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 .
Priority
Acknowledgment is made of applicant’s claim for foreign priority under 35 U.S.C. 119 (a)-(d). The certified copy has been filed in parent Application No. IN202441042044, filed on 05/30/2024.
Claim Objections
Claim 4 is objected to because of the following informalities: Claim 4 appears to mention "receiving second data" which is already defined in claim 2.
Appropriate correction is required.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1- 4,9-11, 12-15, 17, 18, and 19 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by SAWLANI US-20200226742-A1 Published on 2020-07-16.
Regarding claims 1, receiving, by a processing device, first data indicative of one or more defects of a substrate processed in a substrate processing system using a process recipe, the first data having a first data type (SAWLANI discloses ¶39 “Disclosed methods and systems may provide accurate and rapid defect classification, root cause analysis (to identify sources of defects), and/or recommended corrective actions… are combined with use of prior knowledge… recipe information. ” ¶42 “Morphology data 107 such as images of defects is fed into first stage defect classification engine 102,which produces a first stage defect classification 126.”);
processing, by the processing device, the first data using a first trained machine learning model that outputs first information about the one or more defects (SAWLANI discloses Fig. 1A, Morphology data 107 being input into a machine learning model 102 which produces the defect classification 126.);
determining, by the processing device, one or more possible root causes for the one or more defects based at least in part on the first information(SAWLANI discloses ¶54 “In some cases, the second stage defect classification includes multiple classifications, each with an associated probability or likelihood value ascribed thereto. In addition, the second stage defect classification may include one or more sources or root causes of the defects and probability or likelihood values ascribed to each of them.”);
outputting, by the processing device, a sequence of maintenance operations to be performed on the substrate processing system based on the one or more possible root causes for the one or more defects (SAWLANI discloses ¶54 “Still further, the second stage defect classification may include one or more corrective actions with an associated probability that the corrective action will be successful in reducing or removing the defects.”).
Regarding the system of claim 12, comprising memory and a processing device coupled to the memory, wherein the processing device is configured to: (Fig.8 discloses a processor coupled to main memory and a second memory.) The limitations are otherwise identical to claim 1 and have been discussed above.
Regarding claim 18, a non-transitory machine-readable storage medium storing instructions which, when executed, cause a processing device to perform operations comprising: (SAWLANI discloses ¶97 “Program code may be stored in non-transitory media such as persistent storage 810 or memory 808 or both.”) The limitations are otherwise identical to claim 1 and have been discussed above.
Regarding claims 2 and 13, the limitations of claims 1 and 12 are discussed above. Further comprising: receiving, by the processing device, second data indicative of the one or more defects of the substrate processed in the substrate processing system, the second data having a second data type (SAWLANI discloses ¶42 “Metrology data 105 is fed into each first stage defect classification engine to produce first stage defect classifications 124, 126, and 128, respectively. For example, a wafer map 106 is fed into first stage defect classification engine 101, which produces a first stage defect classification 124.”); and
processing, by the processing device, the second data using a second trained machine learning model that outputs second information about the one or more defects, wherein the second information is further used to determine the one or more possible root causes (SAWLANI discloses Fig. 1A, Metrology data 105 being input into a machine learning model 101 which produces the defect classification 124. See ¶54 for determining the root cause.).
Regarding claims 3 and 14, the limitations of claims 2 and 13 are discussed above. Further comprising: receiving, by the processing device, third data indicative of the one or more defects of the substrate processed in the substrate processing system, the third data having a third data type (SAWLANI discloses ¶42 “Composition data 108 is fed into first stage defect classification engine 103, which produces a first stage defect classification 128.”); and
processing, by the processing device, the third data using a third trained machine learning model that outputs third information about the one or more defects, wherein the third information is further used to determine the one or more possible root causes (SAWLANI discloses Fig. 1A, which depicts Compound data 108 being input into a machine learning model 103 which produces the defect classification 128, ¶78 “the machine learning model was able to output a composition-based classification with a 99.9% probability. EDS-generate spectra 723 and 733 confirmed the first stage defect classifications 725 and 735, respectively. Defect analysis using only image data without collecting spectra data is advantageous because it may be easier and less expensive to collect image data compared to spectra data.” See ¶54 for determining the root cause. ).
Regarding claim 19, the limitations of claim 18 are discussed above. Wherein the processing device to perform operations further comprising:
receiving second data indicative of the one or more defects of the substrate processed in the substrate processing system, the second data having a second data type(SAWLANI discloses ¶42 “Metrology data 105 is fed into each first stage defect classification engine to produce first stage defect classifications 124, 126, and 128, respectively. For example, a wafer map 106 is fed into first stage defect classification engine 101, which produces a first stage defect classification 124.”);
processing the second data using a second trained machine learning model that outputs second information about the one or more defects(SAWLANI discloses Fig. 1A, which depicts Metrology data 105 being input into a machine learning model 101 which produces the defect classification 124. See ¶54 for determining the root cause.);
receiving third data indicative of the one or more defects of the substrate processed in the substrate processing system the third data having a third data type(SAWLANI discloses ¶42 “Composition data 108 is fed into first stage defect classification engine 103, which produces a first stage defect classification 128.”);
and processing the third data using a third trained machine learning model that outputs third information about the one or more defects, wherein the second information and the third information is further used to determine the one or more possible root causes(SAWLANI discloses Fig. 1A, which depicts Compound data 108 being input into a machine learning model 103 which produces the defect classification 128, ¶78 “the machine learning model was able to output a composition-based classification with a 99.9% probability. EDS-generate spectra 723 and 733 confirmed the first stage defect classifications 725 and 735, respectively. Defect analysis using only image data without collecting spectra data is advantageous because it may be easier and less expensive to collect image data compared to spectra data.” See ¶54 for determining the root cause. ).
Regarding claims 4, and 15, the limitations of claims 2, and 13 are discussed above. Further comprising: receiving second data comprising at least one of
or an identity of the process recipe, (SAWLANI discloses ¶15 “In some embodiments, the metrology data includes “metadata” pertaining to a metrology system or conditions used in obtaining the metrology data… A non-exclusive list of metadata attributes includes: Process Tools design and operation information such as platform information, robot arm design, tool material details, part information, process recipe information,)
wherein the second data is used at least one of
c) to determine the one or more possible root causes (SAWLANI discloses ¶26 “The metrology data contains information about one or more defects on a substrate. A defect analysis system may also receive, as an input, information about the particular manufacturing equipment and/or fabrication process used to perform an operation that produces defects. In addition to providing a defect classification, a defect analysis system may provide a source or root cause of defects as an output.”).
Regarding claim 9, the limitations of claim 1 are discussed above. Wherein the first data type comprises one of image data of the substrate, map data of the substrate, composition data of the substrate, or textual data associated with the one or more defects (SAWLANI discloses ¶42 “FIG. 1A presents a schematic illustration of an example defect analysis system with multiple first stage defect classification engines 101, 102, and 103 and a second stage defect classification engine130. Metrology data 105 is fed into each first stage defect classification engine to produce first stage defect classifications 124, 126, and 128, respectively. For example, a wafer map 106 is fed into first stage defect classification engine 101, which produces a first stage defect classification 124.Morphology data 107 such as images of defects is fed into first stage defect classification engine 102,which produces a first stage defect classification 126. Composition data 108 is fed into first stage defect classification engine 103, which produces a first stage defect classification 128.”).
Regarding claim 10, the limitations of claim 1 are discussed above. Further comprising: outputting, by the processing device, the sequence of maintenance operations for display on a graphical user interface (GUI) (SAWLANI discloses ¶21 “In various embodiments, the computer executable instructions for determining the one or more likely sources of the defects on the substrate includes computer executable instructions for further classifying, beyond the first stage defect classification, the defects on the substrate. In some implementations the computer executable instructions provide suggested corrective actions to reduce generation of defects on the substrate and/or reduce occurrences of defects on substrates processed in the future.” ¶96 “Embodiments of the invention may be implemented in program code on system 800 with I/O subsystem 802 used to receive input program statements and/or data from a human user (e.g., via a GUI or keyboard) and to display them back to the user.”).
Regarding claim 11, the limitations of claim 1 are discussed above. Wherein the sequence of maintenance operations are selected from a superset of maintenance operations for the substrate processing system (SAWLANI discloses ¶54 “Still further, the second stage defect classification 138a may include one or more corrective actions with an associated probability that the corrective action will be successful in reducing or removing the defects.” ¶55 “Corrective actions may include part replacement (e.g. corroded gas lines, filter failures, O-ring failure, other part failures, pump failures, wear and tear of parts, clogging of parts/orifice, etc.), part cleaning (e.g. poorly cleaned showerhead resulting in showerhead patterns, dirty view ports, dirty mixing bowl, gas line dusting/contaminated, ESC contamination, etc.), part redesign (e.g. mechanical scratches from robot arms and/or other contact points in the tool, aggressive plasma clean damaging pipe, PM door rubbing/contact, poor RF grounding, edge ring height etc.), chemistry residence check/corrections (e.g. gas phase condensation, insufficient chamber clean etc.), operator behavior(e.g. handling of wafers, incorrect process and/or metrology recipe, etc.), process tuning (e.g. peeling of coatings, insufficient chamber conditioning, insufficient undercoat, precoat and clean, in-film defects such as volcanos/pits, unstable plasma modes, etc.), or any combination thereof.”).
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
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 5-8, 16, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over SAWLANI US-20200226742-A1 Published on 2020-07-16 in view of GOMES US-20190347148-A1 Published on 2019-11-14.
Regarding claims 5, 16 and 20, the limitations of claims 1, 12 and 18 are discussed above.
SAWLANI discloses processing the first information using a second trained machine learning model.
SAWLANI does not disclose expressly that outputs matches to historical defects, each of the historical defects having a historical root cause, wherein the one or more possible root causes correspond to historical root causes associated with the matches to historical defects.
GOMES discloses that outputs matches to historical defects, each of the historical defects having a historical root cause, wherein the one or more possible root causes correspond to historical root causes associated with the matches to historical defects (GOMES discloses ¶12 “Information extracted about an experienced or on-going technical issue, such as a specific problem with particular system(s) of the environment, is compared to a set of information about related and/or similar issues and instructions/actions that resolved, or may have resolved, those similar issues in the past. A system collects this information and correlates (matches) it to historical problems/solutions to identify similarities with past incidents and potential resolutive actions to those past incidents.”).
SAWLANI and GOMES are analogous art because they are from the same field of endeavor of using machine learning models to reach determinations of root causes.
At the time of the invention, it would have been prima facie obvious to one of ordinary skill, in the art as of the effective filing date, to modify SAWLANI to match historical data on defects with the corresponding historic root cause using the models of GOMES.
The suggestion/motivation for doing so would have been to improve efficiency by minimizing the time needed to reach a proper solution (GOMES discloses ¶15 “Machine learning techniques are applied to extract the relevant information about an ongoing or unresolved technical issue …This can minimize time and other resources spent diagnosing the issue and searching for a proper solution.”).
Therefore, it would have been prima facie obvious to one of ordinary skill, in the art as of the effective filing date, to combine SAWLANI and GOMES for the benefit of that outputs matches to historical defects, each of the historical defects having a historical root cause, wherein the one or more possible root causes correspond to historical root causes associated with the matches to historical defects to obtain the invention as specified in the claims 5, 16 and 20.
Regarding claim 6, the limitations of claim 5 are discussed above.
SAWLANI discloses the second trained machine learning model.
SAWLANI does not disclose expressly model further outputs, for each of the matches to historical defects, a score value based on a similarity between the first information and corresponding information of the historical defect.
GOMES discloses model further outputs, for each of the matches to historical defects, a score value based on a similarity between the first information and corresponding information of the historical defect (GOMES ¶13 “Past issue/solution (historical defect) combinations may be ranked (score) based on relevancy (similarity) to a current context (first information) (i.e. the context in which a current technical issue is experienced)”).
SAWLANI and GOMES are analogous art because they are from the same field of endeavor of using machine learning models to reach determinations of root causes.
At the time of the invention, it would have been prima facie obvious to one of ordinary skill, in the art as of the effective filing date, to modify SAWLANI to score combinations based on the similarity using the models of GOMES.
The suggestion/motivation for doing so would have been to improve efficiency by minimizing the time needed to reach a proper solution (GOMES discloses ¶15 “Machine learning techniques are applied to extract the relevant information about an ongoing or unresolved technical issue …This can minimize time and other resources spent diagnosing the issue and searching for a proper solution.”).
Therefore, it would have been prima facie obvious to one of ordinary skill, in the art as of the effective filing date, to combine SAWLANI and GOMES for the benefit of model further outputs, for each of the matches to historical defects, a score value based on a similarity between the first information and corresponding information of the historical defect to obtain the invention as specified in the claim 6.
Regarding claims 7 and 16, the limitations of claims 1 and 12 are discussed above.
SAWLANI discloses identifying defects processed in the processing system.
SAWLANI does not disclose expressly further comprising: identifying, by the processing device, historical match information from a data structure, wherein the historical match information corresponds to one or more matches to historical defects.
GOMES discloses further comprising: identifying, by the processing device, historical match information from a data structure, wherein the historical match information corresponds to one or more matches to historical defects (GOMES discloses ¶12 historical match information. ¶15 “In some aspects, collected data, such a system logs and events delivered from monitoring tools, product documentation, and user contributions to public web sources, as examples, is processed by a natural language classifier to understand practical meanings of those inputs and translate them into structured data for a database. Prior RCA documentation can also be analyzed.”) This reads as historic root cause analysis documents which would be the data being matched, could be stored in a data structure or database for the machine learning model to use.
SAWLANI and GOMES are analogous art because they are from the same field of endeavor of using machine learning models to reach determinations of root causes.
At the time of the invention, it would have been prima facie obvious to one of ordinary skill, in the art as of the effective filing date, to modify SAWLANI to store/receive historic match information from a data structure using the models of GOMES.
The suggestion/motivation for doing so would have been to improve efficiency by minimizing the time needed to reach a proper solution (GOMES discloses ¶15 “Machine learning techniques are applied to extract the relevant information about an ongoing or unresolved technical issue …This can minimize time and other resources spent diagnosing the issue and searching for a proper solution.”).
Therefore, it would have been prima facie obvious to one of ordinary skill, in the art as of the effective filing date, to combine SAWLANI and GOMES for the benefit of further comprising: identifying, by the processing device, historical match information from a data structure, wherein the historical match information corresponds to one or more matches to historical defects GOMES discloses further comprising: identifying, by the processing device, historical match information from a data structure, wherein the historical match information corresponds to one or more matches to historical defects to obtain the invention as specified in the claims 7 and 16.
Regarding claim 8, the limitations of claim 1 are discussed above.
SAWLANI discloses determine the one or more possible root causes
SAWLANI does not disclose expressly further comprising: receiving, by the processing device, user input comprising an indication of a ranking of historical defects associated with the first information, wherein the user input is further used.
GOMES discloses further comprising: receiving, by the processing device, user input comprising an indication of a ranking of historical defects associated with the first information, wherein the user input is further used (GOMES ¶62 “Feedback from users can be provided as part of the results fed into the training process at 420 to further train the classification model in identifying best solutions to identified issues. The user feedback can contribute to ranks of the candidate issue-solution combinations in future rankings. In this manner, the ongoing training provided by the feedback loop can affect the rankings of issue-solution combinations. If a particular solution is found based on user feedback to not properly address a problem, the training can correct this to devalue or eliminate the issue-solution combination. Feedback that a proposed solution successfully addressed a given technical issue might boost the model's confidence that that issue-solution combination accurately addresses the root cause of that technical issue.”).
SAWLANI and GOMES are analogous art because they are from the same field of endeavor of using machine learning models to reach determinations of root causes.
At the time of the invention, it would have been prima facie obvious to one of ordinary skill, in the art as of the effective filing date, to modify SAWLANI to take user input indicating a rank of the root cause of the defect of the first information using the models of GOMES.
The suggestion/motivation for doing so would have been to improve efficiency by minimizing the time needed to reach a proper solution (GOMES discloses ¶15 “Machine learning techniques are applied to extract the relevant information about an ongoing or unresolved technical issue …This can minimize time and other resources spent diagnosing the issue and searching for a proper solution.”).
Therefore, it would have been prima facie obvious to one of ordinary skill, in the art as of the effective filing date, to combine SAWLANI and GOMES for the benefit of further comprising: receiving, by the processing device, user input comprising an indication of a ranking of historical defects associated with the first information, wherein the user input is further used.to obtain the invention as specified in the claim 8.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CONNOR D COUSINEAU whose telephone number is (571)447-9620. The examiner can normally be reached Monday-Friday 8am-5pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Kamini Shah can be reached at (571) 272-2279. 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.C./Examiner, Art Unit 2115
/PAUL B YANCHUS III/ Primary Examiner, Art Unit 2115 July 23, 2026
Prosecution Insights