claim 3
Claim’s 4 and 17 are rejected under U.S.C. 103 as being unpatentable over Stilian Pandev (US11415898B2) (“Pandev”), in view of Hendler et al (US20070129836A1) (“Hendler”), Wang et al (US20220276563A1) (“Wang”), and Sameer T. Khanna (US20220083901A1) (“Khanna”)
Regarding Claim 4, Pandev, Hendler, and Wang teaches all the limitations of Claim 2
Pandev does not teach wherein the one or more machine learning algorithms of the triggering algorithm comprise one or more one-class unsupervised machine learning algorithms.
However, Khanna does teach wherein the one or more machine learning algorithms of the triggering algorithm comprise one or more one-class unsupervised machine learning algorithms ([0005] teaches classifying unlabeled feature vectors, it can be reasonably interpreted that to classify the unlabeled data that an unsupervised machine learning algorithm would have to be used, teaching this limitation.)
Pandev, Handler, Wang, and Khanna are analogous art because they are centered around collecting and processing data.
It would have been obvious to a person skilled in the art before the effective filling date of the claimed invention to combine Pandev with the distance calculations of Handler and the error and retrain handling of Wang and the one-class unsupervised machine learning of Khanna. Doing so would increase the accuracy of the model’s predictive performance ([Khanna-0004])
Regarding Claim 17, see the analysis of Claim 4
Claims 5-6 and 16-17 are rejected under U.S.C. 103 as being unpatentable over Stilian Pandev (US11415898B2) (“Pandev”), in view of Hendler et al (US20070129836A1) (“Hendler”), Wang et al (US20220276563A1) (“Wang”), and Sameer T. Khanna (US20220083901A1) (“Khanna”), Akkurt et al (US20210110280A1) (“Akkurt”)
Regarding Claim 5, Pandev, Hendler, Wang, and Khanna teaches all the limitations of Claim 4
Pandev does not teach wherein the one or more one-class unsupervised machine learning algorithms comprise a one-class support vector machine.
However, Akkurt does teach wherein the one or more one-class unsupervised machine learning algorithms comprise a one-class support vector machine ([0005] teaches a one class unsupervised support vector machine model)
Pandev, Hendler, Wang, Khanna and Akkurt are analogous art because they are centered around collecting and processing data.
It would have been obvious to a person skilled in the art before the effective filling date of the claimed invention to combine Pandev with the distance calculations of Handler and the error and retrain handling of Wang and the one-class unsupervised machine learning of Khanna and the one class support vector machine of Akkurt. Doing so would lead to a more accurate model ([Akkurt-0005])
Regarding Claim 6, see the analysis of Claim 5
Regarding Claim 18, see the analysis of Claim 5
Regarding Claim 19, see the analysis of Claim 5
Claims 7-8, and 20-21 are rejected under U.S.C. 103 as being unpatentable over Stilian Pandev (US11415898B2) (“Pandev”), in view of Hendler et al (US20070129836A1) (“Hendler”), Wang et al (US20220276563A1) (“Wang”), and Liu et al (US20240346244A1) (“Liu”)
Regarding Claim 7, Pandev, Hendler, and Wang teaches all the limitations of Claim 1
Pandev does not teach wherein the first threshold comprises a selected percentage of measurement data that does not overlap with the training data set.
However, Liu does teach wherein the first threshold comprises a selected percentage of measurement data that does not overlap with the training data set ([0151] teaches a method that checks whether the data range overlap is above a threshold. It can be reasonably interpreted to check to see if the data range is above a specific threshold that it is checking for if a percentage of that data is meeting the threshold teaching this limitation.)
Pandev, Hendler, Wang, and Liu are analogous art because they are centered around collecting and processing data.
It would have been obvious to a person skilled in the art before the effective filling date of the claimed invention to combine Pandev with the distance calculations of Handler and the error and retrain handling of Wang and the threshold data handling of Liu. Doing so would lead to more cost efficient machine learning training with a dataset ([Liu-0020])
Regarding Claim 8, see the analysis of Claim 7
Regarding Claim 20, see the analysis of Claim 7
Regarding Claim 21, see the analysis of Claim 7
Claim 9 and 22 are rejected under U.S.C. 103 as being unpatentable over Stilian Pandev (US11415898B2) (“Pandev”), in view of Hendler et al (US20070129836A1) (“Hendler”), Wang et al (US20220276563A1) (“Wang”), Kim et al (NPL: A variational autoencoder for a semiconductor fault detection model robust to process drift due to incomplete maintenance) (“Kim”)
Regarding Claim 9, Pandev, Hendler and Wang teaches all the limitations of Claim 1
Pandev does not teach wherein the second threshold comprises: determining whether a mean value of predictions from the one or more machine learning algorithms on the measurement data from wafer sites is positive or negative, wherein a positive result indicates the measurement data is adequately similar to the training data set, wherein a negative result indicates the measurement data is inadequately dissimilar from the training data set.
However, Kim does teach wherein the second threshold comprises: determining whether a mean value of predictions from the one or more machine learning algorithms on the measurement data from wafer sites is positive or negative, wherein a positive result indicates the measurement data is adequately similar to the training data set, wherein a negative result indicates the measurement data is inadequately dissimilar from the training data set. ([Page 4: Lines 25-31 & Page 5: Lines 1-6] teaches extracting features and those features being represented by gaussian distribution with mean and variance vectors, which is being interpreted as a mean value. The encoder is used to approximate the distribution of normal traces with drift with the autoencoder also being used to learn about the gradual shifts due to incomplete cleaning. The dataset is trained on multiple repair cycles, so the model begins to generate normal traces. It can be reasonably interpreted in order to successfully train the model the data that they are using will have positive and negative results indicating if the training was a success or not teaching this limitation.)
Pandev, Hendler, Wang, and Kim are analogous art because they are both centered around data collected from the manufacturing process including semiconductors
It would have been obvious to a person skilled in the art before the effective filling date of the claimed invention to combine Pandev with the distance calculations of Handler and the error and retrain handling of Wang and the mean value verification process of Kim. Doing so would lead to a more accurate fault detection method ([Kim-Abstract])
Regarding Claim 22, see the analysis of Claim 9
Claims 10 and 23 are rejected under U.S.C. 103 as being unpatentable over Stilian Pandev (US11415898B2) (“Pandev”), in view of Hendler et al (US20070129836A1) (“Hendler”), Wang et al (US20220276563A1) (“Wang”), and Kim et al (NPL: Wafer defect pattern classification with detecting out-of-distribution)
Regarding Claim 10, Pandev, Hendler, and Wang teaches all the limitations of Claim 1
Pandev does not teach wherein the second threshold comprises: determining whether a percentage of positive predictions from the one or more machine learning algorithms on the measurement data from wafer sites is greater than a selected percentage, wherein a percentage above the selected percentage indicates the measurement data is adequately similar to the training data set, wherein a percentage below the selected percentage indicates the measurement data is inadequately dissimilar from the training data set.
However, Kim does teach wherein the second threshold comprises: determining whether a percentage of positive predictions from the one or more machine learning algorithms on the measurement data from wafer sites is greater than a selected percentage, wherein a percentage above the selected percentage indicates the measurement data is adequately similar to the training data set, wherein a percentage below the selected percentage indicates the measurement data is inadequately dissimilar from the training data set ([3.3] teaches using probability value to make sure the out of distribution data has same or similar probability values as the wafer map patter classification. With out-of-distribution data referring to data having different values from the training dataset the different data being used to check for the out-of-distribution data, that is being interpreted as measurement data which would teach the measurement data and training data limitation [Page 1-Column 2: Lines 17-20]. The model needs to be trained to have similar probability values which would teach the limitation of the measurement data percentage being similar to the training data set, it can be reasonably interpreted that percentage below means that it is not similar to the training data set teaching the dissimilar part of the limitation)
Pandev, Hendler, Wang, and Kim are analogous art because they are both centered around data collected from the manufacturing process including semiconductors
It would have been obvious to a person skilled in the art before the effective filling date of the claimed invention to combine Pandev with the distance calculations of Handler and the error and retrain handling of Wang and the probability verification process of Kim. Doing so would lead to better data processing without compromising the accuracy ([Kim-Abstract])
Regarding Claim 23, see the analysis of Claim 10
Claims 11, 24, and 28 are rejected under U.S.C. 103 as being unpatentable over Stilian Pandev (US11415898B2) (“Pandev”), in view of Hendler et al (US20070129836A1) (“Hendler”), Wang et al (US20220276563A1) (“Wang”), and Li et al (US20210025695A1) (“Li”)
Regarding Claim 11, Pandev, Hendler, and Wang teaches all the limitations of Claim 1
Pandev does not teach wherein the one or more metrics comprise tool induced shift (TIS).
However, Li does teach wherein the one or more metrics comprise tool induced shift (TIS). ([0048] teaches the TIS being used as an accuracy indicator)
Pandev, Hendler, Wang, and Li are analogous art because they are both centered around data collected from the manufacturing process including semiconductors
It would have been obvious to a person skilled in the art before the effective filling date of the claimed invention to combine Pandev with the distance calculations of Handler and the error and retrain handling of Wang and the TIS metric of Li. Doing so would lead to a more efficient evaluation of the data ([Li-0008])
Regarding Claim 24, see the analysis of Claim 11
Regarding Claim 28, Pandev, Hendler, Wang teaches all the limitations of Claim 27
Pandev does not teach wherein the metrology sub-system is configured for tool-induced-shift measurements
However, Li teaches wherein the metrology sub-system is configured for tool-induced-shift measurements ([0048] teaches using tool induced shifts as an accuracy indicator. It can be reasonably interpreted that the system they are using is configured to process TIS measurements teaching this limitations)
It would have been obvious to a person skilled in the art before the effective filling date of the claimed invention to combine Pandev with the distance calculations of Handler and the error and retrain handling of Wang and the TIS metric of Li. Doing so would lead to a more efficient evaluation of the data ([Li-0008])
Conclusion
The Prior arts are made of recorded and relied upon is considered to applicant’s disclosure
Hoad et al (20250021082) (2023-07-14) ([Abstract] “A method of operating a set of dispatchers for a manufacturing facility, wherein each dispatcher of the set of dispatchers is a software application that makes dispatch decisions for the manufacturing facility based on facility data related to the manufacturing facility, includes identifying a first dispatcher of the set of dispatchers, wherein the first dispatcher is a non-initialized dispatcher, selecting, as an initialization partner, a second dispatcher of the set of dispatchers, and causing the first dispatcher to initiate a data retrieval process with the second dispatcher to retrieve, from the second dispatcher, an initial set of facility data related to the manufacturing facility.”)
Kim et al (20240402619) (2024-01-04) ([Abstract] “An apparatus for predicting a structure of a semiconductor device, the apparatus includes: at least one processor; a storage configured to store a learned model configured to predict the structure of the semiconductor device; and a memory configured to store at least one code, and at least one processor operatively connected to the memory and configured to execute the at least one code to: input non-destructive metrology data measured from the semiconductor device into the learned model, and predict the structure of the semiconductor device, based on the learned model, wherein the learned model is trained with training data including first data which is non-destructive metrology data and second data which is structural metrology data as reference data of the first data, and wherein the training data is refined based on a similarity of the training data in a space having a first axis corresponding to the first data and a second axis corresponding to the second data as reference axes.”)
Feng et al (20240255858) (2022-05-23) ([Abstract] “A machine learning model may employ in situ chemical composition information, as an input, to characterize processes in real time, and optionally assist in process control. Chemical composition information may be obtained from an in situ emission spectrometer such an optical emission spectrometer.”)
Ophir et al (20210142466) (2021-05-13) ([Abstract] “Metrology methods, modules and systems are provided, for using machine learning algorithms to improve the metrology accuracy and the overall process throughput. Methods comprise calculating training data concerning metrology metric(s) from initial metrology measurements, applying machine learning algorithm(s) to the calculated training data to derive an estimation model of the metrology metric(s), deriving measurement data from images of sites on received wafers, and using the estimation model to provide estimations of the metrology metric(s) with respect to the measurement data. While the training data may use two images per site, in operation a single image per site may suffice—reducing the measurement time to less than half the current measurement time. Moreover, confidence score(s) may be derived as an additional metrology and process control, and deep learning may be used to enhance the accuracy and/or speed of the metrology module.”)
Any inquiry concerning this communication or earlier communications from the examiner should be directed to URIAH V MOORE whose telephone number is (571)384-8341. The examiner can normally be reached Monday-Friday 8am-5pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Mariela Reyes can be reached at (571)270-1006. 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.
/URIAH VENDELL MOORE/Examiner, Art Unit 2142
/HAIMEI JIANG/Primary Examiner, Art Unit 2142
Prosecution Insights