DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Objections
Claims 1, 8, 11, 12, and 16 objected to because of the following informalities:
Claims 1, 8, and 12 include the limitation “wherein each set captures a respective site on the wafer and includes different images obtained using different tools or different tool settings.” There is insufficient antecedent basis for “the wafer” in the claim. For the purposes of examination, it will be read as “wherein each set captures a respective site on a wafer and includes different images obtained using different tools or different tool settings.”
Claim 1 includes the limitation “obtain multiple measurements each pertaining to the respective specific feature for each image in a set of images.” There is insufficient antecedent basis for “the respective specific feature” in the claim. For the purposes of examination, it will be read as “obtain multiple measurements each pertaining to ”
Claims 11 and 16 include the limitation “sensitivity defining a way to measure that changes in the object we are measuring are reflected in the results of the measurements.” The limitation is grammatically unclear and for grammatical clarity will be read as “sensitivity defining a way to measure that ensures changes in the object we are measuring are reflected in the results of the measurements”
Claims 11 and 16 include the limitation “external mean consistency i.e. matching given samples representing different tools we take samples from several tools of the same location.” The limitation is grammatically unclear and for grammatical clarity will be read as “external mean consistency i.e. matching given samples representing different tools by taking samples from several tools of the same location.”
Appropriate correction is required.
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.
Claims 1-11 and 13 are 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.
Claim 1 includes the limitation “wherein each target indicates whether the respective measurement falls within a prescribed range with respect to a metrology metric relating to said component loss function.” It is unclear and indefinite how the target and the respective measurements relate to the one or more target measurements previously defined. For the purposes of examination, the limitation will be read as “wherein each value indicates whether the respective target measurement falls within a prescribed range with respect to a metrology metric relating to said component loss function.”
Claim 1 includes the limitation, “wherein the loss calculator is configured to amplify each component loss function Mi by a non-linear function that compares an actual value of the component loss function Mi with the respective target measurement.” It is unclear and indefinite what an actual value is and how it compares to the previously defined respective value. For the purposes of examination, the limitation will be read as “wherein the loss calculator is configured to amplify each component loss function Mi by a non-linear function that compares the respective value of the component loss function Mi with the respective target measurement.”
Claims 1 and 8 include the limitation, “while for out-of-range measurements whose difference from the respective target measurement exceeds said threshold, applies a steep penalty that swamps any cumulative gains associated with other component loss functions.” It is unclear and indefinite what swamps means with relation to the cumulative gains. For the purposes of examination, the limitation will be read as “while for out-of-range measurements whose difference from the respective target measurement exceeds said threshold, applies a steep penalty that negates any cumulative gains associated with other component loss functions.”
Claims 2 and 9 include the following equation:
u
̅
(
x
)
=
2
x
(
1
-
e
c
x
)
+
x
e
c
x
x
>
0
x
x
<
0
However, the claims do not define what c is. For the purposes of examination, c will be viewed as a constant.
Claims 3, 10, and 13, include the limitation “the higher the value of wi the more effort is exerted by the optimization process to minimize the respective component loss function.” It is unclear and indefinite what is meant by more effort being exerted. For the purposes of examination, the limitation will be read as “the higher the value of wi the more ”
Claims that depend on the above rejected claims are also rejected under 35 U.S.C. 112(b) or 35
U.S.C. 112 (pre-AIA ), second paragraph.
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 1-18 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
With respect to claim 1, the following bold limitations are considered abstract:
“a storage unit for storing at least one set of images, wherein each set captures a respective site on the wafer and includes different images obtained using different tools or different tool settings,
a processing unit configured to run a specified metrology algorithm multiple times, each time with a different respective set of input parameters to obtain multiple measurements each pertaining to the respective specific feature for each image in a set of images;
said processing unit being responsive to one or more target measurements each relating to a respective component loss function,
M
i
for computing a respective value of each component loss function wherein each target indicates whether the respective measurement falls within a prescribed range with respect to a metrology metric relating to said component loss function;
a loss calculator for computing an aggregate loss function of the form:
L
o
s
s
=
∑
i
ω
i
∙
M
i
wherein one of the component loss functions relates to tool matching;
and
ω
i
is a coefficient;
and a parameter optimizer responsive to a value of the aggregate loss function for optimizing the metrology algorithm to obtain an optimal set of input parameters, which when applied to the metrology algorithm produces measurements that are consistent when made by a single inspection tool of a given type or by different inspection tools of the same given type;
and wherein the loss calculator is configured to amplify each component loss function
M
i
by a non-linear function that compares an actual value of the component loss function
M
i
with the respective target measurement and applies a positive gain for in-range measurements whose difference from the respective target measurement is less than a prescribed threshold, while for out-of-range measurements whose difference from the respective target measurement exceeds said threshold, applies a steep penalty that swamps any cumulative gains associated with other component loss functions.”
The above bolded limitations are directed to abstract ideas and would fall within the “Mathematical Concept” and “Mental Process” groupings of abstract ideas. Running algorithms multiple times with different input parameters, computing values for a component loss function, aggregating loss functions in the form of the claimed equation, amplifying the component loss functions by a non-linear function, and applying a positive gain or a steep penalty are all mathematical concepts as seen in specification Para(s). [0058-0073]. According to MPEP 2106.04(C) “A claim that recites a mathematical calculation, when the claim is given its broadest reasonable interpretation in light of the specification, will be considered as falling within the "mathematical concepts" grouping. A mathematical calculation is a mathematical operation (such as multiplication) or an act of calculating using mathematical methods to determine a variable or number, e.g., performing an arithmetic operation such as exponentiation. There is no particular word or set of words that indicates a claim recites a mathematical calculation. That is, a claim does not have to recite the word "calculating" in order to be considered a mathematical calculation. For example, a step of "determining" a variable or number using mathematical methods or "performing" a mathematical operation may also be considered mathematical calculations when the broadest reasonable interpretation of the claim in light of the specification encompasses a mathematical calculation.” Comparing values to a threshold is a mental process because it can be done in the human mind using observation, judgement, and opinion.
This judicial exception is not integrated into a practical application. In particular, the claim recites the additional elements –
“a storage unit for storing at least one set of images, wherein each set captures a respective site on the wafer and includes different images obtained using different tools or different tool settings, a processing unit, and a loss calculator”
Examiner views these limitations amount to generally linking the use of the judicial exception to a particular technological environment or field of use – see MPEP 2106.05(h)
As such Examiner does NOT view that the claims
-Improve the functioning of a computer, or to any other technology or technical field
-Apply the judicial exception with, or by use of, a particular machine - see MPEP
2106.05(b)
-Effect a transformation or reduction of a particular article to a different state or thing -
see MPEP 2106.05(c)
-Apply or use the judicial exception in some other meaningful way beyond generally
linking the use of the judicial exception to a particular technological environment, such that the
claim as a whole is more than a drafting effort designed to monopolize the exception - see MPEP
2106.05(e) and Vanda Memo.
Moreover, Examiner views the claims to be merely generally linking the use of the judicial exception to a computer system and generic wafer data.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of “a storage unit for storing at least one set of images, wherein each set captures a respective site on the wafer and includes different images obtained using different tools or different tool settings, a processing unit, and a loss calculator;” amounts to using a computer as a tool as storing data in a storage unit and processing information using a processing unit is viewed as simply adding a general purpose computer or computer components to an abstract idea. Examiner further notes that such additional elements are viewed to be well known routine and conventional as evidenced by
Pandev (US 20250259051 A1)
Kuznetsov (US 20240142948 A1)
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. Considering the claim as a whole, one of ordinary skill in the art would not know the practical application of the present invention since the claims do not apply or use the judicial exception in some meaningful way. As currently claimed, Examiner views that the additional elements do not apply, rely on, or use the judicial exception in a manner that imposes a meaningful limit on the judicial exception, because the claim fails to recite clearly how the judicial exception is applied in a manner that does not monopolize the exception because the limitations “a storage unit for storing at least one set of images, wherein each set captures a respective site on the wafer and includes different images obtained using different tools or different tool settings, a processing unit, and a loss calculator;” just tie the claim to data from a wafer and well-known computing components.
With respect to claim 8, the following bold limitations are considered abstract:
“A computerized method for optimizing a metrology algorithm used by an inspection tool, the method comprising:
acquiring at least one set of images, wherein each set captures a respective site on the wafer and includes different images obtained using different tools or different tool settings,
for each specific feature common to each image in the set of images for which a measurement is required, running the metrology algorithm multiple times, each time with a different respective set of input parameters to obtain multiple measurements each pertaining to the respective specific feature;
for each measurement, providing one or more target measurements, each target measurement relating to a component loss function, M.sub.i that indicates whether each measurement falls within a prescribed range with respect to a metrology metric relating to said component loss function;
defining an aggregate loss function of the form:
L
o
s
s
=
∑
i
ω
i
∙
M
i
wherein one of the component loss functions relates to tool matching; and ω.sub.i is a coefficient;
and optimizing the metrology algorithm to obtain an optimal set of input parameters, which when applied to the metrology algorithm produces measurements that are consistent when made by a single inspection tool of a given type or by different inspection tools of the same given type;
wherein optimizing the metrology algorithm includes:
amplifying each component loss function M.sub.i by a non-linear function that compares an actual value of the respective target measurement is less than a prescribed threshold, while for out-of-range measurements whose difference from the respective target measurement exceeds said threshold, applies a steep penalty that swamps any cumulative gains associated with other component loss functions.”
The above bolded limitations are directed to abstract ideas and would fall within the “Mathematical Concept” and “Mental Process” groupings of abstract ideas. Running algorithms multiple times with different input parameters, computing values for a component loss function, aggregating loss functions in the form of the claimed equation, amplifying the component loss functions by a non-linear function, and applying a positive gain or a steep penalty are all mathematical concepts as seen in specification Para(s). [0058-0073]. According to MPEP 2106.04(C) “A claim that recites a mathematical calculation, when the claim is given its broadest reasonable interpretation in light of the specification, will be considered as falling within the "mathematical concepts" grouping. A mathematical calculation is a mathematical operation (such as multiplication) or an act of calculating using mathematical methods to determine a variable or number, e.g., performing an arithmetic operation such as exponentiation. There is no particular word or set of words that indicates a claim recites a mathematical calculation. That is, a claim does not have to recite the word "calculating" in order to be considered a mathematical calculation. For example, a step of "determining" a variable or number using mathematical methods or "performing" a mathematical operation may also be considered mathematical calculations when the broadest reasonable interpretation of the claim in light of the specification encompasses a mathematical calculation.” Comparing values to a threshold is a mental process because it can be done in the human mind using observation, judgement, and opinion.
This judicial exception is not integrated into a practical application. In particular, the claim recites the additional elements –
“A computerized method for optimizing a metrology algorithm used by an inspection tool, the method comprising:
acquiring at least one set of images, wherein each set captures a respective site on the wafer and includes different images obtained using different tools or different tool settings.”
Examiner views these limitations amount to generally linking the use of the judicial exception to a particular technological environment or field of use – see MPEP 2106.05(h)
As such Examiner does NOT view that the claims
-Improve the functioning of a computer, or to any other technology or technical field
-Apply the judicial exception with, or by use of, a particular machine - see MPEP
2106.05(b)
-Effect a transformation or reduction of a particular article to a different state or thing -
see MPEP 2106.05(c)
-Apply or use the judicial exception in some other meaningful way beyond generally
linking the use of the judicial exception to a particular technological environment, such that the
claim as a whole is more than a drafting effort designed to monopolize the exception - see MPEP
2106.05(e) and Vanda Memo.
Moreover, Examiner views the claims to be merely generally linking the use of the judicial exception to a computer system and generic wafer data.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of “A computerized method for optimizing a metrology algorithm used by an inspection tool, the method comprising: acquiring at least one set of images, wherein each set captures a respective site on the wafer and includes different images obtained using different tools or different tool settings” amounts to using a computer as a tool and mere data gathering. Computerizing a method is viewed as simply adding a general-purpose computer or computer components to an abstract idea. Acquiring data from wafers using generic tools is mere data gathering as all uses of the recited judicial exception require such data gathering. Examiner further notes that such additional elements are viewed to be well known routine and conventional as evidenced by
Pandev (US 20250259051 A1)
Kuznetsov (US 20240142948 A1)
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. Considering the claim as a whole, one of ordinary skill in the art would not know the practical application of the present invention since the claims do not apply or use the judicial exception in some meaningful way. As currently claimed, Examiner views that the additional elements do not apply, rely on, or use the judicial exception in a manner that imposes a meaningful limit on the judicial exception, because the claim fails to recite clearly how the judicial exception is applied in a manner that does not monopolize the exception because the limitations “A computerized method for optimizing a metrology algorithm used by an inspection tool, the method comprising: acquiring at least one set of images, wherein each set captures a respective site on the wafer and includes different images obtained using different tools or different tool settings” just tie the claim to data from a wafer and well-known computing components.
With respect to claim 12, the following bold limitations are considered abstract:
“A computerized method for optimizing a metrology algorithm used by an inspection tool, the method comprising:
acquiring at least one set of images, wherein each set captures a respective site on the wafer and includes different images obtained using different tools or different tool settings;
for each specific feature common to each image in the set of images for which a measurement is required, running the metrology algorithm multiple times, each time with a different respective set of input parameters to obtain multiple measurements each pertaining to the respective specific feature;
for each measurement, providing one or more target measurements, each target measurement relating to a component loss function, M.sub.i that indicates whether each measurement falls within a prescribed range with respect to a metrology metric relating to said component loss function;
defining a loss function of the form:
L
o
s
s
=
∑
i
ω
i
∙
M
i
wherein one of the component loss functions relates to tool matching;
and ω.sub.i is a coefficient; and optimizing the metrology algorithm to obtain an optimal set of input parameters, which when applied to the metrology algorithm produces measurements that are consistent when made by said inspection tool or by different inspection tools of similar type;
wherein optimizing the metrology algorithm includes:
obtaining respective measurements for multiple locations across two different tools;
creating respective distributions of the measurements for each of the two different tools; and using distribution-based metrics to measure similarity between the two distributions.”
The above bolded limitations are directed to abstract ideas and would fall within the “Mathematical Concept” grouping of abstract ideas. Running algorithms multiple times with different input parameters, computing values for a component loss function, aggregating loss functions in the form of the claimed equation, creating distributions and determining similarities between two distributions are all mathematical concepts as seen in specification Para(s). [0093-0094]. According to MPEP 2106.04(C) “A claim that recites a mathematical calculation, when the claim is given its broadest reasonable interpretation in light of the specification, will be considered as falling within the "mathematical concepts" grouping. A mathematical calculation is a mathematical operation (such as multiplication) or an act of calculating using mathematical methods to determine a variable or number, e.g., performing an arithmetic operation such as exponentiation. There is no particular word or set of words that indicates a claim recites a mathematical calculation. That is, a claim does not have to recite the word "calculating" in order to be considered a mathematical calculation. For example, a step of "determining" a variable or number using mathematical methods or "performing" a mathematical operation may also be considered mathematical calculations when the broadest reasonable interpretation of the claim in light of the specification encompasses a mathematical calculation.”
This judicial exception is not integrated into a practical application. In particular, the claim recites the additional elements –
“A computerized method for optimizing a metrology algorithm used by an inspection tool, the method comprising:
acquiring at least one set of images, wherein each set captures a respective site on the wafer and includes different images obtained using different tools or different tool settings; obtaining respective measurements for multiple locations across two different tools;”
Examiner views these limitations amount to generally linking the use of the judicial exception to a particular technological environment or field of use – see MPEP 2106.05(h)
As such Examiner does NOT view that the claims
-Improve the functioning of a computer, or to any other technology or technical field
-Apply the judicial exception with, or by use of, a particular machine - see MPEP
2106.05(b)
-Effect a transformation or reduction of a particular article to a different state or thing -
see MPEP 2106.05(c)
-Apply or use the judicial exception in some other meaningful way beyond generally
linking the use of the judicial exception to a particular technological environment, such that the
claim as a whole is more than a drafting effort designed to monopolize the exception - see MPEP
2106.05(e) and Vanda Memo.
Moreover, Examiner views the claims to be merely generally linking the use of the judicial exception to a computer system and generic wafer data.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of “acquiring at least one set of images, wherein each set captures a respective site on the wafer and includes different images obtained using different tools or different tool settings; obtaining respective measurements for multiple locations across two different tools;” amounts to using a computer as a tool and mere data gathering. Computerizing a method is viewed as simply adding a general-purpose computer or computer components to an abstract idea. Acquiring data from wafers using generic tools is mere data gathering as all uses of the recited judicial exception require such data gathering. Examiner further notes that such additional elements are viewed to be well known routine and conventional as evidenced by
Pandev (US 20250259051 A1)
Kuznetsov (US 20240142948 A1)
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. Considering the claim as a whole, one of ordinary skill in the art would not know the practical application of the present invention since the claims do not apply or use the judicial exception in some meaningful way. As currently claimed, Examiner views that the additional elements do not apply, rely on, or use the judicial exception in a manner that imposes a meaningful limit on the judicial exception, because the claim fails to recite clearly how the judicial exception is applied in a manner that does not monopolize the exception because the limitations “acquiring at least one set of images, wherein each set captures a respective site on the wafer and includes different images obtained using different tools or different tool settings; obtaining respective measurements for multiple locations across two different tools;” just tie the claim to data from a wafer and well-known computing components.
Dependent claims 2-7, 9-11, and 13-18 when analyzed as a whole are held to be patent ineligible under 35 U.S.C. 101 because the additional recited limitation(s) fail(s) to establish that the claims are not directed to an abstract idea, as detailed below:
The dependent claims are directed to further limit the functions used and the optimization process which all amounts to mathematical and mental processes. Claims 4 and 5 are directed to inputting data into the system via an interface which is an additional element, however, they amount to using a computer as a tool. Claims 6, 7, 17, and 18 include computer elements which are also viewed as using a computer as a tool.
Therefore, dependent claims 2-7, 9-11, and 13-18 further limit the abstract idea with an abstract idea and thus the claims are still directed to an abstract idea without significantly more.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 12-14, 16 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Pandev (US 20250259051 A1) in view of Kendall (Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics; 2018) and Pandev (2021) (US 20210165398 A1).
With respect to claim 12,
Pandev teaches,
A computerized method for optimizing a metrology algorithm used by an inspection tool, the method comprising: (Para. [0001] teaches “Certain embodiments relate to using the ML library to create an application-specific ML architecture for use in a process such as wafer inspection or metrology.”)
acquiring at least one set of images, wherein each set captures a respective site on the wafer and includes different images obtained using different tools or different tool settings; (Para. [0032] teaches “In some embodiments, the specimen is a wafer. The wafer may include any wafer known in the semiconductor arts.” Para. [0047] “However, in other instances, the detectors may be configured as imaging detectors that are configured to generate imaging signals or image data. Therefore, the output acquisition subsystem may be configured to generate images in a number of ways.” Para. [0100] teaches “FIG. 3 provides an illustration of multiple metrology heads integrated on the same tool. However, in many cases, multiple metrology tools are used for measurements on a single or multiple metrology targets, which is described, e.g. in U.S. Pat. No. 7,478,019 to Zangooie et al, which is incorporated by reference as if fully set forth herein. The embodiments described herein may be further configured as described in this reference.” (I.e. different tools))
for each specific feature common to each image in the set of images for which a measurement is required, running the metrology algorithm multiple times, each time with a different respective set of input parameters to obtain multiple measurements each pertaining to the respective specific feature; (Para. [0108] “Computational algorithms are usually optimized for metrology applications with one or more approaches being used such as design and implementation of computational hardware, parallelization, distribution of computation, load-balancing, multi-service support, dynamic load optimization, etc. Different implementations of algorithms can be done in firmware, software, FPGA, programmable optics components, etc.” (Para. [0120] “When the input layer receives an input, it passes on a modified version of the input to the next layer. In a DL-based model, there are usually many layers between the input and output, allowing the algorithm to use multiple processing layers, composed of multiple linear and/or non-linear transformations.” (I.e. since each layer has a different input, and there are multiple layers this is viewed as running the algorithm multiple times with different input.)
for each measurement, providing one or more target measurements, each target measurement relating to a component loss function, M.sub.i that indicates whether each measurement falls within a prescribed range with respect to a metrology metric relating to said component loss function; (Para. [0155] teaches “the selecting step includes selecting a loss function and HPs from the ML library based on the input data metrics and the performance objectives specific to the application. As shown in steps 606 and 608, the computer system(s), a decision algorithm executed by the computer system(s), or a user may select a loss function and HP optimization, respectively, based on the data analysis of step 600, performance objectives 602, and the architecture selected in step 604.”)
Pandev does not explicitly teach,
defining a loss function of the form:
L
o
s
s
=
∑
i
ω
i
∙
M
i
wherein one of the component loss functions relates to tool matching;
and ω.sub.i is a coefficient;
and optimizing the metrology algorithm to obtain an optimal set of input parameters, which when applied to the metrology algorithm produces measurements that are consistent when made by said inspection tool or by different inspection tools of similar type; wherein optimizing the metrology algorithm includes: obtaining respective measurements for multiple locations across two different tools; creating respective distributions of the measurements for each of the two different tools; and using distribution-based metrics to measure similarity between the two distributions.
Kendall teaches,
defining a loss function of the form:
L
o
s
s
=
∑
i
ω
i
∙
M
i
and ω.sub.i is a coefficient; (Section 3 on Pg. 3 teaches “Multi-task learning concerns the problem of optimizing a model with respect to multiple objectives. It is prevalent in many deep learning problems.” Where equation 1 shows the claimed equation.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Pandev with defining a loss function of the form: wherein one of the component loss functions relates to tool matching.
One of ordinary skill would have been motivated to modify Pandev, because Pandev teaches using multiple loss functions depending on input data metrics and performance objectives as seen in Para. [0148]. Tool to tool matching is seen as one of the performance objectives in Para. [0154]. Therefore, it would be obvious to combine loss functions wherein one of the loss functions is directed to tool matching. Furthermore, Kendall teaches that equation 1 is the dominant approach for combining loss functions as seen in Section 3 on page 3.
The combination of Pandev and Kendall does not explicitly teach,
and optimizing the metrology algorithm to obtain an optimal set of input parameters, which when applied to the metrology algorithm produces measurements that are consistent when made by said inspection tool or by different inspection tools of similar type;
wherein optimizing the metrology algorithm includes: obtaining respective measurements for multiple locations across two different tools; creating respective distributions of the measurements for each of the two different tools; and using distribution-based metrics to measure similarity between the two distributions.
Pandev (2021) teaches,
and optimizing the metrology algorithm to obtain an optimal set of input parameters, which when applied to the metrology algorithm produces measurements that are consistent when made by said inspection tool or by different inspection tools of similar type; (Para. [0055] teaches “At each iteration, the optimization function drives changes to the weighting values, W, and bias values, b, of the neural network model, h.sub.W,b(.Math.) that minimize the optimization function. When the optimization function reaches a sufficiently low value, the measurement model is considered trained, and the trained measurement model 157 is stored in memory (e.g., memory 132).” Para. [0064] teaches “By way of non-limiting example, the physical attributes of the regularization structures includes any of measurement precision, tool to tool matching, wafer mean, within wafer range, tracking to reference, wafer to wafer matching, tracking to wafer split, etc.”)
wherein optimizing the metrology algorithm includes: obtaining respective measurements for multiple locations across two different tools; creating respective distributions of the measurements for each of the two different tools; and using distribution-based metrics to measure similarity between the two distributions. (Para. [0068] teaches “In some examples, a measurement performance metric includes distributions of measured values of parameters of interest across multiple tools to characterize tool to tool matching. The distributions may represent mean values across each wafer, values at each site, or both.” Para. [0076] teaches “real data from measurements of the same site measured by different tools to estimate tool-to-tool matching;”
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Pandev and Kendall with optimizing the metrology algorithm to obtain an optimal set of input parameters, which when applied to the metrology algorithm produces measurements that are consistent when made by said inspection tool or by different inspection tools of similar type; wherein optimizing the metrology algorithm includes: obtaining respective measurements for multiple locations across two different tools; creating respective distributions of the measurements for each of the two different tools; and using distribution-based metrics to measure similarity between the two distributions such as that of Pandev (2021).
One of ordinary skill would have been motivated to modify the combination of Pandev and Kendall, because Pandev teaches using multiple loss functions depending on input data metrics and performance objectives as seen in Para. [0148]. Tool to tool matching is seen as one of the performance objectives in Para. [0154]. In Para. [0017] Pandev (2021) teaches that using probability distributions physically regularizes optimization process providing significant improvement in measurement performance and reliability. Therefore, to improve reliability and performance one would be motivated to combine Pandev and Kendall with Pandev (2021).
With respect to claim 13,
Pandev does not explicitly teach,
wherein the coefficient ω.sub.i defines a relative importance of the respective component loss function within the loss function such that the higher the value of ω.sub.i the more effort is exerted by the optimization process to minimize the respective component loss function.
Kendall teaches,
wherein the coefficient ω.sub.i defines a relative importance of the respective component loss function within the loss function such that the higher the value of ω.sub.i the more effort is exerted by the optimization process to minimize the respective component loss function.( Section 3 Page 3 teaches “Namely, model performance is extremely sensitive to weight selection, wi, as illustratedinFigure2. These weigh hyper-parameters are expensive to tune, often taking many days for each trial.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Pandev, Kendall, and Pandev (2021) wherein the coefficient ω.sub.i defines a relative importance of the respective component loss function within the loss function such that the higher the value of ω.sub.i the more effort is exerted by the optimization process to minimize the respective component loss function.
One of ordinary skill would have been motivated to modify the combination of Pandev, Kendall, and Pandev (2021) because the larger the weight factor the more processing power that would be required to make the calculations.
With respect to claim 14,
Pandev does not explicitly teach,
The method according to claim 12, wherein the measurements include corresponding measurements taken at a same or similar location for each tool.
Pandev (2021) teaches,
wherein the measurements include corresponding measurements taken at a same or similar location for each tool. (Para. [0076] teaches “real data from measurements of the same site measured by different tools to estimate tool-to-tool matching;”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Pandev, Kendall, and Pandev (2021) wherein the measurements include corresponding measurements taken at a same or similar location for each tool such as that of Pandev (2021).
One of ordinary skill would have been motivated to modify the combination of Pandev, Kendall, and Pandev (2021) because relating measurements that were not taken at the same location would inherently have different results making it near impossible to relate values measured by the different tools together as it would introduce other variables into the system.
With respect to claim 16,
Pandev further teaches,
The method according to claim 12, wherein the component loss functions define one or more of the following: sensitivity defining a way to measure that changes in the object we are measuring are reflected in the results of the measurements; (Para. [00150] teaches “In another such embodiment, at least two of the multiple loss functions are configured for implementing different methods for regularization in the ASMLA that cannot otherwise be implemented in the ASMLA.” (i.e. regularization ensures that a model is not overfitted and is able to detect changes in the object)
external mean consistency i.e. matching given samples representing different tools we take samples from several tools of the same location; (Para. [0153] teaches “The data analysis step may therefore provide information about the number of samples in the training data, the type of data (e.g., design of experiment (DOE) data, nominal data, etc.), labeled or unlabeled data, DOF of the data, precision or tool to tool matching data, etc.”
With respect to claim 18,
Pandev further teaches,
A computer program product comprising a non-transitory computer readable medium storing program code, which, when executed by a computer processor, carries out the method according to claim 12. (Para. [0028] teaches “FIG. 15 is a block diagram illustrating one embodiment of a non-transitory computer-readable medium storing program instructions for causing a computer system to perform a computer-implemented method described herein.” Para. [0049] teaches “Computer subsystem 36 may be coupled to the detectors of the output acquisition subsystem in any suitable manner (e.g., via one or more transmission media, which may include “wired” and/or “wireless” transmission media) such that the computer subsystem can receive the output generated by the detectors. Computer subsystem 36 may be configured to perform a number of functions with or without the output of the detectors including the steps and functions described further herein.”)
Claim 15 is rejected under 35 U.S.C. 103 as being unpatentable over Pandev (US 20250259051 A1), Kendall (Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics; 2018), and Pandev (2021) (US 20210165398 A1) as applied to claim 12 above, and further in view of Kuznetsov (US 20240142948 A1).
With respect to claim 15,
Pandev does not explicitly teach,
The method according to claim 12, wherein the distribution-based metrics are based on any one in the group consisting of {Jensen-Shannon Divergence (JSD), Kullback Liebler (KL), Total Variation (TV), x.sup.2, Hellinger distance (HL), Le cam distance (LC)}.
Kuznetsov teaches,
wherein the distribution-based metrics are based on any one in the group consisting of {Jensen-Shannon Divergence (JSD), Kullback Liebler (KL), Total Variation (TV), x.sup.2, Hellinger distance (HL), Le cam distance (LC)}. (Para. [0034] teaches “FIG. 8 depicts a chart of accuracy metric values associated with the KL divergence calculations associated with each tool of the fleet of tools.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Pandev, Kendall, and Pandev (2021) wherein the distribution-based metrics are based on any one in the group consisting of {Jensen-Shannon Divergence (JSD), Kullback Liebler (KL), Total Variation (TV), x.sup.2, Hellinger distance (HL), Le cam distance (LC)} such as that of Kuznetsov.
One of ordinary skill would have been motivated to modify the combination of Pandev, Kendall, and Pandev (2021) because Kullback Liebler (KL) is a well-known tool in statistics that is useful for data compression, consistent model convergence, and positive valued solutions. Therefore, it would be useful for finding the distribution-based metrics.
Prior Art Analysis
Claims 1-11 and 17 stand rejected under 35 U.S.C. 101 and 35 U.S.C. 112(b), however, none of the known prior art could be applied to the claims for the following reasons.
With respect to claims 1 and 8,
Houben (US 20240054669 A1) teaches,
A system for determining three-dimensional information of a structure of a patterned substrate. The 3D information can be determined using one or more models configured to generate 3D information using only a single image of a patterned substrate. (Abstract) They further teach adjusting model parameters to cause minimization of a performance function where the performance function comprises a loss function. (Para(s). [0066-0067]) The loss function is represented by the sum of the similarity loss function and another function. (Para. [0070]) They also teach adjusting one or more parameters based on the performance function where the performance function is compared against a threshold. (Para. [0077]) Lastly, they teach a conversion function that may be a non-linear function. (Para. [0063) However, they do not explicitly teach that one of the component loss function relates to tool matching or applying a positive gain for in range measurements whose difference from a target measurement is less than a threshold and applying a steep penalty otherwise.
Pandev (2021) (US 20210165398 A1) teaches,
A system for training and implementing metrology recipes based on performance metrics employed to quantitatively characterize the measurement performance of a metrology system in a particular measurement application. (Abstract) They further teach a total output error which represents an aggregation of all errors arising in measurement including tool-to-tool matching errors. (Para. [0013]) They also describe a loss function that measures the difference between real measurement data and simulated measurement data. Lastly, they teach a measurement performance metric includes distributions of measured values of parameters of interest across multiple tools to characterize tool to tool matching. (Para. [0068]) However, they do not explicitly teach an aggregate loss function or applying a positive gain for in range measurements whose difference from a target measurement is less than a threshold and applying a steep penalty otherwise.
Kendall (Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics; 2018) teaches,
A principled approach to multi-task deep learning which weighs multiple loss functions by considering the homoscedastic uncertainty of each task. (Abstract) They further teach a weighted linear sum of losses for each individual task. (Section 3) However, they do not explicitly teach that any of the loss functions relate to tool matching.
Groenendijk (MULTI-LOSS WEIGHTING WITH COEFFICIENT OF VARIATIONS; 2020) teaches,
Optimizing an objective function defined as a weighted linear combination of multiple losses. (Abstract) They further teach that the model performance is sensitive to choosing the correct weighting values and that these weighting values can vary over time. (Introduction) However, they do not explicitly teach that one of the component loss function relates to tool matching or applying a positive gain for in range measurements whose difference from a target measurement is less than a threshold and applying a steep penalty otherwise.
As seen above none of the known prior art explicitly teaches and it would be non-obvious to
combine the known prior art to teach,
“and wherein the loss calculator is configured to amplify each component loss function M_i by a non-linear function that compares an actual value of the component loss function M_i with the respective target measurement and applies a positive gain for in-range measurements whose difference from the respective target measurement is less than a prescribed threshold, while for out-of-range measurements whose difference from the respective target measurement exceeds said threshold, applies a steep penalty that swamps any cumulative gains associated with other component loss functions.”
Therefore, prior art cannot be applied to claims 1-11 and 17.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner
should be directed to JOSHUA L FORRISTALL whose telephone number is 703-756-4554. The examiner
can normally be reached Monday-Friday 8:30 AM- 5 PM.
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, Andrew Schechter can be reached on 571-272-2302. 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.
/JOSHUA L FORRISTALL/Examiner, Art Unit 2857
/ANDREW SCHECHTER/Supervisory Patent Examiner, Art Unit 2857
Prosecution Insights