DETAILED ACTION
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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 6/11/26 has been entered.
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 .
Response to Arguments
Applicant's arguments filed 6/11/26 have been fully considered.
Applicant has argued that Arabshahi fails to teach or suggest combining sensor data having different temporal dimensionality. However, the argument is not persuasive because the broad term is not specifically defined in the Specification and Arabshahi clearly teaches and suggests (Paragraph 53) combining sensor data having different temporal dimensionality as the term is broadly used in Applicants specification and Claims. Note that the neural network (Arabshahi) comprises a class of artificial neural networks where connections between nodes form a directed graph along a temporal sequence. This allows the neural network to handle temporal dynamic behavior. Unlike simple neural networks, RNNs may include a saved internal state that processes sequences of inputs. As described above, the outputs from the sensors of the processing chamber may be analyzed and fed into the model in real time as they are received. This generates a time sequence of inputs that may be analyzed sequentially as a temporal sequence within the model. The RRN uses its internal state memory to recognize current conditions as well as previous conditions that indicate a changing trajectory of sensor values. In some embodiments, the model may use a Long-Short Term Memory (LSTM) model designed to handle gaps between important events in a time series.
In support, Applicant has further argued that different temporal dimensionality refers to different sampling rates. However, the argument is not persuasive at least because the specification uses the term “temporal resolution” when describing different sampling rates. Further, the Prior Art teaches collecting from multiple sensors that implicitly collect data at different rates. Guha teaches (Paragraph 50 and Table A) the sensors may include one or more of an optical emission spectrometry (OES) sensor, a pressure sensor, a voltage sensor, a current sensor, a temperature sensor, a flow rate sensor, frequency sensor, a power sensor, a metrology sensor, and combinations of two or more thereof. Arabshahi teaches (Paragraph 39) different categories may include pressure, gas flow, optical emission spectrum, RF emission, voltage, current, position, and/or any other used in semiconductor processing systems.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 19, 21, 24, 25, 27, 28, 30, 31 and 33 are rejected under 35 U.S.C. 103 as being unpatentable over US Publication 2018/0082826 to Guha et al. in view of US Publication 2021/0116896 to Arabshahi et al.
Regarding Claim 19, Guha et al. teaches a computer-implemented method for controlling a wafer production process in real-time (Paragraphs 44, 81 102, 105, 122) using a trained machine learning, ML, model (150, 180), the method comprising: receiving sensor data from a plurality of sensors (136) monitoring the wafer production process in real-time; inputting the sensor data from the plurality of sensors into a neural network (Paragraphs 83-85) of the trained ML model (150, 180); generating, using the trained ML model (150, 180), a latent representation of a state of a plasma used in the wafer production process (processing state of the plasma reactor); and adjusting in real-time, using the generated latent representation, at least one control parameter (compensation processing and turning knobs) of a plasma reactor used in the wafer production process
Regarding Claim 19, Guha et al. teaches the method of the invention substantially as claimed, but does not expressly teach combining sensor data having different temporal dimensionality. However, Arabshahi et al. teaches (Paragraph 53) combining sensor data having different temporal dimensionality in a semiconductor plasma processing environment. It would have been obvious to one of ordinary skill in the art at the time of the claimed invention to combine sensor data having different temporal dimensionality in the method of Guha et al. in order to incorporate the changing trajectory of multiple sensor values in real time with predictable results.
Regarding Claim 21, Guha et al. teaches receiving sensor data comprises receiving at least one of: RF power applied to the plasma reactor, temperature of chamber furniture inside the plasma reactor, pressure inside the plasma reactor, gas flow rate into the plasma reactor, plasma impedance, and plasma electron density (See at least Paragraph 50 and Table A).
Regarding Claim 24, Guha et al. teaches comparing the generated latent representation of the state of the plasma with a desired latent representation of an ideal state of the plasma; and identifying any difference (See at least Paragraphs 16 and 99) between the generated and desired latent representations.
Regarding Claim 25, Guha et al. teaches adjusting at least one control parameter of a plasma reactor used in the wafer production process comprises: determining at least one parameter of the wafer production process to adjust to minimize any identified difference between the generated latent representation and the desired latent representation; and adjusting (Paragraph 52) the determined at least one parameter.
Regarding Claim 27, Guha et al. teaches combining the sensor data comprises combining sensor data having different spatial and/or temporal dimensionality (Paragraph 42).
Regarding Claim 28, Guha et al. teaches a computer-implemented method for training a machine learning, ML model (150, 180) for controlling a wafer production process in real-time (Paragraphs 44, 81 102, 105, 122), the method comprising: receiving training data (processing data and stored data offline; See at least Paragraph 82) comprising sensor data from a plurality of sensors (136) monitoring a wafer production process; inputting the training data into a neural network (Paragraphs 83-85) of the ML model (150, 180); and training the neural network of the ML model (150, 180) to generate a latent representation of a state of a plasma (processing state) in a plasma reactor used in the wafer production process.
Regarding Claim 30, Guha et al. teaches (See at least Paragraph 50 and Table A) each set of data items further comprises at least one of: RF power applied to the plasma reactor, temperature inside the plasma reactor, pressure inside the plasma reactor, gas flow rate into the plasma reactor, plasma impedance, and plasma electron density.
Regarding Claim 31, Guha et al. teaches training the neural network comprises training an encoder of the neural network to: combine each set of data items to generate a latent representation of the state of the plasma at a particular point in time.
Regarding Claim 33, Guha et al. teaches training the neural network further comprises: inputting, into the neural network, a desired latent representation of an ideal state of the plasma; training the neural network to identify any difference (compensation vector) between each generated latent representation and the desired latent representation (See at least Paragraphs 72 and 99); and determining at least one parameter (compensation value) of the wafer production process to adjust to minimize any identified difference between each generated latent representation and the desired latent representation.
Claims 20 and 29 are rejected under 35 U.S.C. 103 as being unpatentable over US Publication 2018/0082826 to Guha et al. in view of US Publication 2021/0116896 to Arabshahi et al. and in view of US Publication 2007/0224709 to Ogasawara et al.
Regarding Claims 20 and 29, Guha et al. teaches receiving sensor data comprises at least one optical emission spectrograph of the plasma (Paragraphs 50, 66, 74) and additional sensors may be used (Paragraph 51), but does not expressly teach an image of the plasma us used as sensor data. However, the use of image sensor data is well known for plasma process control. For example, Ogasawara et al. teaches (Paragraphs 57 and 58) monitor (50) camera capturing an image of a plasma may be used as a process controller (60) input regarding the state of a plasma sheath. It would have been obvious to one of ordinary skill in the art at the time of the claimed invention to provide at least one image of the plasma as taught by Osasawara et al. as a data sensor input in the method of Guha et al. in order to provide plasma sheath data and process control with predictable results.
Claim 23 is rejected under 35 U.S.C. 103 as being unpatentable over US Publication 2018/0082826 to Guha et al. in view of US Publication 2021/0116896 to Arabshahi et al. and in view of US Publication 2020/166909 to Noone et al.
Regarding Claim 23, Guha et al. does not expressly teach the neural network
comprises an autoencoder. However, an autoencoder is a well-known algorithm for data set analysis in a machine learning process including neural network (Noone et al. Paragraphs 9 and 225) It would have been obvious to one of ordinary skill in the art at the time of the claimed invention to provide an autoencoder as taught by Noone et al. in the method of Guha et al. in order to provide machine learning process control with predictable results.
Claims 26 is rejected under 35 U.S.C. 103 as being unpatentable over US Publication 2018/0082826 to Guha et al. in view of US Publication 2021/0116896 to Arabshahi et al. and in view of US Publication 2020/0111650 to Oka.
Regarding Claim 26, Guha et al. does not expressly teach outputting an alert to an operator of the plasma reactor when the identified difference between the generated and latent representations exceeds a threshold value or cannot be minimized by adjusting at least one parameter. However, use of an operator alarm is well known in plasma process control operations. For example, Oka teaches an alarm unit for issuing an alarm when a predetermined degree of change is detected in a plasma processing condition (Paragraph 160) It would have been obvious to one of ordinary skill in the art at the time of the claimed invention to provide an alarm as taught by Oka in the method of Guha et al. in order to notify an operator in the well-known manner.
Claim 32 is rejected under 35 U.S.C. 103 as being unpatentable over US
Publication 2018/0082826 to Guha et al. in view of US Publication 2021/0116896 to Arabshahi et al. and in view of US Patent 6,351,683 to Johnson et al.
Regarding Claim 32, Guha et al. teaches training the neural network further
comprises training a decoder (implicit) of the neural network to: reconstruct, from the generated latent representation, a set of data items corresponding to the generated
latent representation, but does not expressly teach a step to minimize, using
backpropagation, a difference between the set of data items and the reconstructed set of data items. However, backpropagation is a well-known algorithm for neural network training. For example, Johnson et al. teaches backpropagation algorithm for controlling a plasma process (Col. 14, Lines 59-67) by training a neural network. It would have been obvious to one of ordinary skill in the art at the time of the claimed invention to provide a backpropagation algorithm as taught by Johnson et al. in the method of
Guha et al. in order to provide neural network training in a plasma control process with predictable results.
Conclusion
All claims are identical to or patentably indistinct from, or have unity of invention with claims in the application prior to the entry of the submission under 37 CFR 1.114 (that is, restriction (including a lack of unity of invention) would not be proper) and all claims could have been finally rejected on the grounds and art of record in the next Office action if they had been entered in the application prior to entry under 37 CFR 1.114. Accordingly, THIS ACTION IS MADE FINAL even though it is a first action after the filing of a request for continued examination and the submission under 37 CFR 1.114. See MPEP § 706.07(b). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Roberts P Culbert whose telephone number is (571)272-1433. The examiner can normally be reached Monday thru Thursday 7:30 AM-6 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, Parviz Hassanzadeh can be reached at 571-272-1435. 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.
/ROBERTS P CULBERT/Primary Examiner, Art Unit 1716
Prosecution Insights