Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
DETAILED ACTION
The action is in response to the Applicant’s communication filed on 06/09/2023.
Claims 31-47 are canceled by the applicant.
Claims 1-30 are pending, where claims 1, 20, 23 and 29 are independent.
This application claims the priority benefit of the provisional application no. 63/199,237 filed on 12/15/2020 incorporated herein.
This application claims the priority benefit under of the international application no. PCT/JUS2021/063222 filed on 12/14/2021 incorporated herein.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 09/06/2023 has been filed after the filing date of the application. The submission is in-compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
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 of this title, 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 set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied 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.
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
Claims 1-30 are rejected under AIA 35 U.S.C. 103 as being unpatentable over Feng, et al. USPGPub No. 20190244870 A1).
As to claim 1, Feng discloses A method of generating a machine learning model configured to predict a substrate parameter value on a substrate during or after processing the substrate in a process chamber (Feng [0001-23] “time-series of spectra information extracted during processing of etch processing operations in order control etch endpoint operations - utilize training processes to generate three dimensional intensity surface profiles - converted into a virtual carpet - real-time processing of wafers to predict or identify an effective etch depth at a current point in time” [0040-117] “machine learning implemented to use the time-series of spectra to extract critical conditions of the wafer” [abstract] “generated from a time-series of spectra for an etch process - processing a fabrication etch process on a fabrication wafer” see Fig. 1-11, virtual carpet generated from time-series spectra, machine learning, utilize training processes to generate three dimensional intensity surface profiles, predict or identify etch depth obviously provides generating a machine learning model to predict substrate parameter), the method comprising:
receiving training data comprising, for each of a plurality of training substrates, (a) spectral data collected at a plurality of time points in situ from a training substrate over multiple steps of a multi-step etch process or a multi-step deposition process performed on the training substrate, and (b) a parameter value characterizing at least one physical property of the training substrate, wherein the physical property was modified by the multi-step etch process or by the multi-step deposition process (Feng [0040-117] “machine learning implemented to use the time-series of spectra to extract critical conditions of the wafer - time traces from multiple sensors - to predict the CD (critical dimension) or CD uniformity in analogy to wavelength time traces from wafer to predict local depth - covariance of these non-spectral signals handled by principle component analysis to extract essential information for given time frame, therefore enabling endpoint control at higher accuracy - plasma etch chamber or module, a deposition chamber or module, a spin-rinse chamber or module, a metal plating chamber or module, a clean chamber or module, a bevel edge etch chamber or module, a physical vapor deposition (PVD) chamber or module, a chemical vapor deposition (CVD) chamber or module, an atomic layer deposition (ALD) chamber or module, an atomic layer etch (ALE) chamber or module, an ion implantation chamber or module, a track chamber or module, and any other semiconductor processing systems - associated or used in the fabrication and/or manufacturing of semiconductor wafers” [claim 1] “accessing a virtual carpet generated from a time-series of spectra for an etch process collected during a training” [0001-23] “time-series of spectra information extracted during processing of etch processing operations in order control etch endpoint operations - utilize training processes to generate three dimensional intensity surface profiles - converted into a virtual carpet - real-time processing of wafers to predict or identify an effective etch depth at a current point in time” [abstract] “a time-series of spectra - accessing a virtual carpet - generated from a time-series of spectra for an etch process - polynomial with coefficients represents the virtual carpet - processing a fabrication etch process on a fabrication wafer and generating a carpet defined from a time-series of spectra while processing the fabrication etch process - comparing portions of the carpet and the virtual carpet to identify an endpoint metric of the fabrication etch process” see Fig. 1-11, multiple sensors, real-time, physical quantity/property, machine learning, accessing a virtual carpet, extract essential information for given time frame, utilize training processes to generate three dimensional intensity surface profiles obviously provides receiving training data - a plurality of training substrates, (a) spectral data collected at a plurality of time points in situ from a training substrate over multiple steps of a multi-step etch process or a multi-step deposition process performed on the training substrate, and (b) a parameter value characterizing at least one physical property of the training substrate);
extracting features from the spectral data to provide a separate virtual representation of the spectral data for each of the training substrates; (Feng [0040-117] “machine learning implemented to use the time-series of spectra to extract critical conditions of the wafer” [0001-23] “time-series of spectra information extracted during processing of etch processing operations in order control etch endpoint operations - utilize training processes to generate three dimensional intensity surface profiles - converted into a virtual carpet - real-time processing of wafers to predict or identify an effective etch depth at a current point in time” [abstract] “a time-series of spectra - accessing a virtual carpet - generated from a time-series of spectra for an etch process - polynomial with coefficients represents the virtual carpet - processing a fabrication etch process on a fabrication wafer and generating a carpet defined from a time-series of spectra while processing the fabrication etch process - comparing portions of the carpet and the virtual carpet to identify an endpoint metric of the fabrication etch process” see Fig. 1-11, extract critical conditions of the wafer, time-series of spectra, machine learning, utilize training processes to generate three dimensional intensity surface profiles obviously provides extracting features from the spectral data to provide a separate virtual representation of the spectral data) and
generating the machine learning model by using, for each of the plurality of training substrates, the separate virtual representation of the spectral data and the parameter value characterizing at least one physical property of the training substrate,
wherein the machine learning model is configured to predict the substrate parameter value of a test substrate subjected to the multi-step etch process or the multi-step deposition process using, as inputs, spectral data collected in situ from the test substrate (Feng [0040-117] “machine learning implemented to use the time-series of spectra to extract critical conditions of the wafer - time traces from multiple sensors - to predict the CD (critical dimension) or CD uniformity in analogy to wavelength time traces from wafer to predict local depth - covariance of these non-spectral signals handled by principle component analysis to extract essential information for given time frame, therefore enabling endpoint control at higher accuracy - dynamic time wrapping (DTW) algorithm used - controller 110 handle processing of one or more recipes including multiple set points for various operating parameters - for operating a plasma processing system- instructions communicated to the controller 110 in the form of various individual settings (or program files) - to accomplish one or more processing steps during the fabrication - plasma etch chamber or module, a deposition chamber or module, a spin-rinse chamber or module, a metal plating chamber or module, a clean chamber or module, a bevel edge etch chamber or module, a physical vapor deposition (PVD) chamber or module, a chemical vapor deposition (CVD) chamber or module, an atomic layer deposition (ALD) chamber or module, an atomic layer etch (ALE) chamber or module, an ion implantation chamber or module, a track chamber or module, and any other semiconductor processing systems - associated or used in the fabrication and/or manufacturing of semiconductor wafers.” [claim 1] “accessing a virtual carpet generated from a time-series of spectra for an etch process collected during a training” [0001-23] “time-series of spectra information extracted during processing of etch processing operations in order control etch endpoint operations - utilize training processes to generate three dimensional intensity surface profiles - converted into a virtual carpet - real-time processing of wafers to predict or identify an effective etch depth at a current point in time” [abstract] “a time-series of spectra - accessing a virtual carpet - generated from a time-series of spectra for an etch process - polynomial with coefficients represents the virtual carpet - processing a fabrication etch process on a fabrication wafer and generating a carpet defined from a time-series of spectra while processing the fabrication etch process - comparing portions of the carpet and the virtual carpet to identify an endpoint metric of the fabrication etch process” see Fig. 1-11, controller, dynamic time wrapping (DTW) algorithm, processing multiple recipes including multiple set points for various operating parameters, operating a plasma processing system, multiple sensors, real-time, physical quantity/property, machine learning, accessing a virtual carpet, extract essential information for given time frame, utilize training processes to generate three dimensional intensity surface profiles obviously provides generating the machine learning model by using, for each of the plurality of training substrates, the separate virtual representation of the spectral data and the parameter value characterizing at least one physical property of the training substrate, wherein the machine learning model is configured to predict the substrate parameter value of a test substrate subjected to the multi-step etch process or the multi-step deposition process using, as inputs, spectral data collected in situ from the test substrate).
Application and the reference Feng are analogous arts from the same field of endeavor and contain overlapping structural and functional similarities and both contain machine learning and generating spectra for wafer fabrication processing.
Therefore, it would be obvious to one having ordinary skill in the art at the time of the invention that virtual carpet generated from time-series spectra using machine learning, utilize training processes to generate three-dimensional intensity surface profiles, operations controller, fabrication wafer, ALD and ALE chamber or module, are assumed as generating machine learning model, predict substrate parameter value, process chamber.
As to claim 2, Feng further discloses The method of claim 1, wherein the multi-step etch process or the multi-step deposition process included at least two non-contiguous etching steps or at least two non-contiguous deposition steps (Feng [0040-117] “machine learning implemented to use the time-series of spectra to extract critical conditions of the wafer - predict the CD (critical dimension) or CD uniformity in analogy to wavelength time traces from wafer to predict local depth - during real-time processing (i.e., run-time) - to predict broadband in-situ reflectometry spectra vs. time and intended target etch depth - process enables accurate predication of etch rates at a wafer level, and time to stop the etching -
dynamic time wrapping (DTW) algorithm used - controller 110 handle processing of one or more recipes including multiple set points for various operating parameters - for operating a plasma processing system- instructions communicated to the controller 110 in the form of various individual settings (or program files) - to accomplish one or more processing steps during the fabrication of one or more layers, materials, metals, oxides, silicon, silicon dioxide, surfaces, circuits, and/or dies of a wafer - each of the processing steps to be performed during one or more operations - one or more discrete controller 110s - include a plasma etch chamber or module, a deposition chamber or module, a spin-rinse chamber or module, a metal plating chamber or module, a clean chamber or module, a bevel edge etch chamber or module, a physical vapor deposition (PVD) chamber or module, a chemical vapor deposition (CVD) chamber or module, an atomic layer deposition (ALD) chamber or module, an atomic layer etch (ALE) chamber or module, an ion implantation chamber or module, a track chamber or module, and any other semiconductor processing systems - depending on the process step or steps to be performed” [0001-23] see Fig. 1-11, machine learning, time-series of spectra, controller process recipes, on multiple set points for various operating parameters, instructions of various individual settings or program files and accomplish multiple processing steps time to stop etching, dynamic time wrapping (DTW) algorithm to perform multiple operations for a given time frame obviously includes multi-step etch process or the multi-step deposition process included at least two non-contiguous etching steps or at least two non-contiguous deposition steps).
As to claim 3, Feng further discloses The method of claim 1, wherein the multi-step etch process or the multi-step deposition process included at least two contiguous etching steps or at least two contiguous deposition steps (Feng [0040-117] “machine learning implemented to use the time-series of spectra to extract critical conditions of the wafer - predict the CD (critical dimension) or CD uniformity in analogy to wavelength time traces from wafer to predict local depth - during real-time processing (i.e., run-time) - to predict broadband in-situ reflectometry spectra vs. time and intended target etch depth - process enables accurate predication of etch rates at a wafer level, and time to stop the etching - dynamic time wrapping (DTW) algorithm used - controller 110 handle processing of one or more recipes including multiple set points for various operating parameters - for operating a plasma processing system- instructions communicated to the controller 110 in the form of various individual settings (or program files) - to accomplish one or more processing steps during the fabrication of one or more layers, materials, metals, oxides, silicon, silicon dioxide, surfaces, circuits, and/or dies of a wafer - each of the processing steps to be performed during one or more operations - one or more discrete controller 110s - include a plasma etch chamber or module, a deposition chamber or module, a spin-rinse chamber or module, a metal plating chamber or module, a clean chamber or module, a bevel edge etch chamber or module, a physical vapor deposition (PVD) chamber or module, a chemical vapor deposition (CVD) chamber or module, an atomic layer deposition (ALD) chamber or module, an atomic layer etch (ALE) chamber or module, an ion implantation chamber or module, a track chamber or module, and any other semiconductor processing systems - depending on the process step or steps to be performed” [0001-23] see Fig. 1-11, machine learning, time-series of spectra, controller process recipes, on multiple set points for various operating parameters, instructions of various individual settings or program files and accomplish multiple processing steps time to stop etching, dynamic time wrapping (DTW) algorithm to perform multiple operations for a given time frame obviously includes multi-step etch process or the multi-step deposition process included at least two contiguous etching steps or at least two contiguous deposition steps).
As to claim 4, Feng further discloses The method of claim 1, further comprising: based on the machine learning model and the spectral data collected in situ from the test substrate, changing a duration of an intermediate step of the multi-step etch process or the multi-step deposition process (Feng [0040-117] “machine learning implemented to use the time-series of spectra to extract critical conditions of the wafer - predict the CD (critical dimension) or CD uniformity in analogy to wavelength time traces from wafer to predict local depth - during real-time processing (i.e., run-time) - to predict broadband in-situ reflectometry spectra vs. time and intended target etch depth - process enables accurate predication of etch rates at a wafer level, and time to stop the etching - dynamic time wrapping (DTW) algorithm used - controller 110 handle processing of one or more recipes including multiple set points for various operating parameters - for operating a plasma processing system- instructions communicated to the controller 110 in the form of various individual settings (or program files) - to accomplish one or more processing steps during the fabrication of one or more layers, materials, metals, oxides, silicon, silicon dioxide, surfaces, circuits, and/or dies of a wafer - each of the processing steps to be performed during one or more operations - one or more discrete controller 110s - include a plasma etch chamber or module, a deposition chamber or module, a spin-rinse chamber or module, a metal plating chamber or module, a clean chamber or module, a bevel edge etch chamber or module, a physical vapor deposition (PVD) chamber or module, a chemical vapor deposition (CVD) chamber or module, an atomic layer deposition (ALD) chamber or module, an atomic layer etch (ALE) chamber or module, an ion implantation chamber or module, a track chamber or module, and any other semiconductor processing systems - depending on the process step or steps to be performed” [0001-23] see Fig. 1-11, machine learning, time-series of spectra, controller process recipes, on multiple set points for various operating parameters, instructions of various individual settings or program files and accomplish multiple processing steps time to stop etching, dynamic time wrapping (DTW) algorithm to perform multiple operations for a given time frame obviously includes machine learning model and the spectral data collected in situ from the test substrate, changing a duration of an intermediate step of the multi-step etch process or the multi-step deposition process).
As to claim 5, Feng further discloses The method of claim 1, wherein the spectral data comprises at least two types of spectra collected in situ from the training substrates (Feng [0040-117] “predict the CD (critical dimension) - wavelength time traces from wafer to predict local depth - real-time processing (i.e., run-time), the virtual carpet used to predict broadband in-situ reflectometry spectra vs. time and intended target etch depth - predication of etch rates at a wafer level - in-situ reflectometry or interferometer measures of reflectance of the wafer surface during etching (or deposition), by focusing a light beam on a spot onto the wafer and measuring the intensity of the reflected light in a plurality of wavelengths - broadband in-situ reflectometry is flash lamp/ continuous wave reflectometry” [0001-23] “utilize training processes to generate three dimensional intensity surface profiles - converted into a virtual carpet - real-time processing of wafers to predict or identify an effective etch depth at a current point in time” [abstract] “generated from a time-series of spectra for an etch process - polynomial with coefficients represents the virtual carpet” see Fig. 1-11, real-time, physical quantity/property, etch depth, etching operations, utilize training processes to generate three dimensional intensity surface profiles obviously provides two types of spectra collected in situ from the training substrates).
As to claim 6, Feng further discloses The method of claim 1, wherein the spectral data comprises reflectance spectra collected in situ from the training substrates (Feng [0040-117] “predict the CD (critical dimension) - wavelength time traces from wafer to predict local depth - real-time processing (i.e., run-time), the virtual carpet used to predict broadband in-situ reflectometry spectra vs. time and intended target etch depth - predication of etch rates at a wafer level - in-situ reflectometry or interferometer measures of reflectance of the wafer surface during etching (or deposition), by focusing a light beam on a spot onto the wafer and measuring the intensity of the reflected light in a plurality of wavelengths - broadband in-situ reflectometry is flash lamp/ continuous wave reflectometry” [0001-23] “utilize training processes to generate three dimensional intensity surface profiles - converted into a virtual carpet - real-time processing of wafers to predict or identify an effective etch depth at a current point in time” [abstract] “generated from a time-series of spectra for an etch process - polynomial with coefficients represents the virtual carpet” see Fig. 1-11, real-time, in-situ reflectometry or interferometer, physical quantity/property, etch depth, etching operations, utilize training processes to generate three dimensional intensity surface profiles obviously provides reflectance spectra collected in situ from the training substrates).
As to claim 7, Feng further discloses The method of claim 1, wherein the spectral data comprises emission spectra collected in situ from the training substrates (Feng [0040-117] “predict the CD (critical dimension) - wavelength time traces from wafer to predict local depth - real-time processing (i.e., run-time), the virtual carpet used to predict broadband in-situ reflectometry spectra vs. time and intended target etch depth - predication of etch rates at a wafer level - in-situ reflectometry or interferometer measures of reflectance of the wafer surface during etching (or deposition), by focusing a light beam on a spot onto the wafer and measuring the intensity of the reflected light in a plurality of wavelengths - broadband in-situ reflectometry is flash lamp/ continuous wave reflectometry” [0001-23] “utilize training processes to generate three dimensional intensity surface profiles - converted into a virtual carpet - real-time processing of wafers to predict or identify an effective etch depth at a current point in time” [abstract] “generated from a time-series of spectra for an etch process - polynomial with coefficients represents the virtual carpet” see Fig. 1-11, real-time, in-situ reflectometry or interferometer, physical quantity/property, etch depth, etching operations, utilize training processes to generate three dimensional intensity surface profiles obviously provides emission spectra collected in situ from the training substrates).
As to claim 8, Feng further discloses The method of claim 1, wherein extracting features from the spectral data comprises fitting the spectral data with a polynomial (Feng [0040-117] “predict the CD (critical dimension) - wavelength time traces from wafer to predict local depth - real-time processing (i.e., run-time), the virtual carpet used to predict broadband in-situ reflectometry spectra vs. time and intended target etch depth - predication of etch rates at a wafer level - in-situ reflectometry or interferometer measures of reflectance of the wafer surface during etching (or deposition), by focusing a light beam on a spot onto the wafer and measuring the intensity of the reflected light in a plurality of wavelengths - broadband in-situ reflectometry is flash lamp/ continuous wave reflectometry” [0001-23] “utilize training processes to generate three dimensional intensity surface profiles - converted into a virtual carpet - real-time processing of wafers to predict or identify an effective etch depth at a current point in time” [abstract] “generated from a time-series of spectra for an etch process - polynomial with coefficients represents the virtual carpet” see Fig. 1-11, real-time, polynomial with coefficients, physical quantity/property, etch depth, etching operations, utilize training processes to generate three dimensional intensity surface profiles obviously provides fitting the spectral data with a polynomial).
As to claim 9, Feng further discloses The method of claim 1, wherein the multi-step etch process or the multi-step deposition process is an atomic layer etch process (Feng [0040-117] “[0040-117] “predict the CD (critical dimension) - wavelength time traces from wafer to predict local depth - real-time processing (i.e., run-time), the virtual carpet used to predict broadband in-situ reflectometry spectra vs. time and intended target etch depth - predication of etch rates at a wafer level - in-situ reflectometry or interferometer measures of reflectance of the wafer surface during etching (or deposition), by focusing a light beam on a spot onto the wafer and measuring the intensity of the reflected light in a plurality of wavelengths - broadband in-situ reflectometry is flash lamp/ continuous wave reflectometry - plasma etch chamber or module, a deposition chamber or module, a spin-rinse chamber or module, a metal plating chamber or module, a clean chamber or module, a bevel edge etch chamber or module, a physical vapor deposition (PVD) chamber or module, a chemical vapor deposition (CVD) chamber or module, an atomic layer deposition (ALD) chamber or module, an atomic layer etch (ALE) chamber or module, an ion implantation chamber or module, a track chamber or module, and any other semiconductor processing systems - associated or used in the fabrication and/or manufacturing of semiconductor wafers” [0001-23] “utilize training processes to generate three dimensional intensity surface profiles - converted into a virtual carpet - real-time processing of wafers to predict or identify an effective etch depth at a current point in time” [abstract] “generated from a time-series of spectra for an etch process - polynomial with coefficients represents the virtual carpet” see Fig. 1-11, real-time, atomic layer etch chamber, etch depth, etching operations, utilize training processes to generate three dimensional intensity surface profiles obviously provides an atomic layer etch process).
As to claim 10, Feng further discloses The method of claim 1, wherein the multi-step etch process or the multi-step deposition process is a plasma etching process having at least two non-contiguous etching steps (Feng [0040-117] “machine learning implemented to use the time-series of spectra to extract critical conditions of the wafer - time traces from multiple sensors - to predict the CD (critical dimension) or CD uniformity in analogy to wavelength time traces from wafer to predict local depth - covariance of these non-spectral signals handled by principle component analysis to extract essential information for given time frame, therefore enabling endpoint control at higher accuracy - plasma etch chamber or module, a deposition chamber or module, a spin-rinse chamber or module, a metal plating chamber or module, a clean chamber or module, a bevel edge etch chamber or module, a physical vapor deposition (PVD) chamber or module, a chemical vapor deposition (CVD) chamber or module, an atomic layer deposition (ALD) chamber or module, an atomic layer etch (ALE) chamber or module, an ion implantation chamber or module, a track chamber or module, and any other semiconductor processing systems - associated or used in the fabrication and/or manufacturing of semiconductor wafers” [0001-23] [abstract] see Fig. 1-11, machine learning, plasma etch chamber, time-series of spectra, multiple sensors, real-time, physical quantity/property, machine learning, accessing a virtual carpet, extract essential information for given time frame, utilize training processes to generate three dimensional intensity surface profiles obviously provides multi-step etch process or the multi-step deposition process is a plasma etching process having at least two non-contiguous etching steps).
As to claim 11, Feng further discloses The method of claim 1, wherein the parameter value characterizing at least one physical property of the training substrate is an etch depth or a deposition depth (Feng [0040-117] “predict the CD (critical dimension) - wavelength time traces from wafer to predict local depth - real-time processing (i.e., run-time), the virtual carpet used to predict broadband in-situ reflectometry spectra vs. time and intended target etch depth - predication of etch rates at a wafer level - in-situ reflectometry or interferometer measures of reflectance of the wafer surface during etching (or deposition), by focusing a light beam on a spot onto the wafer and measuring the intensity of the reflected light in a plurality of wavelengths - broadband in-situ reflectometry is flash lamp/ continuous wave reflectometry” [0001-23] “utilize training processes to generate three dimensional intensity surface profiles - converted into a virtual carpet - real-time processing of wafers to predict or identify an effective etch depth at a current point in time” [abstract] “generated from a time-series of spectra for an etch process - polynomial with coefficients represents the virtual carpet” see Fig. 1-11, real-time, physical quantity/property, etch depth, etching operations, utilize training processes to generate three dimensional intensity surface profiles obviously provides the parameter value characterizing at least one physical property of the training substrate is an etch depth or a deposition depth).
As to claim 12, Feng further discloses The method of claim 1, wherein the parameter value characterizing at least one physical property of the training substrate is a critical dimension (Feng [0040-117] “predict the CD (critical dimension) - wavelength time traces from wafer to predict local depth - real-time processing (i.e., run-time), the virtual carpet used to predict broadband in-situ reflectometry spectra vs. time and intended target etch depth - predication of etch rates at a wafer level - in-situ reflectometry or interferometer measures of reflectance of the wafer surface during etching (or deposition), by focusing a light beam on a spot onto the wafer and measuring the intensity of the reflected light in a plurality of wavelengths - broadband in-situ reflectometry is flash lamp/ continuous wave reflectometry” [0001-23] “utilize training processes to generate three dimensional intensity surface profiles - converted into a virtual carpet - real-time processing of wafers to predict or identify an effective etch depth at a current point in time” [abstract] “generated from a time-series of spectra for an etch process - polynomial with coefficients represents the virtual carpet” see Fig. 1-11, real-time, physical quantity/property, etch depth, etching operations, utilize training processes to generate three dimensional intensity surface profiles obviously provides parameter value characterizing at least one physical property of the training substrate is a critical dimension).
As to claim 13, Feng further discloses The method of claim 1, wherein the parameter value characterizing at least one physical property of the training substrate is a sidewall angle (Feng [0040-117] “predict the CD (critical dimension) - wavelength time traces from wafer to predict local depth - real-time processing (i.e., run-time), the virtual carpet used to predict broadband in-situ reflectometry spectra vs. time and intended target etch depth - predication of etch rates at a wafer level - in-situ reflectometry or interferometer measures of reflectance of the wafer surface during etching (or deposition), by focusing a light beam on a spot onto the wafer and measuring the intensity of the reflected light in a plurality of wavelengths - broadband in-situ reflectometry is flash lamp/ continuous wave reflectometry” [0001-23] “utilize training processes to generate three dimensional intensity surface profiles - converted into a virtual carpet - real-time processing of wafers to predict or identify an effective etch depth at a current point in time” [abstract] “generated from a time-series of spectra for an etch process - polynomial with coefficients represents the virtual carpet” see Fig. 1-11, machine learning, plasma etch chamber, time-series of spectra, real-time, physical quantity/property, etch depth, etching operations, utilize training processes to generate three dimensional intensity surface profiles obviously provides parameter value characterizing at least one physical property of the training substrate is a sidewall angle).
As to claim 14, Feng further discloses The method of claim 1, wherein the parameter value characterizing at least one physical property of the training substrate is an overlay (Feng [0040-117] “predict the CD (critical dimension) - wavelength time traces from wafer to predict local depth - real-time processing (i.e., run-time), the virtual carpet used to predict broadband in-situ reflectometry spectra vs. time and intended target etch depth - predication of etch rates at a wafer level - in-situ reflectometry or interferometer measures of reflectance of the wafer surface during etching (or deposition), by focusing a light beam on a spot onto the wafer and measuring the intensity of the reflected light in a plurality of wavelengths - broadband in-situ reflectometry is flash lamp/ continuous wave reflectometry” [0001-23] “utilize training processes to generate three dimensional intensity surface profiles - converted into a virtual carpet - real-time processing of wafers to predict or identify an effective etch depth at a current point in time” [abstract] “generated from a time-series of spectra for an etch process - polynomial with coefficients represents the virtual carpet” see Fig. 1-11, machine learning, plasma etch chamber, time-series of spectra, real-time, physical quantity/property, etch depth, etching operations, utilize training processes to generate three dimensional intensity surface profiles obviously provides parameter value characterizing at least one physical property of the training substrate is an overlay).
As to claim 15, Feng further discloses The method of claim 1, wherein the parameter value characterizing at least one physical property of the training substrate is a critical dimension of recessed features on the substrate (Feng [0040-117] “predict the CD (critical dimension) - wavelength time traces from wafer to predict local depth - real-time processing (i.e., run-time), the virtual carpet used to predict broadband in-situ reflectometry spectra vs. time and intended target etch depth - predication of etch rates at a wafer level - in-situ reflectometry or interferometer measures of reflectance of the wafer surface during etching (or deposition), by focusing a light beam on a spot onto the wafer and measuring the intensity of the reflected light in a plurality of wavelengths - broadband in-situ reflectometry is flash lamp/ continuous wave reflectometry” [0001-23] “utilize training processes to generate three dimensional intensity surface profiles - converted into a virtual carpet - real-time processing of wafers to predict or identify an effective etch depth at a current point in time” [abstract] “generated from a time-series of spectra for an etch process - polynomial with coefficients represents the virtual carpet” see Fig. 1-11, real-time, physical quantity/property, etch depth, etching operations, utilize training processes to generate three dimensional intensity surface profiles obviously provides parameter value characterizing at least one physical property of the training substrate is a critical dimension of recessed features on the substrate).
As to claim 16, Feng further discloses The method of claim 1, wherein receiving the training data comprises, for each training substrate of the plurality of training substrates, receiving a plurality of parameter values characterizing a plurality of physical properties of the training substrate, wherein generating the machine learning model comprises using, for each of the plurality of training substrates, the plurality of parameter values characterizing the plurality of physical properties of the training substrate, and wherein the machine learning model is configured to predict the plurality of parameter values of the test substrate subjected to the multi-step etch process (Feng [0040-117] “machine learning implemented to use the time-series of spectra to extract critical conditions of the wafer - time traces from multiple sensors - to predict the CD (critical dimension) or CD uniformity in analogy to wavelength time traces from wafer to predict local depth - covariance of these non-spectral signals handled by principle component analysis to extract essential information for given time frame, therefore enabling endpoint control at higher accuracy - plasma etch chamber or module, a deposition chamber or module, a spin-rinse chamber or module, a metal plating chamber or module, a clean chamber or module, a bevel edge etch chamber or module, a physical vapor deposition (PVD) chamber or module, a chemical vapor deposition (CVD) chamber or module, an atomic layer deposition (ALD) chamber or module, an atomic layer etch (ALE) chamber or module, an ion implantation chamber or module, a track chamber or module, and any other semiconductor processing systems - associated or used in the fabrication and/or manufacturing of semiconductor wafers” [claim 1] “accessing a virtual carpet generated from a time-series of spectra for an etch process collected during a training” [0001-23] “time-series of spectra information extracted during processing of etch processing operations in order control etch endpoint operations - utilize training processes to generate three dimensional intensity surface profiles - converted into a virtual carpet - real-time processing of wafers to predict or identify an effective etch depth at a current point in time” [abstract] “a time-series of spectra - accessing a virtual carpet - generated from a time-series of spectra for an etch process - polynomial with coefficients represents the virtual carpet - processing a fabrication etch process on a fabrication wafer and generating a carpet defined from a time-series of spectra while processing the fabrication etch process - comparing portions of the carpet and the virtual carpet to identify an endpoint metric of the fabrication etch process” see Fig. 1-11, machine learning, time-series of spectra, extract critical conditions of wafer, multiple sensors, real-time, physical quantity/property, machine learning, accessing a virtual carpet, extract essential information for given time frame, utilize training processes to generate three dimensional intensity surface profiles obviously provides the limitations).
As to claims 17 and 26, Feng further discloses The method of claim 1, wherein the training data further comprises, for each of the plurality of training substrates, at least one feed forward parameter of a process chamber, and wherein generating the machine learning model uses the at least one feed forward parameter (Feng [0040-117] “machine learning implemented to use the time-series of spectra to extract critical conditions of the wafer - time traces from multiple sensors - to predict the CD (critical dimension) or CD uniformity in analogy to wavelength time traces from wafer to predict local depth - covariance of these non-spectral signals handled by principle component analysis to extract essential information for given time frame, therefore enabling endpoint control at higher accuracy - controller 110 handle processing of one or more recipes including multiple set points for various operating parameters (e.g., voltage, current, frequency, pressure, flow rate, power, temperature, etc.), e.g., for operating a plasma processing system” [0001-23] “time-series of spectra information extracted during processing of etch processing operations in order control etch endpoint operations - utilize training processes to generate three dimensional intensity surface profiles - accessing a virtual carpet - generated from a time-series of spectra for an etch process” see Fig. 1-11, machine learning (includes feed forward process), time-series of spectra, extract critical conditions of wafer, accessing a virtual carpet, extract essential information for given time frame, utilize training processes to generate three dimensional intensity surface profiles obviously provides feed forward parameter of a process chamber, and wherein generating the machine learning model uses the at least one feed forward parameter).
As to claims 18 and 27, Feng further discloses The method claim 17, wherein the at least one feed forward parameter is selected from the group consisting of a temperature in the process chamber, a plasma condition in the process chamber, a pressure in the process chamber, a flow rate in the process chamber, a time duration of one or more process steps, and a design and/or configuration of a component in the process chamber (Feng [0040-117] “machine learning implemented to use the time-series of spectra to extract critical conditions of the wafer - time traces from multiple sensors - to predict the CD (critical dimension) or CD uniformity in analogy to wavelength time traces from wafer to predict local depth - covariance of these non-spectral signals handled by principle component analysis to extract essential information for given time frame, therefore enabling endpoint control at higher accuracy - controller 110 handle processing of one or more recipes including multiple set points for various operating parameters (e.g., voltage, current, frequency, pressure, flow rate, power, temperature, etc.), e.g., for operating a plasma processing system - etching operations (e.g., etching tools) - verifying etch performance, verification of deposition performance - quantified in various ways - deposition performance - measured, sensed, approximated, and/or tested in-situ or off-line” [claim 1] “accessing a virtual carpet generated from a time-series of spectra for an etch process collected during a training” [0001-23] “time-series of spectra information extracted during processing of etch processing operations in order control etch endpoint operations - utilize training processes to generate three dimensional intensity surface profiles - accessing a virtual carpet - generated from a time-series of spectra for an etch process” see Fig. 1-11, machine learning (includes feed forward process and sequential multi-steps), time-series of spectra, extract critical conditions of wafer, accessing a virtual carpet, extract essential information for given time frame, utilize training processes to generate three dimensional intensity surface profiles obviously provides limitations).
As to claims 19 and 28, Feng further discloses The method of claim 17, wherein the at least one feed forward parameter is selected from the group consisting of a parameter from (a) a current step of the multi-step etch process or the multi-step deposition process, (b) a previous step prior to the current step of the multi-step etch process or the multi-step deposition process, or (c) a subsequent condition after completion of the current step of the multi-step etch process or the multi-step deposition process (Feng [0040-117] “machine learning implemented to use the time-series of spectra to extract critical conditions of the wafer - time traces from multiple sensors - to predict the CD (critical dimension) or CD uniformity in analogy to wavelength time traces from wafer to predict local depth - covariance of these non-spectral signals handled by principle component analysis to extract essential information for given time frame, therefore enabling endpoint control at higher accuracy” [claim 1] “accessing a virtual carpet generated from a time-series of spectra for an etch process collected during a training” [0001-23] “time-series of spectra information extracted during processing of etch processing operations in order control etch endpoint operations - utilize training processes to generate three dimensional intensity surface profiles - accessing a virtual carpet - generated from a time-series of spectra for an etch process” see Fig. 1-11, machine learning (includes feed forward process and sequential multi-steps), time-series of spectra, extract critical conditions of wafer, accessing a virtual carpet, extract essential information for given time frame, utilize training processes to generate three dimensional intensity surface profiles obviously provides feed forward parameter is selected from the group consisting of a parameter from (a) a current step of the multi-step etch process or the multi-step deposition process, (b) a previous step prior to the current step of the multi-step etch process or the multi-step deposition process, or (c) a subsequent condition after completion of the current step of the multi-step etch process or the multi-step deposition process).
As to the independent claims 20, 23 and 29, the claims recite similar limitations as the independent claim 1 and is rejected using same rational as stated above.
As to claims 21 and 24, Feng further discloses The method of claim 20, wherein the controlling and/or adjusting the process condition comprises controlling or adjusting a length of time during a final step of the multi-step deposition process or of the multi-step etch process (Feng [0040-117] “machine learning implemented to use the time-series of spectra to extract critical conditions of the wafer - predict the CD (critical dimension) or CD uniformity in analogy to wavelength time traces from wafer to predict local depth - during real-time processing (i.e., run-time) - to predict broadband in-situ reflectometry spectra vs. time and intended target etch depth - process enables accurate predication of etch rates at a wafer level, and time to stop the etching - dynamic time wrapping (DTW) algorithm used - controller 110 handle processing of one or more recipes including multiple set points for various operating parameters - for operating a plasma processing system- instructions communicated to the controller 110 in the form of various individual settings (or program files) - to accomplish one or more processing steps during the fabrication of one or more layers, materials, metals, oxides, silicon, silicon dioxide, surfaces, circuits, and/or dies of a wafer - each of the processing steps to be performed during one or more operations - one or more discrete controller 110s - include a plasma etch chamber or module, a deposition chamber or module, a spin-rinse chamber or module, a metal plating chamber or module, a clean chamber or module, a bevel edge etch chamber or module, a physical vapor deposition (PVD) chamber or module, a chemical vapor deposition (CVD) chamber or module, an atomic layer deposition (ALD) chamber or module, an atomic layer etch (ALE) chamber or module, an ion implantation chamber or module, a track chamber or module, and any other semiconductor processing systems - depending on the process step or steps to be performed” [0001-23] see Fig. 1-11, machine learning, time-series of spectra, controller process recipes, on multiple set points for various operating parameters, instructions of various individual settings or program files and accomplish multiple processing steps time to stop etching, dynamic time wrapping (DTW) algorithm to perform multiple operations for a given time frame obviously includes controlling and/or adjusting the process condition comprises controlling or adjusting a length of time during a final step of the multi-step deposition process or of the multi-step etch process).
As to claims 22 and 25, Feng further discloses The method of claim 20, wherein the controlling and/or adjusting the process condition comprises controlling or adjusting a length of time during an intermediate step of the multi-step deposition process or of the multi-step etch process, the intermediate step preceding a final step of the multi-step deposition process or the multi-step etch process (Feng [0040-117] “machine learning implemented to use the time-series of spectra to extract critical conditions of the wafer - predict the CD (critical dimension) or CD uniformity in analogy to wavelength time traces from wafer to predict local depth - during real-time processing (i.e., run-time) - to predict broadband in-situ reflectometry spectra vs. time and intended target etch depth - process enables accurate predication of etch rates at a wafer level, and time to stop the etching - dynamic time wrapping (DTW) algorithm used - controller 110 handle processing of one or more recipes including multiple set points for various operating parameters - for operating a plasma processing system- instructions communicated to the controller 110 in the form of various individual settings (or program files) - to accomplish one or more processing steps during the fabrication of one or more layers, materials, metals, oxides, silicon, silicon dioxide, surfaces, circuits, and/or dies of a wafer - each of the processing steps to be performed during one or more operations - one or more discrete controller 110s - include a plasma etch chamber or module, a deposition chamber or module, a spin-rinse chamber or module, a metal plating chamber or module, a clean chamber or module, a bevel edge etch chamber or module, a physical vapor deposition (PVD) chamber or module, a chemical vapor deposition (CVD) chamber or module, an atomic layer deposition (ALD) chamber or module, an atomic layer etch (ALE) chamber or module, an ion implantation chamber or module, a track chamber or module, and any other semiconductor processing systems - depending on the process step or steps to be performed” [0001-23] see Fig. 1-11, machine learning, time-series of spectra, controller process recipes, on multiple set points for various operating parameters, instructions of various individual settings or program files and accomplish multiple processing steps time to stop etching, dynamic time wrapping (DTW) algorithm to perform multiple operations for a given time frame obviously includes controlling and/or adjusting the process condition comprises controlling or adjusting a length of time during an intermediate step of the multi-step deposition process or of the multi-step etch process, the intermediate step preceding a final step of the multi-step deposition process or the multi-step etch process).
As to claim 30, Feng further discloses The method of claim 29, further comprising: based at least in part on the in situ metrology values, adjusting a process setting of the process chamber (Feng [0040-117] “during real-time processing (i.e., run-time) - predict broadband in-situ reflectometry spectra vs. time and intended target etch depth - process enables accurate predication of etch rates at a wafer level, and time to stop the etching - dynamic time wrapping (DTW) algorithm used - controller 110 handle processing of one or more recipes including multiple set points for various operating parameters - for operating a plasma processing system- instructions communicated to the controller 110 in the form of various individual settings (or program files) - to accomplish one or more processing steps during the fabrication of one or more layers, materials, metals, oxides, silicon, silicon dioxide, surfaces, circuits, and/or dies of a wafer - each of the processing steps to be performed during one or more operations - one or more discrete controller 110s - include a plasma etch chamber or module, a deposition chamber or module, a spin-rinse chamber or module, a metal plating chamber or module, a clean chamber or module, a bevel edge etch chamber or module, a physical vapor deposition (PVD) chamber or module, a chemical vapor deposition (CVD) chamber or module, an atomic layer deposition (ALD) chamber or module, an atomic layer etch (ALE) chamber or module, an ion implantation chamber or module, a track chamber or module, and any other semiconductor processing systems - depending on the process step or steps to be performed” [0001-23] see Fig. 1-11, machine learning, multiple sensors, time-series of spectra, controller process recipes, on multiple set points for various operating parameters, instructions of various individual settings or program files and accomplish multiple processing steps time to stop etching, dynamic time wrapping (DTW) algorithm to perform multiple operations for a given time frame obviously provides in situ metrology values, adjusting a process setting of the process chamber).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. The prior art made of record:
Feng, et al. USPGPub No. 2018/0182632 A1 discloses a computer implemented processes for examining time-series spectra extracted during processing of etch processing operations to control etch endpoint operations, utilize training processes to generate three-dimensional intensity surface profiles during real-time processing of wafers to predict or identify effective etch depth at a current point in time to determine etch endpoints reached.
Koopman, et al. USPGPub No. 2021/0374936 A1 discloses a method for training a deep learning model of a patterning process obtaining training data including input image of substrate having plurality of features and generating predicted image by modeling and/or simulation with the deep learning model using the input image and assigning a set of classes to a feature within the predicted image and generating a trained deep learning model.
Funk, et al. USPGPub No. 2009/0242513 A1 discloses a method of a substrate processing using multilayer processing sequences and Multi-Layer/ Multi-Input/Multi-Output (MLMIMO) models and libraries include plurality of masking layer creation procedures, pre-processing measurement procedures, Partial-Etch (P-E) procedures, Final-Etch (F-E) procedures, and post-processing measurement procedures.
Bailey, et al. USP No. 10,032,681 B2 discloses a method for monitoring geometric parameter value for multiple features produced on a substrate during an etch process measuring optical signals and determining to correlate with target geometric parameter values for features, applying to a model to predict the target geometric parameter values from measured optical signals and comparing current value of target geometric parameter and repeating until current value of target geometric parameter being etched reached endpoint value.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Md Azad whose telephone @(571)272-0553 or email: md.azad@uspto.gov. The examiner can normally be reached on Mon-Thu 9AM-5PM.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Mohammad Ali can be reached on (571)272-4105. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from Patent Center and the Private Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from Patent Center or Private PAIR. Status information for unpublished applications is available through Patent Center and Private PAIR for authorized users only. Should you have questions about access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
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) Form at https://www.uspto.gov/patents/uspto-automated- interview-request-air-form.
/Md Azad/
Primary Examiner, Art Unit 2119