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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 01/15/2026 has been entered.
Response To Arguments
Remarks page 13, Applicant contends:
“Agreement was reached that the amendment ‘wherein the polishing recipe is used for polishing wafers’ overcomes the 101 rejection.”
Response:
The examiner and applicant discussed the possibility of satisfying 101 by utilizing the generated data in the claims in a particular machine (MPEP 2106.05(b)). However, while a possibility of satisfying 101 was noted, no particular wording was agreed upon during the interview. As a result, “wherein the polishing recipe is used for polishing wafers” is seen as needing to be given a prima facie case in the current office action.
Remarks page 14-15, Applicant contends:
“The examiner’s analysis under 35 U.S.C. 101 does not comport with the controlling guidance set forth in the MPEP and recent USPTO eligibility instructions.”
Response:
The engineer being able to perform the step is not utilizing the specification to read into the claims, but instead the specification is being used to support that the step can be a mental process, thus the claims are simply utilizing a mental process within a generic computer (MPEP 2106.04(a)(2)(3): “An example of a case identifying a mental process performed in a computer environment as an abstract idea is Symantec Corp., 838 F.3d at 1316-18, 120 USPQ2d at 1360. In this case, the Federal Circuit relied upon the specification when explaining that the claimed electronic post office, which recited limitations describing how the system would receive, screen and distribute email on a computer network, was analogous to how a person decides whether to read or dispose of a particular piece of mail and that ‘with the exception of generic computer-implemented steps, there is nothing in the claims themselves that foreclose them from being performed by a human, mentally or with pen and paper’.”).
Aspects of the claims, like the top ring, are not seen as being hardware within the claim for a particular machine for the abstract ideas, as the top ring is noted to be merely an aspect for data gathering (“based on area response data acquired by changing a pressure for each area in a top ring…”)
Remarks page 15, Applicant contends:
The amended claims now include the feature of a polishing controller configured to control the devices in the polishing apparatus according to the determined polishing recipe, thus it is a practical application in which the claimed invention is integrated into a specific technological process.
Response:
Applicant’s arguments with respect to claim(s) 1 have been considered but are moot because the new ground of rejection contain elements that have not been previously examined or does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
The arguments in regards to the 101 rejections are not seen as persuasive, thus the 101 rejections are maintained.
Remarks page 16-17, Applicant contends:
Dhandapani does not teach “screening” as performed in the claims.
Response:
Dhandapani was not intended to be taken as teaching all of the elements related to the screening. Dhandapani is intended to teach the screening unit in combination with Bhaskar. The current claim rejections have been updated to help make the rejection more clear. Dhandapani supposedly teaching a calculation instead of a neural network is addressed by the combination and then in the motivation to combine with Bhaskar. Elements related to what Dhandapani teaches that are relevant to the combination are also noted near the associated elements in the “Dhandapani does not explicitly teach:” section for claim 1.
Remark page 17, Applicant contends:
Godbole does not teach reconstructing CMP area response data into an irregularity-removed profile suitable for simulation.
Response:
Godbole, as noted in the previous rejection for claim 1, was used to help teach aspects related to the irregularity presence or absence estimation unit. Aspects related to an irregularity removed profile suitable for simulation is interpreted as referring to aspects related to the screening unit, which the elements relate to that are taught by Bhaskar in combination with the primary reference Dhandapani. The current office action in the rejection for claim 1 under 103 notes the details in regards to the combination and a previous version of the rejection exists in the previous office action in claim 1 under 103.
Remarks page 17-18, Applicant contends:
The combination of references with Dhandapani is based on generalized assertions of improved results from neural networks and overlapping fields of endeavor.
Response:
The motivations to combine with Dhandapani often noted improved results from neural networks as many aspects of the current invention are related to the use of neural networks for performing aspects of the process of lithography or polishing wafers. The combinations have motivations that provide reasonings as to why one of ordinary skill in the art would feel motivated to utilize the combination such as with Godbole where Godbole taught the effectiveness of using machine learning for detecting irregularities or defects for wafers. Aspects of the motivations have had wording adjusted in the current office action to help make the motivations clearer, including noting further that in Godbole not only are machine learning models good for detecting irregularities, but the need for better detection is arising as a result of demand for more pure silicon [Godbole Introduction page 1].
The combinations with Dhandapani are not seen as unconventional, as the combinations utilize features all within art related to Dhandapani and utilize elements that would not require drastic changes to Dhandapani to achieve the improvement from the combination. As noted more clearly in the motivations of the current office action, the different units claimed (such as the irregularity presence or absence estimation unit) have related aspects within Dhandapani. Thus updating an existing aspect within Dhandapani, such as utilize a detection of irregularities using machine learning from Godbole, as the detection of irregularities would not prevent the utilization of the other aspects taught within Dhandapani for the currently claimed invention. Bhaskar is utilized to help address the screening unit, which works well in combination with Dhandapani having a “desired thickness profile” as such a profile could be acquired through manners such as the method taught via Bhaskar’s use of machine learning for nominal instances (refer to the claim 1 rejection and motivations for detailed quotes). Emami-Naeini works in combination with the teachings of Dhandapani to have an improved system from a feedback method on results, which Dhandapani already notes aspects related to such systems in paragraphs 27 and 36, thus the combination with Emami-Naeini would not deviate heavily from the teachings of Dhandapani in order to add the systems being used to teach “response data correction unit” (refer to the claim 2 rejection and motivations for detailed quotes).
Remarks page 19, Applicant contends:
Emami-Naeini does not disclose the aspects related to the acceptance evaluation unit.
Response:
Emami-Naeini teaching “ideal” outcomes is not seen as not properly teaching being able to use actual wafer data. The noting of values being “ideal” does not mean one of ordinary skill in the art could not consider a wanted value that was actual measured “ideal”. Emami-Naeini also teaches that the desired product characteristics are compared with actual being produced values ([Emami-Naeini 3 Control of Semiconductor Proesses page 4]: “Thus, the regulator uses the difference between the desired product characteristics and those actually being produced to compute corrections to the nominal process inputs computed by the planner; this is the feedback controller.”), thus the use of actual data is known in Emami-Naeini and desired product characteristics are comparable to actual values if not actual values themselves. The desired product characteristics are also seen as being able to be actual values as Emami-Naeini notes some methods stopped upon achieving the desired result, thus the desired result is not a value unachievable ([Emami-Naeini 3 Control Of Semiconductor Processes page 5]: “Open-loop control has been the most common strategy until recently; actuators are held constant. End-point control uses an in-situ sensor to detect the end-point of the process, i.e., to detect when the desired process result has been achieved, at which point in time the process is stopped.”.)
Emami-Naeini is considered teaching that the elements only occur when the result is not considered acceptable. Emami-Naeini methods are not considered being performed forever, thus the iterations performed to improve stop when if the wanted result is achieved. This means if the wanted result was the first result, then an iteration of improvement would not have to perform anything to improve the result, as the result is already acquired. This is further supported by different aspects noted in Emami-Naeini such as [Emami-Naeini III. Control of Semiconductor Processes A. Model Based Control page 4]: “The controller’s performance on the actual equipment can be determined and design iterations can be carried out if necessary.” and [Emami-Naeini 3 Control Of Semiconductor Processes page 5]: “Open-loop control has been the most common strategy until recently; actuators are held constant. End-point control uses an in-situ sensor to detect the end-point of the process, i.e., to detect when the desired process result has been achieved, at which point in time the process is stopped.”.
The arguments from the applicant involving 103 are not seen as persuasive, as a result, the 103 rejections are maintained.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitation(s) is/are: irregularity-presence-or-absence estimation unit… [Current Application 0091] screening unit… [Current Application 0091] simulation unit… [Current Application 0091] in claim 1.
Claim 2 contains the limitations of acceptance evaluation unit… [Current Application 0091] response data correction unit… [Current Application 0091].
All other claims, excluding claims 5-8 which only depend upon such claims, are claims that recite the above units or recite a combination of such units. Examples include claim 3 which recites simulation unit… [Current Application 0091] acceptance evaluation unit… [Current Application 0091] response data correction unit… [Current Application 0091] , or examples include claim 10 which is analogous to claim 1.
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Paragraphs 83-85, and 91 of specification is used as the interpretation of the structure for the units in the claims. [Current application 0091]: “The control unit 72 is a control section that performs various processes for the polishing recipe determination device 70. As illustrated in Fig. 5, the control unit 72 has an irregularity-presence-or-absence estimation unit 72a, the screening unit 72b, a simulation unit 72c, an acceptance evaluation unit 72d, and a response data correction unit 72e. These units may be implemented by a processor in the polishing recipe determination device 70 executing a predetermined program or may be mounted by hardware.”
The units, as noted above, are a part of the polishing recipe determination device 70, which is shown in Figure 5 of the drawings. Paragraph 83 of the specification notes that the polishing recipe determination devices utilizes a bus for transmitting information between the elements ([Current Specification 0083]: “These units are connected to each other being capable of communicating with each other through a bus.”). Paragraph 85 then mentions the storage unit is a hard disk or similar hardware ([Current Specification 0085]: “The storage unit 73 is, for example, a magnetic data storage such as a hard disk. The storage unit 73 stores various items of data handled by the control unit 72. The storage unit 73 stores area response data 73a, a polishing recipe 73b, an actual polishing result 73c, and a simulation polishing result 73d.”). The combination of the teachings of paragraph 91 and paragraphs 83-85 are seen as noting units that could be software or hardware that are implemented in hardware, such as the bus and hard disk.
Claim Objections
Claim 1 objected to because of the following informalities: claim 1 recites “the apparatus further comprising a polishing controller” where “the apparatus” is seen as intending to be “the polishing apparatus”. Appropriate correction is required.
Claim 4 is objected to because of the following informalities: claim 4 recites “a machine learning relationship” for both “the first trained model” and “the second trained model”. Claim 1 already recites the “a first trained model” or “a second trained model” “trained on a machine-learning relationship”. As a result, claim 4 is interpreted as intending to be “the machine learning relationship” for both “the first trained model” and “the second trained model”. Appropriate correction is required.
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 towards an abstract idea without significantly more.
In regards to Claim 1:
Step 1: Is the claim directed towards a process, machine, manufacture, or composition of matter?
Yes, it is directed towards a device, so a machine.
Step 2A Prong 1: Does the claim recite a law of nature, a natural phenomenon, or an abstract idea?
Yes, the claim does recite a(n) abstract idea.
Claim 1 recites the following abstract ideas:
the irregularity-presence-or-absence estimation unit being configured to automatically estimate and output, using new area response data, acquired during polishing the wafer, as an input parameter, presence or absence of an irregularity in the new area response data
This limitation is directed towards the abstract idea of a mental process, or a concept performed in the human mind, including observation, evaluation, judgement or opinion (see MPEP 2106.04(a)(2) subsection 3). Here it is seen as evaluation.
the screening unit being configured to, when the irregularity-presence-or-absence estimation unit automatically estimates that an irregularity is present in the new area response data
This limitation is directed towards the abstract idea of a mental process, or a concept performed in the human mind, including observation, evaluation, judgement or opinion (see MPEP 2106.04(a)(2) subsection 3). Here it is seen as evaluation.
automatically estimate and output new area response data after removal of the irregularity using, as an input parameter, the new area response data that was used to automatically estimate that the irregularity is present
This limitation is directed towards the abstract idea of a mental process, or a concept performed in the human mind, including observation, evaluation, judgement or opinion (see MPEP 2106.04(a)(2) subsection 3). Here it is seen as evaluation.
and a simulation unit configured to determine a polishing recipe by simulation based on the new area response data that was used to automatically estimate that no irregularity is present by the irregularity-presence-or-absence estimation unit, or the new area response data after removal of the irregularity automatically estimated by the screening unit, wherein the polishing recipe is used for polishing wafers
This limitation is directed towards the abstract idea of a mental process, or a concept performed in the human mind, including observation, evaluation, judgement or opinion (see MPEP 2106.04(a)(2) subsection 3). Here it is seen as evaluation.
The addition of noting what the polishing recipe is used for does not claim in the claim limitations that the recipe is used by some system to polish wafers. The limitation merely notes that the use case of the recipe is for polishing wafers. That means the use case is noted but actually using the recipe to polish wafers is not claimed. Can refer to MPEP 2106.05(b) for particular machine for satisfying 101 requirements.
Step 2A Prong 2: Does the claim recite additional elements that integrate the exception into a practical application of the exception?
No, the application does not recite any additional elements that would integrate the abstract idea into a practical application.
Claim 1 recites the following additional elements:
A polishing apparatus determining a polishing recipe for a wafer based on area response data acquired by changing a pressure for each area in a top ring applied to a corresponding area in the wafer, the apparatus further comprising a polishing controller configured to control devices in the polishing apparatus according to the determined polishing recipe so that the wafer is polished, the apparatus comprising
This limitation is directed towards linking or indicating a field of use or technological environment (see MPEP 2106.05(h)).
an irregularity-presence-or-absence estimation unit having a first trained model trained on a machine- learning relationship between past area response data, acquired from one or more prior wafers, and whether an irregularity is present in the past area response data
At a high level of generality, this is an activity of using a machine learning model or relationship as an “apply it” use (see MPEP 2106.05(f)).
a screening unit having a second trained model trained on a machine-learning relationship between the past area response data with an irregularity and past area response data after removal of the irregularity
At a high level of generality, this is an activity of using a machine learning model or relationship as an “apply it” use (see MPEP 2106.05(f)).
Step 2B: Does the claim as a whole amount to significantly more than the judicial exception?
No, the claim as a whole does not amount to significantly more than the judicial exception. All elements of the claim, viewed individually or wholistically, do not provide an inventive concept or otherwise significantly more than the abstract idea itself.
Claim 1 recites the following additional elements:
A polishing apparatus determining a polishing recipe for a wafer based on area response data acquired by changing a pressure for each area in a top ring applied to a corresponding area in the wafer, the apparatus further comprising a polishing controller configured to control devices in the polishing apparatus according to the determined polishing recipe so that the wafer is polished, the apparatus comprising
This limitation is directed towards linking or indicating a field of use or technological environment (see MPEP 2106.05(h)). Limitations that amount to merely linking/indicating to a field of use or technological environment, such as determining a polishing recipe (see MPEP 2106.05(h)(x)), do not amount to significantly more than the exception itself
an irregularity-presence-or-absence estimation unit having a first trained model trained on a machine- learning relationship between past area response data, acquired from one or more prior wafers, and whether an irregularity is present in the past area response data
At a high level of generality, this is an activity of using a machine learning model or relationship as an “apply it” use (see MPEP 2106.05(f)). At said high level of generality, a machine learning model or relationship appears to be an implementation of the abstract idea on a computer, so merely using a computer as a tool to perform the abstract idea
a screening unit having a second trained model trained on a machine-learning relationship between the past area response data with an irregularity and past area response data after removal of the irregularity
At a high level of generality, this is an activity of using a machine learning model or relationship as an “apply it” use (see MPEP 2106.05(f)). At said high level of generality, a machine learning model or relationship appears to be an implementation of the abstract idea on a computer, so merely using a computer as a tool to perform the abstract idea
In regards to Claim 2:
Step 2A Prong 1: Does the claim recite a law of nature, a natural phenomenon, or an abstract idea?
Yes, the claim does recite a(n) abstract idea.
Claim 2 recites the following abstract ideas:
an acceptance evaluation unit configured to compare an actual polishing result obtained by actually polishing using the polishing recipe with a simulation polishing result obtained by simulation using the polishing recipe to automatically evaluate an acceptance of the actual polishing result
This limitation is directed towards the abstract idea of a mental process, or a concept performed in the human mind, including observation, evaluation, judgement or opinion (see MPEP 2106.04(a)(2) subsection 3). Here it is seen as evaluation.
the response data correction unit being configured to, when the acceptance evaluation unit automatically evaluates non-acceptance, automatically estimate and output corrected area response data using the actual polishing result automatically evaluated as non-acceptance, the simulation polishing result, and the area response data used for determination of a polishing recipe at that time as input parameters
This limitation is directed towards the abstract idea of a mental process, or a concept performed in the human mind, including observation, evaluation, judgement or opinion (see MPEP 2106.04(a)(2) subsection 3). Here it is seen as evaluation.
wherein the simulation unit again determines a polishing recipe by simulation based on the corrected area response data automatically estimated by the response data correction unit
This limitation is directed towards the abstract idea of a mental process, or a concept performed in the human mind, including observation, evaluation, judgement or opinion (see MPEP 2106.04(a)(2) subsection 3). Here it is seen as evaluation.
Step 2A Prong 2: Does the claim recite additional elements that integrate the exception into a practical application of the exception?
No, the application does not recite any additional elements that would integrate the abstract idea into a practical application.
Claim 2 recites the following additional elements:
a response data correction unit having a third trained model trained on a machine-learning relationship between: (A) a past actual polishing result, a past simulation polishing result, and past area response data used for determination of a polishing recipe at that time, and (B) past corrected area response data
At a high level of generality, this is an activity of using a machine learning model or relationship as an “apply it” use (see MPEP 2106.05(f)).
Step 2B: Does the claim as a whole amount to significantly more than the judicial exception?
No, the claim as a whole does not amount to significantly more than the judicial exception. All elements of the claim, viewed individually or wholistically, do not provide an inventive concept or otherwise significantly more than the abstract idea itself.
Claim 2 recites the following additional elements:
a response data correction unit having a third learned model machine-learning relationship between: (A) a past actual polishing result, a past simulation polishing result, and past area response data used for determination of a polishing recipe at that time, and (B) past corrected area response data
At a high level of generality, this is an activity of using a machine learning model or relationship as an “apply it” use (see MPEP 2106.05(f)). At said high level of generality, a machine learning model or relationship appears to be an implementation of the abstract idea on a computer, so merely using a computer as a tool to perform the abstract idea
In regards to Claim 3:
Step 1: Is the claim directed towards a process, machine, manufacture, or composition of matter?
Yes, it is directed towards a device, so a machine.
Step 2A Prong 1: Does the claim recite a law of nature, a natural phenomenon, or an abstract idea?
Yes, the claim does recite a(n) abstract idea.
Claim 3 recites the following abstract ideas:
a simulation unit configured to determine a polishing recipe by simulation based on new area response data
This limitation is directed towards the abstract idea of a mental process, or a concept performed in the human mind, including observation, evaluation, judgement or opinion (see MPEP 2106.04(a)(2) subsection 3). Here it is seen as evaluation.
an acceptance evaluation unit configured to compare an actual polishing result obtained by actually polishing using the polishing recipe with a simulation polishing result obtained by simulation using the polishing recipe to automatically evaluate an acceptance of the actual polishing result
This limitation is directed towards the abstract idea of a mental process, or a concept performed in the human mind, including observation, evaluation, judgement or opinion (see MPEP 2106.04(a)(2) subsection 3). Here it is seen as evaluation.
the response data correction unit being configured to, when the acceptance evaluation unit automatically evaluates non-acceptance, automatically estimate and output corrected area response data using the actual polishing result automatically evaluated as non-acceptance, the simulation polishing result, and the area response data used for determination of a polishing recipe at that time as input parameters
This limitation is directed towards the abstract idea of a mental process, or a concept performed in the human mind, including observation, evaluation, judgement or opinion (see MPEP 2106.04(a)(2) subsection 3). Here it is seen as evaluation.
wherein the simulation unit again determines a polishing recipe by simulation based on the corrected area response data automatically estimated by the response data correction unit
This limitation is directed towards the abstract idea of a mental process, or a concept performed in the human mind, including observation, evaluation, judgement or opinion (see MPEP 2106.04(a)(2) subsection 3). Here it is seen as evaluation.
Step 2A Prong 2: Does the claim recite additional elements that integrate the exception into a practical application of the exception?
No, the application does not recite any additional elements that would integrate the abstract idea into a practical application.
Claim 3 recites the following additional elements:
A polishing recipe determination device determining a polishing recipe based on area response data acquired by changing a pressure for each area in a top ring, the device comprising
This limitation is directed towards linking or indicating a field of use or technological environment (see MPEP 2106.05(h)).
and a response data correction unit having a third trained model trained on a machine-learning relationship between: (A) a past actual polishing result, a past simulation polishing result, and past area response data used for determination of a polishing recipe at that time, and (B) past corrected area response data
At a high level of generality, this is an activity of using a machine learning model or relationship as an “apply it” use (see MPEP 2106.05(f)).
Step 2B: Does the claim as a whole amount to significantly more than the judicial exception?
No, the claim as a whole does not amount to significantly more than the judicial exception. All elements of the claim, viewed individually or wholistically, do not provide an inventive concept or otherwise significantly more than the abstract idea itself.
Claim 3 recites the following additional elements:
A polishing recipe determination device determining a polishing recipe based on area response data acquired by changing a pressure for each area in a top ring, the device comprising
This limitation is directed towards linking or indicating a field of use or technological environment (see MPEP 2106.05(h)). Limitations that amount to merely linking/indicating to a field of use or technological environment, such as determining a polishing recipe (see MPEP 2106.05(h)(x)), do not amount to significantly more than the exception itself
and a response data correction unit having a third trained model trained on a machine-learning relationship between: (A) a past actual polishing result, a past simulation polishing result, and past area response data used for determination of a polishing recipe at that time, and (B) past corrected area response data
At a high level of generality, this is an activity of using a machine learning model or relationship as an “apply it” use (see MPEP 2106.05(f)). At said high level of generality, a machine learning model or relationship appears to be an implementation of the abstract idea on a computer, so merely using a computer as a tool to perform the abstract idea
In regards to Claim 4:
Step 2A Prong 1: Does the claim recite a law of nature, a natural phenomenon, or an abstract idea?
Yes, the claim does recite a(n) abstract idea.
Claim 4 recites the following abstract ideas:
wherein the first trained model is trained on a machine-learning relationship between: (A) the past area response data and (B) whether an irregularity is present and a type of an irregularity in the past area response data
This limitation is directed towards the abstract idea of a mental process, or a concept performed in the human mind, including observation, evaluation, judgement or opinion (see MPEP 2106.04(a)(2) subsection 3). Here it is seen as evaluation.
and the irregularity-presence-or-absence estimation unit automatically estimates and outputs, using new area response data as an input parameter, presence or absence of an irregularity and a type of the irregularity in the new area response data
This limitation is directed towards the abstract idea of a mental process, or a concept performed in the human mind, including observation, evaluation, judgement or opinion (see MPEP 2106.04(a)(2) subsection 3). Here it is seen as evaluation.
and the second trained model is trained on a machine-learning relationship between: (A) the past area response data with an irregularity and a type of the irregularity, and (B) the past area response data after removal of the irregularity
This limitation is directed towards the abstract idea of a mental process, or a concept performed in the human mind, including observation, evaluation, judgement or opinion (see MPEP 2106.04(a)(2) subsection 3). Here it is seen as evaluation.
and the screening unit automatically estimates and outputs, when the irregularity-presence-or- absence estimation unit automatically estimates that an irregularity is present in the new area response data, new area response data after removal of the irregularity using the new area response data that was used to automatically estimate that the irregularity is present and the automatically estimated type of the irregularity as input parameters
This limitation is directed towards the abstract idea of a mental process, or a concept performed in the human mind, including observation, evaluation, judgement or opinion (see MPEP 2106.04(a)(2) subsection 3). Here it is seen as evaluation.
In regards to Claim 5:
Step 2A Prong 1: Does the claim recite a law of nature, a natural phenomenon, or an abstract idea?
Yes, the claim does recite a(n) abstract idea.
Claim 5 recites the following abstract ideas:
wherein the type of an irregularity includes one or more than one of an asymmetric irregular point, an edge irregular point at time of applying a pressure to a center area, and a polar irregular point
This limitation is directed towards the continuation of abstract ideas of a mental process, or a concept performed in the human mind, including observation, evaluation, judgement or opinion (see MPEP 2106.04(a)(2) subsection 3) from claim 4.
In regards to Claim 6:
Step 2A Prong 1: Does the claim recite a law of nature, a natural phenomenon, or an abstract idea?
Yes, the claim does recite a(n) abstract idea.
Claim 6 recites the following abstract ideas:
wherein the area response data is data that a variation in an amount of removal by polishing is divided by a variation in an air bag pressure on positions on a wafer
This limitation is directed towards the continuation of abstract ideas of a mental process, or a concept performed in the human mind, including observation, evaluation, judgement or opinion (see MPEP 2106.04(a)(2) subsection 3) from claim 1.
In regards to Claim 7:
Step 2A Prong 1: Does the claim recite a law of nature, a natural phenomenon, or an abstract idea?
Yes, the claim does recite a(n) abstract idea.
Claim 7 recites the following abstract ideas:
wherein the area response data is data that a variation in a polishing removal rate is divided by a variation in an air bag pressure on positions on a wafer
This limitation is directed towards the continuation of abstract ideas of a mental process, or a concept performed in the human mind, including observation, evaluation, judgement or opinion (see MPEP 2106.04(a)(2) subsection 3) from claim 1.
In regards to Claim 8:
Step 2A Prong 1: Does the claim recite a law of nature, a natural phenomenon, or an abstract idea?
Yes, the claim does recite a(n) abstract idea.
Claim 8 recites the following abstract ideas:
wherein the area response data is data that for positions on a wafer, a variation in a remaining film on the wafer is divided by a variation in an air bag pressure
This limitation is directed towards the continuation of abstract ideas of a mental process, or a concept performed in the human mind, including observation, evaluation, judgement or opinion (see MPEP 2106.04(a)(2) subsection 3) from claim 1.
In regards to Claim 9:
Step 2A Prong 1: Does the claim recite a law of nature, a natural phenomenon, or an abstract idea?
Yes, the claim does recite a(n) abstract idea.
Claim 9 recites the following abstract ideas:
A polishing apparatus comprising the polishing recipe determination device according to claim 1
This limitation is directed towards the continuation of abstract ideas of a mental process, or a concept performed in the human mind, including observation, evaluation, judgement or opinion (see MPEP 2106.04(a)(2) subsection 3) from claim 1.
In regards to Claim 10:
Step 1: Is the claim directed towards a process, machine, manufacture, or composition of matter?
Yes, it is directed towards a device, so a machine.
Step 2A Prong 1: Does the claim recite a law of nature, a natural phenomenon, or an abstract idea?
Yes, the claim does recite a(n) abstract idea.
Claim 10 recites the same abstract ideas as analogous claim 1.
Step 2A Prong 2: Does the claim recite additional elements that integrate the exception into a practical application of the exception?
No, the application does not recite any additional elements that would integrate the abstract idea into a practical application.
Claim 10 recites the same additional elements as analogous claim 1.
Step 2B: Does the claim as a whole amount to significantly more than the judicial exception?
No, the claim as a whole does not amount to significantly more than the judicial exception. All elements of the claim, viewed individually or wholistically, do not provide an inventive concept or otherwise significantly more than the abstract idea itself.
Claim 10 recites the same additional elements as analogous claim 1.
In regards to Claim 11:
Step 2A Prong 1: Does the claim recite a law of nature, a natural phenomenon, or an abstract idea?
Yes, the claim does recite a(n) abstract idea.
Claim 11 recites the same abstract ideas as analogous claim 2.
Step 2A Prong 2: Does the claim recite additional elements that integrate the exception into a practical application of the exception?
No, the application does not recite any additional elements that would integrate the abstract idea into a practical application.
Claim 11 recites the same additional elements as analogous claim 2.
Step 2B: Does the claim as a whole amount to significantly more than the judicial exception?
No, the claim as a whole does not amount to significantly more than the judicial exception. All elements of the claim, viewed individually or wholistically, do not provide an inventive concept or otherwise significantly more than the abstract idea itself.
Claim 11 recites the same additional elements as analogous claim 2.
In regards to Claim 12:
Step 1: Is the claim directed towards a process, machine, manufacture, or composition of matter?
Yes, it is directed towards a device, so a machine.
Step 2A Prong 1: Does the claim recite a law of nature, a natural phenomenon, or an abstract idea?
Yes, the claim does recite a(n) abstract idea.
Claim 12 recites the same abstract ideas as claim 3.
Step 2A Prong 2: Does the claim recite additional elements that integrate the exception into a practical application of the exception?
No, the application does not recite any additional elements that would integrate the abstract idea into a practical application.
Claim 12 recites the same additional elements as claim 3.
Step 2B: Does the claim as a whole amount to significantly more than the judicial exception?
No, the claim as a whole does not amount to significantly more than the judicial exception. All elements of the claim, viewed individually or wholistically, do not provide an inventive concept or otherwise significantly more than the abstract idea itself.
Claim 12 recites the same additional elements as claim 3.
In regards to Claim 13:
Step 1: Is the claim directed towards a process, machine, manufacture, or composition of matter?
No, the claim is directed towards software per se.
Claim 13 recites the following software per se:
A polishing recipe determination program causing a computer to execute a process for determining a polishing recipe based on area response data acquired by changing a pressure for each area in a top ring, the program causing the computer to execute the steps of
The claim limitation directly try to claim a “program” for a computer
Step 2A Prong 1: Does the claim recite a law of nature, a natural phenomenon, or an abstract idea?
Yes, the claim does recite a(n) abstract idea.
Claim 13 recites the same abstract ideas as analogous claim 1.
Step 2A Prong 2: Does the claim recite additional elements that integrate the exception into a practical application of the exception?
No, the application does not recite any additional elements that would integrate the abstract idea into a practical application.
Claim 13 further recites additional elements in addition to the elements from analogous claim 1:
a computer to execute a process for determining a polishing recipe based on area response data acquired by changing a pressure for each area in a top ring, the program causing the computer to execute the steps of
This limitation is directed towards linking or indicating a field of use or technological environment (see MPEP 2106.05(h)).
At a high level of generality, this is an activity of using a machine learning model or relationship as an “apply it” use (see MPEP 2106.05(f)).
Step 2B: Does the claim as a whole amount to significantly more than the judicial exception?
No, the claim as a whole does not amount to significantly more than the judicial exception. All elements of the claim, viewed individually or wholistically, do not provide an inventive concept or otherwise significantly more than the abstract idea itself.
Claim 13 further recites additional elements in addition to the elements from analogous claim 1:
a computer to execute a process for determining a polishing recipe based on area response data acquired by changing a pressure for each area in a top ring, the program causing the computer to execute the steps of
This limitation is directed towards linking or indicating a field of use or technological environment (see MPEP 2106.05(h)). Limitations that amount to merely linking/indicating to a field of use or technological environment, such as determining a polishing recipe (see MPEP 2106.05(h)(x)), do not amount to significantly more than the exception itself
At a high level of generality, this is an activity of using a machine learning model or relationship as an “apply it” use (see MPEP 2106.05(f)). At said high level of generality, a machine learning model or relationship appears to be an implementation of the abstract idea on a computer, so merely using a computer as a tool to perform the abstract idea
In regards to Claim 14:
Step 2A Prong 1: Does the claim recite a law of nature, a natural phenomenon, or an abstract idea?
Yes, the claim does recite a(n) abstract idea.
Claim 14 recites the same abstract ideas as claim 2.
Step 2A Prong 2: Does the claim recite additional elements that integrate the exception into a practical application of the exception?
No, the application does not recite any additional elements that would integrate the abstract idea into a practical application.
Claim 14 recites the same additional elements as claim 2.
Step 2B: Does the claim as a whole amount to significantly more than the judicial exception?
No, the claim as a whole does not amount to significantly more than the judicial exception. All elements of the claim, viewed individually or wholistically, do not provide an inventive concept or otherwise significantly more than the abstract idea itself.
Claim 14 recites the same additional elements as claim 2.
In regards to Claim 15:
Step 1: Is the claim directed towards a process, machine, manufacture, or composition of matter?
No, the claim is directed towards software per se.
Claim 15 recites the following software per se
A polishing recipe determination program causing a computer to execute a process for determining a polishing recipe based on area response data acquired by changing a pressure for each area in a top ring, the program causing the computer to execute the steps of
Step 2A Prong 1: Does the claim recite a law of nature, a natural phenomenon, or an abstract idea?
Yes, the claim does recite a(n) abstract idea.
Claim 15 recites the same abstract ideas as claim 3.
Step 2A Prong 2: Does the claim recite additional elements that integrate the exception into a practical application of the exception?
No, the application does not recite any additional elements that would integrate the abstract idea into a practical application.
Claim 15 further recites additional elements in addition to the elements from claim 3:
a computer to execute a process for determining a polishing recipe based on area response data acquired by changing a pressure for each area in a top ring, the program causing the computer to execute the steps of
This limitation is directed towards linking or indicating a field of use or technological environment (see MPEP 2106.05(h)).
At a high level of generality, this is an activity of using a machine learning model or relationship as an “apply it” use (see MPEP 2106.05(f)).
Step 2B: Does the claim as a whole amount to significantly more than the judicial exception?
No, the claim as a whole does not amount to significantly more than the judicial exception. All elements of the claim, viewed individually or wholistically, do not provide an inventive concept or otherwise significantly more than the abstract idea itself.
Claim 15 further recites additional elements in addition to the elements from claim 3:
a computer to execute a process for determining a polishing recipe based on area response data acquired by changing a pressure for each area in a top ring, the program causing the computer to execute the steps of
This limitation is directed towards linking or indicating a field of use or technological environment (see MPEP 2106.05(h)). Limitations that amount to merely linking/indicating to a field of use or technological environment, such as determining a polishing recipe (see MPEP 2106.05(h)(x)), do not amount to significantly more than the exception itself
At a high level of generality, this is an activity of using a machine learning model or relationship as an “apply it” use (see MPEP 2106.05(f)). At said high level of generality, a machine learning model or relationship appears to be an implementation of the abstract idea on a computer, so merely using a computer as a tool to perform the abstract idea
In regards to Claim 16:
Step 1: Is the claim directed towards a process, machine, manufacture, or composition of matter?
Yes, it is directed towards a device, so a machine.
Step 2A Prong 1: Does the claim recite a law of nature, a natural phenomenon, or an abstract idea?
Yes, the claim does recite a(n) abstract idea.
Claim 16 recites the same abstract ideas as claim 1.
Step 2A Prong 2: Does the claim recite additional elements that integrate the exception into a practical application of the exception?
No, the application does not recite any additional elements that would integrate the abstract idea into a practical application.
Claim 16 further recites additional elements in addition to the elements already mentioned in claim 1:
A computer-readable recording medium recording a program causing a computer to execute a process for determining a polishing recipe based on area response data acquired by changing a pressure for each area in a top ring, the program causing the computer to execute the steps of:
This limitation is directed towards linking or indicating a field of use or technological environment (see MPEP 2106.05(h)).
At a high level of generality, this is an activity of using a machine learning model or relationship as an “apply it” use (see MPEP 2106.05(f)).
Step 2B: Does the claim as a whole amount to significantly more than the judicial exception?
No, the claim as a whole does not amount to significantly more than the judicial exception. All elements of the claim, viewed individually or wholistically, do not provide an inventive concept or otherwise significantly more than the abstract idea itself.
Claim 16 further recites additional elements in addition to the elements already mentioned in claim 1:
A computer-readable recording medium recording a program causing a computer to execute a process for determining a polishing recipe based on area response data acquired by changing a pressure for each area in a top ring, the program causing the computer to execute the steps of :
This limitation is directed towards linking or indicating a field of use or technological environment (see MPEP 2106.05(h)). Limitations that amount to merely linking/indicating to a field of use or technological environment, such as determining a polishing recipe (see MPEP 2106.05(h)(x)), do not amount to significantly more than the exception itself
At a high level of generality, this is an activity of using a machine learning model or relationship as an “apply it” use (see MPEP 2106.05(f)). At said high level of generality, a machine learning model or relationship appears to be an implementation of the abstract idea on a computer, so merely using a computer as a tool to perform the abstract idea
In regards to Claim 17:
Step 2A Prong 1: Does the claim recite a law of nature, a natural phenomenon, or an abstract idea?
Yes, the claim does recite a(n) abstract idea.
Claim 17 recites the same abstract ideas as claim 2.
Step 2A Prong 2: Does the claim recite additional elements that integrate the exception into a practical application of the exception?
No, the application does not recite any additional elements that would integrate the abstract idea into a practical application.
Claim 17 recites the same additional elements as claim 2.
Step 2B: Does the claim as a whole amount to significantly more than the judicial exception?
No, the claim as a whole does not amount to significantly more than the judicial exception. All elements of the claim, viewed individually or wholistically, do not provide an inventive concept or otherwise significantly more than the abstract idea itself.
Claim 17 recites the same additional elements as claim 2.
In regards to Claim 18:
Step 1: Is the claim directed towards a process, machine, manufacture, or composition of matter?
Yes, it is directed towards a device, so a machine.
Step 2A Prong 1: Does the claim recite a law of nature, a natural phenomenon, or an abstract idea?
Yes, the claim does recite a(n) abstract idea.
Claim 18 recites the same abstract ideas as claim 3.
Step 2A Prong 2: Does the claim recite additional elements that integrate the exception into a practical application of the exception?
No, the application does not recite any additional elements that would integrate the abstract idea into a practical application.
Claim 18 further recites additional elements in addition to the additional elements already mentioned in claim 3.
A computer-readable recording medium recording a program causing a computer to execute a process for determining a polishing recipe based on area response data acquired by changing a pressure for each area in a top ring, the program causing the computer to execute the steps of :
This limitation is directed towards linking or indicating a field of use or technological environment (see MPEP 2106.05(h)).
At a high level of generality, this is an activity of using a machine learning model or relationship as an “apply it” use (see MPEP 2106.05(f)).
Step 2B: Does the claim as a whole amount to significantly more than the judicial exception?
No, the claim as a whole does not amount to significantly more than the judicial exception. All elements of the claim, viewed individually or wholistically, do not provide an inventive concept or otherwise significantly more than the abstract idea itself.
Claim 18 further recites additional elements in addition to the additional elements already mentioned in claim 3.
A computer-readable recording medium recording a program causing a computer to execute a process for determining a polishing recipe based on area response data acquired by changing a pressure for each area in a top ring, the program causing the computer to execute the steps of :
This limitation is directed towards linking or indicating a field of use or technological environment (see MPEP 2106.05(h)). Limitations that amount to merely linking/indicating to a field of use or technological environment, such as determining a polishing recipe (see MPEP 2106.05(h)(x)), do not amount to significantly more than the exception itself
At a high level of generality, this is an activity of using a machine learning model or relationship as an “apply it” use (see MPEP 2106.05(f)). At said high level of generality, a machine learning model or relationship appears to be an implementation of the abstract idea on a computer, so merely using a computer as a tool to perform the abstract idea
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1, 4, 5, 9, 10, 13, 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Dhandapani et al (US 20190095797 A1) referred to as Dhandapani in this document, in further view of Bhaskar et al (US 20170193400 A1), referred to as Bhaskar in this document, and further in view of Godbole et al (“Neural decision directed segmentation of silicon defects”), referred to as Godbole in this document.
Regarding Claim 1:
Dhandapani teaches:
A polishing recipe determination device determining a polishing recipe for a wafer based on area response data acquired by changing a pressure for each area in a top ring applied to a corresponding area in the wafer
[Dhandapani 0025]: “Returning to FIG. 1, the chambers 52a-52c can be defined by a flexible membrane 54 having a bottom surface to which the substrate 10 is mounted. The carrier head 50 can also include a retaining ring [A polishing recipe determination device determining a polishing recipe for a wafer based on area response data acquired by changing a pressure for each area in a top ring applied to a corresponding area in the wafer] 56 to retain the substrate 10 below the flexible membrane 54.”
Where support for the process being related to wafer polishing recipes is further given in [Dhandapani 0013]: “Product wafers may be used for model refinement, leading to the actual profile of processed substrates being closer to a desired profile. Complex behavior of the polishing process in response to polishing parameters may be accounted for without explicit knowledge of the functional relationships.”
the apparatus further comprising a polishing controller configured to control devices in the polishing apparatus according to the determined polishing recipe so that the wafer is polished, the apparatus comprising
[Dhandapani 0029]: “The described polishing apparatus has many associated process parameters that control the operation of the polishing apparatus or describe the state of the apparatus or the polishing environment. Process parameters that control the operation [the apparatus further comprising a polishing controller configured to control devices in the polishing apparatus according to the determined polishing recipe so that the wafer is polished, the apparatus comprising] of the polishing apparatus (and that can be set, at least initially, by the tool control module 92) (‘control parameters’) include the following: rotation rate of platen 22; rotation rate of carrier head 50; pressure of the chambers 52a-52c; and polishing time.”
An irregularity is interpreted as part of a surface of a wafer that should be polished. This interpretation is supported by [Current Application 0018]: “Fig. 8A is a diagram that illustrates an example of a response amount profile on a center area having an irregularity at an asymmetric irregular point. Fig. 8B is a diagram that illustrates an example of a response amount profile on a center area having an irregularity at an edge irregular point at the time of a pressure center swing. Fig. 8C is a diagram that illustrates an example of a response amount profile on a center area having an irregularity at a polar irregular point.” as well as the corresponding figures, as the figures show the area response data which is a representation of the surface of the wafer.
and a simulation unit configured to determine a polishing recipe by simulation based on the new area response data that was used to automatically estimate that no irregularity is present by the irregularity-presence-or-absence estimation unit, or the new area response data after removal of the irregularity automatically estimated by the screening unit, wherein the polishing recipe is used for polishing wafers
[Dhandapani 0025]: “for each respective second substrate, determining respective control parameter values to apply [and a simulation unit configured to determine a polishing recipe by simulation based on the new area response data that was used to automatically estimate that no irregularity is present by the irregularity-presence-or-absence estimation unit, or the new area response data after removal of the irregularity automatically estimated by the screening unit, wherein the polishing recipe is used for polishing wafers] to the respective second substrate from the output nodes of the artificial neural network by applying the target removal profile to the input nodes of the artificial neural network”
A polishing recipe is seen as instructions to smooth a wafer supported by [Current Application 0006]: “The determination of the polishing recipe is performed by the skilled engineer, and thus the determination of a highly accurate polishing recipe is enabled for a short time (e.g., excellent in-plane uniformity).”, as the polishing recipe is noted to relate to “excellent in-plane uniformity”.
The idea of irregularities or some form of surface deformation and relation to the removal profile is noted in Dhandapani in [Dhandapani 0032]: "The polishing apparatus 20 can implement a wafer-to-wafer control. The wafer-to-wafer control can provide improved likelihood of achieving target material removal profiles over a wide range of designs and wafer non-uniformities.”
[Dhandapani 0059]: “Embodiments and all of the functional operations described in this specification can be implemented in digital electronic circuitry, or in computer software, firmware, or hardware, including the structural means disclosed in this specification and structural equivalents thereof, or in combinations of them. Embodiments can be implemented as one or more computer program products, i.e., one or more computer programs tangibly embodied in a machine readable storage media, for execution by, or to control the operation of, data processing apparatus, e.g., a programmable processor [processors], a computer, or multiple processors or computers.”
Dhandapani does not explicitly teach:
an irregularity-presence-or-absence estimation unit having a first trained model trained on a machine-learning relationship between past area response data, acquired from one or more prior wafers, and whether an irregularity is present in the past area response data, the irregularity-presence-or-absence estimation unit being configured to automatically estimate and output, using new area response data, acquired during polishing the wafer, as an input parameter, presence or absence of an irregularity in the new area response data
Dhandapani teaches the use of previous substrates ([Dhandapani 0032]: “A wafer-to-wafer feedback control method uses information about previously processed substrates to improve processing of a subsequent substrate. The wafer-to-wafer feedback control method can be implemented by the i-APC module 94.”) and there being irregularities on the surface of a wafer ([Dhandapani 0031]: “A typical wafer to be polished by a CMP process has a layer of material with surface topologies to be planarized.”), but not explicitly having a unit for detecting the presence of an irregularity.
a screening unit having a second trained model trained on a machine-learning relationship between the past area response data with an irregularity and past area response data after removal of the irregularity, the screening unit being configured to, when the irregularity-presence-or-absence estimation unit automatically estimates that an irregularity is present in the new area response data, automatically estimate and output new area response data after removal of the irregularity using, as an input parameter, the new area response data that was used to automatically estimate that the irregularity is present;
Dhandapani may not explicitly note having a unit for the machine learned relationship between before and after polishing, but Dhandapani notes having a wanted “new area response data for after removal of the irregularity” based on the area response data ([Dhandapani 0012]: “The determining of the target removal profile may include storing a desired thickness profile, receiving a measured thickness profile of the respective second substrate, and determining a difference between the measured thickness profile and the desired thickness profile. The receiving of the measured thickness profile may include measuring a thickness profile of the respective second substrate with the monitoring system.”).
Godbole teaches:
an irregularity-presence-or-absence estimation unit having a first trained model trained on a machine-learning relationship between past area response data, acquired from one or more prior wafers, and whether an irregularity is present in the past area response data, the irregularity-presence-or-absence estimation unit being configured to automatically estimate and output, using new area response data, acquired during polishing the wafer, as an input parameter, presence or absence of an irregularity in the new area response data
[Godbole Section 7 Conclusions and Future Work page 7]: “In this paper we use neural network classifier since it approximates the posterior probabilities [an irregularity-presence-or-absence estimation unit having a first trained model trained on a machine-learning relationship between past area response data, acquired from one or more prior wafers, and whether an irregularity is present in the past area response data, the irregularity-presence-or-absence estimation unit being configured to automatically estimate and output, using new area response data, acquired during polishing the wafer, as an input parameter, presence or absence of an irregularity in the new area response data as Godbole is teaching the detection of irregularities using a machine learning model] thereby giving us the outputs for correct segmentor and class.”
Further support for noting that Godbole is teaching detection of defects/irregularities on wafers in relation to machine learning is in [Godbole Introduction page 1]: “In this paper we develop a silicon defect recognition system that reliably segments and classify defects. This paper is organized as follows; section II describes silicon defects under consideration and their properties. Section III discusses methods that can be used for segmenting the defects and proposes an algorithm for consistent segmentation. In section IV the classification algorithm used for identification of defects is described.”
The ”or absence” part of the estimation is shown by [Godbole Section 3 Image Segmentation C. Edge detection based segmentation page 3]: “Step 4: Decision If all the filters fail to find the region then no defect is detected.”
One of ordinary skill in the art, prior to the effective filing date, would have been motivated to combine Dhandapani and Godbole to incorporate the use of neural networks in polishing, especially for irregularity detection. Dhandapani and Godbole are both in the same field of endeavor of neural networks. One of ordinary skill in the art would have been motivated to combine Dhandapani and Godbole to incorporate neural networks, especially for irregularity detection, as methods that utilize neural networks are shown to give better results than prior methods in the art [Godbole table 3 page 7]. Godbole also notes that the need for more pure silicon has made the detection of defects more necessary ([Godbole Introduction page 1]: “In recent years [1] significant progress has been achieved with the use of silicon semiconductors in integrated circuit technology. The need to produce hyper pure silicon has made it necessary to detect and recognize the defects in silicon at all stages of silicon semiconductor production.”). The addition of a check for irregularities or defects would not be unconventional to combine with Dhandapani as checking for irregularities before polishing can be done by simply adding the checking step.
PNG
media_image1.png
95
407
media_image1.png
Greyscale
Table 3 of Godbole showing MLP (Multilayer Perceptron) versus some other classification methods.
Bhaskar teaches:
when the irregularity-presence-or-absence estimation unit automatically estimates that an irregularity is present in the new area response data,
[Bhaskar 0080]: “The different dies can then be inspected in any suitable manner to detect defects [when the irregularity-presence-or-absence estimation unit automatically estimates that an irregularity is present in the new area response data where this is teaching that the combination works with a detection system, for the irregularity-presence-or-absence estimation unit is taught earlier by Godbole] in the different dies. That information is then typically used to determine a process window for the focus and exposure of the lithography process. Therefore, a FEM method may be used to print such dies on a specimen, and the non-nominal instances may include instances of any defects detected on such a specimen.”
a screening unit having a second trained model trained on a machine-learning relationship between the past area response data with an irregularity and past area response data after removal of the irregularity, the screening unit being configured to,
automatically estimate and output new area response data after removal of the irregularity using, as an input parameter, the new area response data that was used to automatically estimate that the irregularity is present;
[Bhaskar 0094]: “In one embodiment, the one or more components include a deep generative model configured to create the information for the nominal instances [a screening unit having a second trained model trained on a machine-learning relationship between the past area response data with an irregularity and past area response data after removal of the irregularity, the screening unit being configured to, as creating a nominal instance of a specimen is seen as creating new area response data after removal of the irregularity as the nominal instances are noted to as being “as intended/non-defective” later in this quote] of the one or more specimens. For example, deep generative models that learn the joint probability distribution (mean and variance) between the SEM (image of actual wafer) and design (e.g., CAD or a vector representation of intended layout) can be used to generate the nominal instances that are used to train the machine learning based model. A generative model may also be used to generate other simulation results described herein for non-nominal instances of the specimen. Once the machine learning based model is trained for nominal (as intended/non-defective) samples [automatically estimate and output new area response data after removal of the irregularity using, as an input parameter, the new area response data that was used to automatically estimate that the irregularity is present], as described further herein, a transfer learning training input dataset, which includes defective images or other non-nominal instances described herein, can be used to re-train the machine learning based model. In addition, a machine learning based model can be pre-trained by using synthetic data that is generated by modifying design data (e.g., CAD or EDA data) used to make semiconductor wafers. Defect artifacts such as opens, shorts, protrusions, intrusions, etc. along with metrology markers such as line end pull backs could be inserted into the CAD and then fed into a generative model trained by a network described in the above-referenced patent application by Zhang et al to create realistic defects.”
Support for using real instance or past data instead of just synthetic data is given in [Bhaskar 0111]: “As further shown in FIG. 2, actual wafer data 204 may be generated as described further herein (e.g., using PWQ and/or FEM training wafers). That actual wafer data may be provided to generative model 200, so that the actual wafer data may be used to train and/or update the generative model. That actual wafer data may also be provided to machine learning based model 206 so that re-training of the machine learning based model may be performed using the actual wafer data, which may be performed as described further herein.”
One of ordinary skill in the art, prior to the effective filing date, would have been motivated to combine modified Dhandapani and Bhaskar to incorporate performing actions based on whether an irregularity was detected. Dhandapani and Bhaskar are in the same field of endeavor of substrates or wafer processing. One of ordinary skill would have been motivated to combine modified Dhandapani and Bhaskar in order to improve manufacturing and increase profits [Bhaskar 0006] using machine learning for elements of the process as machine learning excels in areas where solutions are difficult to express [Bhaskar 0098]. An example would be in simulation of recipes for polishing wafers, as defect behavior can be learned to assist to assist the simulation [Bhaskar 0091]. Using machine learning for nominal instances works as a combination with Dhandapani as Dhandapani notes using a desired thickness profile [Dhandapani 0012] which can be or use data from a nominal instance created by machine learning.
Quotes used in motivation:
[Bhaskar 0006]: "Inspection processes are used at various steps during a semiconductor manufacturing process to detect defects on wafers to drive higher yield in the manufacturing process and thus higher profits. Inspection has always been an important part of fabricating semiconductor devices. However, as the dimensions of semiconductor devices decrease, inspection becomes even more important to the successful manufacture of acceptable semiconductor devices because smaller defects can cause the devices to fail.".
[Bhaskar 0098]: “In another embodiment, the machine learning based model is a neural network. For example, the machine learning based model may be a deep neural network with a set of weights that model the world according to the data that it has been fed to train it. Neural networks can be generally defined as a computational approach which is based on a relatively large collection of neural units loosely modeling the way a biological brain solves problems with relatively large clusters of biological neurons connected by axons. Each neural unit is connected with many others, and links can be enforcing or inhibitory in their effect on the activation state of connected neural units. These systems are self-learning and trained rather than explicitly programmed and excel in areas where the solution or feature detection is difficult to express in a traditional computer program.”
[Bhaskar 0091]: “For example, an additional capability that can be applied is simulation of the metrology tool whose recipe is being developed. In this manner, defect behavior for programmed defects can be learned in one model and applied in another. The output of the metrology system for the one or more specimens on which the synthetic defects are printed may be generated using any suitable model of the metrology system known in the art.”
Regarding Claim 4:
The polishing recipe determination device is taught in claim 1 by Dhandapani, Godbole, and Bhaskar.
Irregularity-presence-or-absence estimation unit is taught in claim 1 by Dhandapani, Godbole, and Bhaskar.
The screening unit is taught in claim 1 by Dhandapani, Godbole, and Bhaskar.
Goldbole teaches:
a type of an irregularity in the past area response data
using new area response data as an input parameter… a type of the irregularity in the new area response data
a type of the irregularity
and the automatically estimated type of the irregularity as input parameters
[Godbole Section 1 Introduction page 1]: “In this paper we develop a silicon defect recognition system that reliably segments and classify defects [a type of an irregularity in the past area response data] [using new area response data as an input parameter… a type of the irregularity in the new area response data] [a type of the irregularity] [and the automatically estimated type of the irregularity as input parameters]. This paper is organized as follows; section II describes silicon defects under consideration and their properties”
[Godbole Section 2 Defects in Silicon Wafers page 1]
“A. Defect types
There are many different types of silicon defects. Type A-defects are interpreted as clusters of silicon self-interstitials. Type D-defects are formed by clusters of silicon vacancies and crystal-originated pits are formed through agglomeration of vacancies [11]. The defects formed by interactions of native defects and impurities are the main concern in this paper.
1) Copper ball defect
Copper is an omnipresent contaminant that can be easily introduced into silicon wafers during the cleaning or device processing. The presence of copper rich precipitates in silicon reduces minority carrier diffusion length [11]. Ball shaped copper defects are considered here.
2) Plastic defects
Plastic defects in silicon are formed by the adsorption of organic contamination on the silicon wafer surface. They damage the performance and yield of semiconductor devices [12]. Plastic defects are spread in random shapes over the wafer surface. Pixel intensities of these defects differ little from background intensities, which make them difficult to detect.
3) Pit defects
Crystal originated pits are formed during the polishing or cleaning process of Czochralski-grown silicon wafers. Pits cause gate oxide degradation or an increase in leakage current [13] [14]. In this paper rounded pit defects are considered.
4) Protrusion defects
Protrusion defects deter fabrication processes, by preventing proper mask positioning, resulting in a loss of resolution [15]. These defects can be formed due to expansion of a thin oxide film on the silicon surface [16]. In this paper dome shaped or bubble shaped protrusions are considered.”
The motivation to combine with Godbole is the same as claim 1 motivation to combine with Godbole, as the MLP model in the motivation is classifying for type of irregularity (as stated by quotes above), thus motivation for use of the type of irregularity being used as data is shown.
Regarding Claim 5:
The polishing recipe determination device is taught in claim 4 by Dhandapani, Godbole, and Bhaskar.
Godbole teaches:
wherein the type of an irregularity includes one or more than one of an asymmetric irregular point, an edge irregular point at time of applying a pressure to a center area, and a polar irregular point
[Godbole Section 2 Defects in Silicon Wafers page 1]
“A. Defect types
There are many different types of silicon defects. Type A-defects are interpreted as clusters of silicon self-interstitials. Type D-defects are formed by clusters of silicon vacancies and crystal-originated pits are formed through agglomeration of vacancies [11]. The defects formed by interactions of native defects and impurities are the main concern in this paper.
1) Copper ball defect
Copper is an omnipresent contaminant that can be easily introduced into silicon wafers during the cleaning or device processing. The presence of copper rich precipitates in silicon reduces minority carrier diffusion length [11]. Ball shaped copper defects are considered here.
2) Plastic defects
Plastic defects in silicon are formed by the adsorption of organic contamination on the silicon wafer surface. They damage the performance and yield of semiconductor devices [12]. Plastic defects are spread in random shapes over the wafer surface. Pixel intensities of these defects differ little from background intensities, which make them difficult to detect.
3) Pit defects
Crystal originated pits are formed during the polishing or cleaning process of Czochralski-grown silicon wafers. Pits cause gate oxide degradation or an increase in leakage current [13] [14]. In this paper rounded pit defects are considered.
4) Protrusion defects
Protrusion defects deter fabrication processes, by preventing proper mask positioning, resulting in a loss of resolution [15]. These defects can be formed due to expansion of a thin oxide film on the silicon surface [16]. [wherein the type of an irregularity includes one or more than one of an asymmetric irregular point, an edge irregular point at time of applying a pressure to a center area, and a polar irregular point] In this paper dome shaped or bubble shaped protrusions are considered.”
Asymmetric irregular point, edge irregular point, and polar irregular point are interpreted, in light of the drawings 8A to 8C, to be example variations of protrusion defects (as no limiting definition was given for these irregularities).
The motivation to combine with Godbole is the same motivation used in claim 4 to combined with Godbole.
Regarding Claim 9:
Claim 9 is analogous to the teachings of claim 1.
Regarding Claim 10:
Claim 10 is analogous to the teachings of claim 1.
Regarding Claim 13:
Claim 13 is analogous to the teachings of claim 1.
Regarding Claim 16:
Claim 16 is analogous to the teachings of claim 1.
Claims 2, 3, 11, 12, 14, 15, 17, 18 is/are rejected under 35 U.S.C. 103 as unpatentable over Dhandapani et al (US 20190095797 A1) referred to as Dhandapani in this document, in further view of Bhaskar et al (US 20170193400 A1), referred to as Bhaskar in this document, in further view of Godbole et al (“Neural decision directed segmentation of silicon defects”), referred to as Godbole in this document, and even further in view of Emami-Naeini et al (“Control in Semiconductor Wafer Manufacturing”), referred to as Emami-Naeini in this document.
Regarding Claim 2:
The polishing recipe determination device is taught in claim 1 by Dhandapani, Godbole, and Bhaskar.
Modified Dhandapani does not teach:
an acceptance evaluation unit configured to compare an actual polishing result obtained by actually polishing using the polishing recipe with a simulation polishing result obtained by simulation using the polishing recipe to automatically evaluate an acceptance of the actual polishing result
Dhandapani may not explicitly note an acceptance evaluation unit, aspects related to such are taught in [Dhandapani 0027]: “The fitting produces a determination of the thickness of the layer and a GOF value that is indicative of how closely the measured spectrum agrees with the expected film stack. As such, the GOF value can be used as an indicator of reliability of the determined thickness value.” As GOF can be seen as a form of acceptance determination.
a response data correction unit having a third trained model trained on a machine-learning relationship between: (A) a past actual polishing result, a past simulation polishing result, and past area response data used for determination of a polishing recipe at that time, and (B) past corrected area response data, the response data correction unit being configured to, when the acceptance evaluation unit automatically evaluates non-acceptance, automatically estimate and output corrected area response data using the actual polishing result automatically evaluated as non-acceptance, the simulation polishing result, and the area response data used for determination of a polishing recipe at that time as input parameters, wherein the simulation unit again determines a polishing recipe by simulation based on the corrected area response data automatically estimated by the response data correction unit
Dhandapani may not explicitly teach a response data correction unit, but aspects related via updating the processing of future wafers in [Dhandapani 0036]: “The i-APC module 94 performs tasks including collecting and processing of data from processed wafers to improve processing of future wafers. Collected data can include upstream and downstream metrology data of the product wafers from various wafer metrology tools (“monitoring systems”). Upstream metrology data may include thickness map and associated GOF values of a deposited layer. Downstream metrology data may include a thickness map and associated GOF values of the polished layer, or surface roughness values. The GOF values can be used by the i-APC module 94 to determine whether the thickness value are reliable enough to be used in the process model development. The i-APC module 94 pairs these data with the control and state parameters used during the processing of a particular wafer, and stores it in a data log. The data log may be organized in a variety of ways, including grouping by wafer ID, design ID, lot ID, tool ID, etc. This data log is typically used to monitor trends and drifts in the behavior of a CMP process and to take corrective actions. Due to their size, data logs may be stored in one or more servers that are a part of the controller 90.”
Emami-Naeini teaches:
an acceptance evaluation unit configured to compare an actual polishing result obtained by actually polishing using the polishing recipe with a simulation polishing result obtained by simulation using the polishing recipe to automatically evaluate an acceptance of the actual polishing result
[Emami-Naeini III. Control of Semiconductor Processes A. Model Based Control page 4]: “The controller’s performance on the actual equipment can be determined [an acceptance evaluation unit configured to compare an actual polishing result obtained by actually polishing using the polishing recipe with a simulation polishing result obtained by simulation using the polishing recipe to automatically evaluate an acceptance of the actual polishing result] and design iterations can be carried out if necessary.”
Support for the above quote, especially in relation to a simulation and actual result, is shown in [Emami-Naeini Figure 6 page 4]
PNG
media_image2.png
501
723
media_image2.png
Greyscale
a response data correction unit having a third trained model trained on a machine-learning relationship between: (A) a past actual polishing result, a past simulation polishing result, and past area response data used for determination of a polishing recipe at that time, and (B) past corrected area response data,
[Emami-Naeini VII.Summary and Conclusions page 11]: “Due to increasingly stringent performance requirements, model-based feedback-feedforward control system design is becoming more prevalent, in addition to run-to-run control, which is now commonly used in the fabs… It is anticipated that some process equipment, such as photolithography, will employ sophisticated iterative learning controllers [19]. [a response data correction unit having a third learned model machine-learning relationship between:]”
[Emami-Naeini III. Control of Semiconductor Processes page 4]: “If the model and the planner were perfect and there were no process disturbances, the planner would be all that would be required—but in the real world this is never the case. Thus, the regulator uses the difference between the desired product characteristics [and past area response data used for determination of a polishing recipe at that time,] and those actually being produced [(A) a past actual polishing result,] to compute corrections [and (B) past corrected area response data,] to the nominal process inputs computed by the planner; this is the feedback controller.”
[Emami-Naeini III. Control of Semiconductor Processes Figure 5 page 4]
PNG
media_image3.png
650
809
media_image3.png
Greyscale
The “ideal trajectory of process variable” from the “Path Planner” [a past simulation polishing result,]
the response data correction unit being configured to, when the acceptance evaluation unit automatically evaluates non-acceptance, automatically estimate and output corrected area response data using the actual polishing result automatically evaluated as non-acceptance, the simulation polishing result, and the area response data used for determination of a polishing recipe at that time as input parameters,
[Emami-Naeini Figure 6 page 4] and [Emami-Naeini III. Control of Semiconductor Processes page 4], as noted previously in this claim, teach the acceptance evaluation unit and evaluating acceptance.
[Emami-Naeini Figure 6 page 4] “Adjust Uncertain Model Parameters” and “Adjust Controller in Simulation” [the response data correction unit being configured to, when the acceptance evaluation unit automatically evaluates non-acceptance, automatically estimate and output corrected area response data using the actual polishing result automatically evaluated as non-acceptance, the simulation polishing result, and the area response data used for determination of a polishing recipe at that time as input parameters,]
wherein the simulation unit again determines a polishing recipe by simulation based on the corrected area response data automatically estimated by the response data correction unit
[Emami-Naeini Figure 6 page 4] “Adjust Controller in Simulation” [wherein the simulation unit again determines a polishing recipe by simulation based on the corrected area response data automatically estimated by the response data correction unit]
One of ordinary skill in the art, prior to the effective filing date, would have been motivated to combine modified Dhandapani and Emami-Naeini to incorporate a response data correction unit or regulator and a form of acceptance unit. Dhandapani and Emami-Naeini are in the same field of endeavor of substrates or wafer processing. One of ordinary skill would have been motivated to combine modified Dhandapani and Emami-Naeini in order to improve manufacturing using a regulator/response data correction unit, as models and planning are not realistically perfect ([Emami-Naeini III. Control of Semiconductor Processes page 4]: “If the model and the planner were perfect and there were no process disturbances, the planner would be all that would be required—but in the real world this is never the case. Thus, the regulator uses the difference between the desired product characteristics and those actually being produced to compute corrections to the nominal process inputs computed by the planner; this is the feedback controller.”). The combination with Dhandapani would not be unconventional, as Dhandapani already teaches attempting to improve processing of future wafers (noted in notes below the not explicitly taught by Dhandapani in this claim), thus a modification to add a correction system to the process would not deviating far from aspects of the original process.
Regarding Claim 3:
A polishing recipe determination device involving a top ring is taught in claim 1 by Dhandapani.
A simulation unit is taught in claim 1 by Dhandapani, Godbole, and Bhaskar.
An acceptance evaluation unit is taught in claim 2 by Dhandapani, Godbole, Bhaskar, and Emami-Naeini.
A response data correction unit is taught in claim 2 by Dhandapani, Godbole, Bhaskar, and Emami-Naeini.
Regarding Claim 11:
Claim 11 is analogous to the teachings of claim 2.
Regarding Claim 12:
Claim 12 contains the same limitations as claim 3.
The motivations to combine are the same as claim 3.
Where support for the process being related to wafer polishing is further given in [Dhandapani 0013]: “Product wafers may be used for model refinement, leading to the actual profile of processed substrates being closer to a desired profile. Complex behavior of the polishing [for polishing a substrate] process in response to polishing parameters may be accounted for without explicit knowledge of the functional relationships.”
Regarding Claim 14:
Claim 14 is analogous to the teachings of claim 2.
Regarding Claim 15:
Claim 15 is analogous to the teachings of claim 3.
Regarding Claim 17:
Claim 17 is analogous to the teachings of claim 2.
Regarding Claim 18:
Claim 18 contains the same limitations as claim 3.
The motivations to combine are the same as in claim 3.
Where support for the process being related to wafer polishing is further given in [Dhandapani 0013]: “Product wafers may be used for model refinement, leading to the actual profile of processed substrates being closer to a desired profile. Complex behavior of the polishing [for polishing a substrate][wherein the polishing recipe is used in polishing substrates] process in response to polishing parameters may be accounted for without explicit knowledge of the functional relationships.”
Claims 6, 7, 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Dhandapani et al (US 20190095797 A1) referred to as Dhandapani in this document, in further view of Bhaskar et al (US 20170193400 A1), referred to as Bhaskar in this document, in further view of Godbole et al (“Neural decision directed segmentation of silicon defects”), referred to as Godbole in this document, and even further in view of Sakurai et al (US 20060009127 A1), referred to as Sakurai in this document.
Regarding Claim 6:
The polishing recipe determination device in claim 1 is taught by Dhandapani, Godbole, and Bhaskar.
Modified Dhandapani does not explicitly teach:
wherein the area response data is data that a variation in an amount of removal by polishing is divided by a variation in an air bag pressure on positions on a wafer
Dhandapani does not directly note the division of amount of removal by polishing by a variation in air bag pressure, but does note the elements of removal and pressure [Dhandapani 0007]: “wherein the control parameter values include pressures for the chambers in the carrier head; obtain a target removal profile for each respective substrate of a plurality of substrates; for each respective substrate, determine respective control parameter values to apply to the respective substrate from the output nodes of the artificial neural network by applying the target removal profile to the input nodes of the artificial neural network, wherein the respective control parameter values include respective pressures for the chambers in the carrier head; and for each respective substrate, cause the carrier head to apply the respective pressures to the chambers in the carrier head during polishing.”
Sakurai teaches:
wherein the area response data is data that a variation in an amount of removal by polishing is divided by a variation in an air bag pressure on positions on a wafer
[Sakurai 0081]: “First, in step 1, the surface topology of a film on a wafer is measured in advance. Next, in step 2, the wafer is actually polished under particular set pressure and polishing time conditions. In step 3, the distribution of the pressure of the wafer front surface under the set pressure conditions is calculated in advance using the simulation tool. The surface topology of the polished film on the wafer is re-measured and, from the difference before and after polishing, the distribution of the polishing amount on the wafer front surface is calculated (step 4). Next, in step 5, the calculated distribution of the polishing amount is divided by the polishing time and the calculated pressure distribution to determine the distribution of the polishing rates per unit pressure and unit time at various points on the wafer front surface [wherein the area response data is data that a variation in an amount of removal by polishing is divided by a variation in an air bag pressure on positions on a wafer], i.e. the distribution of polishing coefficients on the wafer front surface. It is also possible to divide [divided] the calculated distribution of the polishing amount only by the calculated pressure distribution without division by the polishing time, thus determining the distribution of the polishing rates per unit pressure.”
One of ordinary skill in the art, prior to the effective filing date, would have been motivated to combine Dhandapani and Sakurai to incorporate response data involving a varying of pressure. Dhandapani and Sakurai are both in the same field of endeavor of wafer processing. One of ordinary skill in the art would have been motivated to combine Dhandapani and Sakurai to utilize response data involving a varying of pressure, as Sakurai notes the methods utilized have high accuracy ([Sakurai 0083]: “It has been confirmed experimentally that the results of estimation of the polishing amount or polishing rate of a wafer by the above-described method for the profile control-type top ring are approximately equal to the results of actual polishing of the wafer. In some cases, the polishing profile in a peripheral annular region of a wafer, the region having a width of about 10 mm from the peripheral end, differs slightly from the pressure distribution profile of the wafer front surface. This is because the annular region of the wafer is influenced, during polishing, by a reaction force due to deformation of a polishing pad, which is an elastic body, and by a peripheral bevel portion of the wafer, in addition to the influence of the pressure applied from the wafer back surface. However, such other influences than the pressure distribution can also be modeled by determining the polishing coefficient from the pressure distribution and the actual polishing profile. This makes it possible to estimate and calculate the polishing profile of the entire front surface of the wafer with high accuracy.”).
Regarding Claim 7:
The polishing recipe determination device in claim 1 is taught by Dhandapani, Godbole, and Bhaskar.
Modified Dhandapani does not explicitly teach:
wherein the area response data is data that a variation in a polishing removal rate is divided by a variation in an air bag pressure on positions on a wafer
Claim 6 notes how Dhandapani teaches related elements.
Sakurai teaches:
wherein the area response data is data that a variation in a polishing removal rate is divided by a variation in an air bag pressure on positions on a wafer
[Sakurai 0081]: “First, in step 1, the surface topology of a film on a wafer is measured in advance. Next, in step 2, the wafer is actually polished under particular set pressure and polishing time conditions. In step 3, the distribution of the pressure of the wafer front surface under the set pressure conditions is calculated in advance using the simulation tool. The surface topology of the polished film on the wafer is re-measured and, from the difference before and after polishing, the distribution of the polishing amount on the wafer front surface is calculated (step 4). Next, in step 5, the calculated distribution of the polishing amount is divided by the polishing time and the calculated pressure distribution to determine the distribution of the polishing rates per unit pressure and unit time at various points on the wafer front surface [wherein the area response data is data that a variation in a polishing removal rate is divided by a variation in an air bag pressure on positions on a wafer], i.e. the distribution of polishing coefficients on the wafer front surface. It is also possible to divide [divided] the calculated distribution of the polishing amount only by the calculated pressure distribution without division by the polishing time, thus determining the distribution of the polishing rates per unit pressure.”
The motivation to combine is the same motivation to combine with Sakurai in claim 6.
Regarding Claim 8:
The polishing recipe determination device in claim 1 is taught by Dhandapani, Godbole, and Bhaskar.
Modified Dhandapani does not explicitly teach:
wherein the area response data is data that for positions on a wafer, a variation in a remaining film on the wafer is divided by a variation in an air bag pressure
Claim 6 notes how Dhandapani teaches related elements.
Sakurai teaches:
wherein the area response data is data that for positions on a wafer, a variation in a remaining film on the wafer is divided by a variation in an air bag pressure
[Sakurai 0081]: “First, in step 1, the surface topology of a film on a wafer is measured in advance. Next, in step 2, the wafer is actually polished under particular set pressure and polishing time conditions. In step 3, the distribution of the pressure of the wafer front surface under the set pressure conditions is calculated in advance using the simulation tool. The surface topology of the polished film on the wafer is re-measured and, from the difference before and after polishing, the distribution of the polishing amount on the wafer front surface is calculated [wherein the area response data is data that on positions for a wafer, a variation in a remaining film on the wafer is divided by a variation in an air bag pressure] (step 4). Next, in step 5, the calculated distribution of the polishing amount is divided by the polishing time and the calculated pressure distribution to determine the distribution of the polishing rates per unit pressure and unit time at various points on the wafer front surface, i.e. the distribution of polishing coefficients on the wafer front surface. It is also possible to divide [divided] the calculated distribution of the polishing amount only by the calculated pressure distribution without division by the polishing time, thus determining the distribution of the polishing rates per unit pressure.”
The motivation to combine is the same motivation to combine with Sakurai in claim 6.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Su et al (US 20200356011 A1) is considered relevant art as Su et al notes a process that involves something similar to simulating a result and having a machine learning model perform corrections on the result.
Shanmugasundram et al (US 20020197745 A1) is considered relevant art as Shanmugasundram et al notes the manipulation of a wafer during processing where a polishing recipe is determined for the wafer.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHRISTOPHER D DEVORE whose telephone number is (703)756-1234. The examiner can normally be reached Monday-Friday 7:30 am - 5 pm EST.
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, Michael J Huntley can be reached at (303) 297-4307. 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.
/C.D.D./Examiner, Art Unit 2129
/MICHAEL J HUNTLEY/Supervisory Patent Examiner, Art Unit 2129