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 received.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 08/15/2024 is being considered by the examiner.
Claim Objections
Claims 6 and 15 are objected to because of the following informalities: “converting another set of process data” should be “converting the another set of process data” in claims 6 and 15. Appropriate correction is required.
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.
Claims 1, 3, 5-10, 12, 14-18 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent Publication No. 2009/0292386 to Cheng et al. (“Cheng”) in view of U.S. Patent Application Publication No. 2023/0376746 to Woo et al. (“Woo”), and further in view of Wu, Haixu, et al. "Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting." Advances in neural information processing systems 34 (2021) (“Wu”). (Note that Cheng corresponds to U.S. Patent No. 8,095484 cited in Applicant’s IDS.).
Regarding claim1:
A virtual metrology method based on a long sequence time-series prediction framework (Cheng at Abstract.
Cheng discloses processing of time-series data (see par. [0049]), but does not explicitly disclose that the “virtual metrology method” is “based on a long sequence time-series prediction framework.” However, in a same field of endeavor, processing time-series data (and thus analogous art), Woo discloses a “time-index model for forecasting time-series data” and discloses that the time-series data can be based on long sequence time-series forecasting. Woo at Abstract and par. [0030]. Based on the disclosure in Woo, those skilled in the art would have understood that the time-series data of Cheng can be based on a long sequence time-series prediction framework. Accordingly, it would have been obvious to process the long sequence time-series data, as disclosed by Woo, in the virtual metrology method of Cheng. One skilled in the art would have been motivated to do so because it would have been a combination of known elements using known methods to yield predictable results. See MPEP § 2143.I.A.), comprising:
configuring a processor to obtain a plurality of sets of process data and a plurality of metrology data (Cheng’s AVM Server 30a is configured to obtain data sets [1-m]. Cheng at pars. [0035], [0038], [0041]-[0042], and [0086] and Figs. 1-2. Cheng does not explicitly disclose a processor, but Woo discloses that such time-series data processing can be performed by computing devices with processors. Woo at par. [0041] and Fig. 4.),
wherein the sets of process data comprise past data and future data of a manufacturing device relative to a time point (Data sets [1-n] include “past data” and data sets [n+1 to m] include “future data.” Cheng at pars. [0041]-[0042] and Table 1. Cheng discloses that its method can be used on workpieces (e.g., wafer) in the semiconductor and TFT-LCD industries. Cheng at par. [0005].), and
the metrology data comprise a plurality of actual measurement values of a measurement device (Data sets [y1-yn+1] include “actual measurement values” of process apparatus. Cheng at pars. [0040]-[0042] and Table 1.);
performing a period calculation operation, wherein the period calculation operation comprises: configuring the processor to calculate the sets of process data and the metrology data according to an autocorrelation function and a confidence interval function of the autocorrelation function so as to find out a memorizing length, a forecasting length and a full-periodic pattern length for the long sequence time-series prediction framework (Cheng in view of Woo does not explicitly discloses the claimed period calculation operation according to an autocorrelation function and a confidence interval. In a same field of endeavor, processing long-term series forecasting data (and thus analogous art), Wu disclose the use of an auto-correlation mechanism to discover period-based dependencies and aggregate sub-series using softmax normalized confidences (“confidence interval function”). Wu at Sec. 3.2. It would have been obvious and one skilled in the art would have been motivated to incorporate the autocorrelation mechanism into the system of Cheng in view of Woo in order to “naturally achieve O(L log L) complexity and yield consistent state-of-the-art performance in extensive real-world datasets.” Wu at Conclusion. Wu’s input length L (also referred to as input length I) corresponds to the “memorizing length” and the prediction length O corresponds to “forecasting length.” Wu at Sec. 3.2 and Table 4 and Figs. 1-2. In Fig. 3(d), Wu discloses aggregated periods [1-N], which corresponds to “a full-periodic pattern length for the long sequence time-series prediction framework.” Thus, Cheng in view of Wu discloses the claimed “period calculation.”);
performing a modeling operation, wherein the modeling operation comprises: configuring the processor to use the memorizing length, the forecasting length and the full-periodic pattern length to establish a virtual metrology model based on the long sequence time-series prediction framework (Cheng discloses a model-creation server 60. Cheng at par. [0089] and Figs. 1 and 5. Cheng in view of Woo and Wu will “establish a virtual metrology model,” as claimed. Cheng at pars. [0010] and [0086] and Fig. 6A, step 170.),
wherein the virtual metrology model based on the long sequence time-series prediction framework comprises at least one deep learning network model (Cheng does not explicitly disclose using a “deep learning network model,” but indicates that it can be “any other prediction algorithm.” Cheng at par. [0010]. Woo discloses a deep learning model referred to as “DeepTIMe.” Woo at [0017]-[0018]. Based on the suggestion in Cheng that any prediction algorithm can be used, it would have been obvious to incorporate Woo’s algorithm into Cheng in order to “accurately predict the data in the horizon window.” Woo at par. [0010]. Accordingly, Cheng in view of Woo and Wu discloses the claimed virtual metrology model. Because both Cheng and Woo relate to developing prediction models, there would have been a reasonable chance of success. See MPEP 2143.I.G.); and
performing a calculating operation, wherein the calculating operation comprises: configuring the processor to obtain at least one of another set of process data and another actual measurement value of the manufacturing device, and executing one of a first step and a second step according to whether the another actual measurement value is obtained, thereby calculating one of a phase-one virtual metrology value and a phase-two virtual metrology value of the manufacturing device (Cheng in view of Woo and Wu performs the claimed “calculating operation.” Cheng at pars. [0124]-[0126] and Fig. 7A, phase-one VM step 300 (“first step”) and phase-two VM step 400 (“second step”). Steps 300 and 400 will be modified based on the autocorrelation function of Wu and the incorporation of long sequence time-series prediction framework of Woo, as discussed above.);
wherein the first step comprises calculating the phase-one virtual metrology value by the another set of process data according to the virtual metrology model based on the long sequence time-series prediction framework (Cheng in view of Woo and Wu performs the claimed “first step.” Cheng at pars. [0124]-[0125], Fig. 7A.), and
the second step comprises calculating the phase-two virtual metrology value of the manufacturing device by the another set of process data and the another actual measurement value according to the virtual metrology model based on the long sequence time-series prediction framework (Cheng in view of Woo and Wu performs the claimed “second step.” Cheng at par. [0126] and Fig. 7A.).
Regarding claim 3: The virtual metrology method based on the long sequence time-series prediction framework of claim 1,
wherein the period calculation operation further comprises: performing a first period calculating step, wherein the first period calculating step comprises defining a searching range, and the searching range is a positive integer greater than 1 (Wu discloses searching an input time series X with a length L (“search range”). Wu at sec. 3.2 and Fig. 2.);
performing a second period calculating step, wherein the second period calculating step comprises setting a lag value to 1 (Wu discloses a time series X with its lag series Xt-τ, where τ is a period length (“lag value”). Eq. 6 shows that in the auto-correlation calculations, τ is initially set to 1. Wu at Sec. 3.2 and Eq. 6.);
performing a third period calculating step, wherein the third period calculating step comprises calculating the sets of process data and the metrology data according to the autocorrelation function and the confidence interval function of the autocorrelation function to generate an autocorrelation function value and a confidence interval (Wu discloses calculation of the softmax normalized confidence RQ,K(τk) (“confidence interval”) and the auto-correlation(Q,K,V) (“an autocorrelation function value”). Wu at Sec. 3.2 and Eq. 6.);
performing a fourth period calculating step, wherein the fourth period calculating step comprises adding the lag value by 1 to generate an added lag value, and then setting the lag value to the added lag value (For calculating the auto-correlation, Wu discloses that period τ (“lag value”) is incremented by 1.); and
performing a fifth period calculating step, wherein the fifth period calculating step comprises judging whether the lag value exceeds the searching range to generate a judgment result, and then determining the full-periodic pattern length according to the judgment result (As part of the incrementing of period τi in Eq. 6, a check is made to see if i exceeds the constant k (“judgement result”), which is based on length L (“searching range”). Wu discloses aligning similar-series that are at the same phase position of estimated periods and then aggregating the sub-series (e.g., periods 1-N) by softmax normalized confidences (“determining the full-periodic pattern length”). Wu at Sec. 3.2 and Fig. 3(d).).
Regarding claim 5: The virtual metrology method based on the long sequence time-series prediction framework of claim 1,
wherein in the calculating operation, in response to determining that the another actual measurement value is not obtained, performing the first step to calculate the phase-one virtual metrology value of the manufacturing device (Cheng discloses that a phase-one VM step (e.g., phase-one VM step 300) corresponds to modeling of process data and that when an actual measurement value is received, a phase-two VM step (e.g., phase-two VM step 400) modeling is performed. Cheng at par. [0015] and Fig. 7A. Thus, if the collected data is determined to be process data rather than metrology data, then it means that “the another actual measurement value is not obtained” and a phase-one VM step is performed. Cheng at pars. [0015], [0124]-[0125] and Fig. 7A (step 320 indicates that the phase-one virtual metrology value computing is always performed on the process data). Thus, the claimed determining is rendered obvious by Cheng in view of Woo and Wu.); and
in response to determining that the another actual measurement value is obtained, performing the second step to calculate the phase-two virtual metrology value of the manufacturing device (Phase-two VM step 400 is performed when actual measurement data is collected. Cheng at pars. [0126]-[0129] and Fig. 7A, steps 420 and 490 (and associated intervening steps).).
Regarding claim 6: The virtual metrology method based on the long sequence time-series prediction framework of claim 5,
wherein the first step comprises: converting another set of process data of the manufacturing device into a set of format length process data according to the memorizing length and the forecasting length, and then inputting the set of format length process data of the manufacturing device into the virtual metrology model based on the long sequence time-series prediction framework, thereby calculating the phase-one virtual metrology value of the manufacturing device (As discussed above with respect to claim 1, the modified system of Cheng in view of Woo and Wu will use long sequence time-series prediction framework and the output of Wu’s auto-correlation (“set of format length process data”) that is sent to Cheng’s VM computing step 320 (see Fig. 7A of Cheng) will be based on Wu’s input length L (“memorizing length”) and the prediction length O (“forecasting length”). Wu at Sec. 3.2, Table 4 and Figs. 1-2. Cheng discloses collecting and converting process data into a phase-one virtual metrology value (“phase-one virtual metrology value of the manufacturing device”). Cheng at pars. [0124]-[0125] and Fig. 7A.).
Regarding claim 7: The virtual metrology method based on the long sequence time-series prediction framework of claim 5, wherein the second step comprises:
performing a strategy selection confirming step on the another actual measurement value of the manufacturing device to generate a confirmation result (Cheng discloses confirming whether there exists an instruction for a manual activation at step 450 (“confirming step on the another actual measurement value of the manufacturing device to generate a confirmation result”). Cheng at pars. [0128] and [0134] and Fig. 7A, step 450.), and
performing one of a first strategy step and a second strategy step according to the confirmation result to update the virtual metrology model based on the long sequence time-series prediction framework (Cheng discloses a retraining step 460 (“second strategy step”). Cheng at par. [0128] and Fig. 7A, step 470 tuning (“first strategy step”), step 460; and
inputting the another set of process data of the manufacturing device into the virtual metrology model based on the long sequence time-series prediction framework, thereby calculating the phase-two virtual metrology value of the manufacturing device (As discussed above with respect to claim 1, the modified system of Cheng in view of Woo and Wu will use long sequence time-series prediction framework. Cheng discloses calculating the phase-two virtual meteorology value at step 490. Cheng at par. [0129] and Fig. 7A, step 490.).
Regarding claim 8: The virtual metrology method based on the long sequence time-series prediction framework of claim 7,
wherein the strategy selection confirming step comprises: confirming whether the manufacturing device performs a manual activation operation (Cheng discloses confirming whether there exists an instruction for a manual activation at step 450 (“confirming whether the manufacturing device performs a manual activation operation”). Cheng at pars. [0128] and [0134] and Fig. 7A, step 450.);
wherein in response to determining that the confirmation result is no, the second step further comprises: confirming whether the virtual metrology model based on the long sequence time-series prediction framework needs to be refreshed to generate a refreshing confirmation result (As discussed above with respect to claim 1, the modified system of Cheng in view of Woo and Wu will use long sequence time-series prediction framework. Cheng discloses checking for instruction of model refreshing at step 450. Cheng at par. [0128] and Fig. 7A, step 450.), and
determining whether to perform the first strategy step according to the refreshing confirmation result (Cheng discloses that tuning step 470 (“first strategy step”) is performed if the result of step 450 is false. Cheng at par. [0128] and Fig. 7A, step 450 and step 470.);
wherein in response to determining that the confirmation result is yes, the second step performs the second strategy step (Cheng discloses that retraining model step 460 (“second strategy step”) is performed if the result of step 450 is true. Cheng at par. [0128] and Fig. 7A, step 450 and step 460.);
wherein the manual activation operation comprises that the manufacturing device is expected to change significantly (Cheng discloses that when a newly-ported set of models is in operation (“manufacturing device is expected to change significantly”), the manual activation step 450 is set to true to retrain the newly-ported set of models. Cheng at par. [0128] and Fig. 7A.).
Regarding claim 9: The virtual metrology method based on the long sequence time-series prediction framework of claim 8,
wherein in the second step, the first strategy step comprises updating the virtual metrology model based on the long sequence time-series prediction framework according to the memorizing length and the forecasting length (Cheng discloses that tuning step 470 (“first strategy step”) is performed if the process apparatus has not been idle for a long period of time or if the model in operation is not a newly-ported set. Cheng at par. [0128] and Fig. 7A. Thus, the existing settings of memorizing length and the forecasting length will be used.); and
the second strategy step comprises reperforming the period calculation operation to find another memorizing length, another forecasting length and another full-periodic pattern length, and then updating the virtual metrology model based on the long sequence time-series prediction framework according to the another memorizing length, the another forecasting length and the another full-periodic pattern length (Cheng disclose that that the retraining model step 460 (“second strategy step”) includes updating the historical process and metrology data and rebuilding the VM models. Cheng at par. [0128]. In order to rebuild the VM modes with updated historical process and metrology data, the period calculation operation will need to be performed again, which will result in finding another memorizing length, another forecasting length and another full-periodic pattern length, as discussed in claim 1.).
Regarding claim 10:
A virtual metrology system based on a long sequence time-series prediction framework (Cheng at Abstract. Cheng discloses processing of time-series data (see par. [0049] but does not explicitly disclose that the “virtual metrology method” is “based on a long sequence time-series prediction framework.” However, in a same field of endeavor, processing time-series data (and thus analogous art), Woo discloses a “time-index model for forecasting time-series data” and discloses that the time-series data can be based on long sequence time-series forecasting. Woo at Abstract and par. [0030]. Because both Cheng and Woo disclose processing of time-series data, it would have been obvious to process the long sequence time-series data, as disclosed by Woo, in the virtual metrology method of Cheng. One skilled in the art would have been motivated to do so because it would have been a combination of known elements using known methods to yield predictable results. Se MPEP § 2143.I.A.), comprising:
a memory configured to store a plurality of sets of process data and a plurality of metrology data, wherein the sets of process data comprise past data and future data of a manufacturing device relative to a time point, and the metrology data comprise a plurality of actual measurement values of a measurement device; and a processor electrically connected to the memory, wherein the processor receives the sets of process data and the actual measurement values (AVM Server 30a is configured to obtain data sets [1-m]. Cheng at pars. [0035], [0038], [0041]-[0042], and [0086] and Figs. 1-2. Cheng does not explicitly disclose a processor and memory, but Woo discloses that such processing is performed by computing devices with processors and memory. Woo at par. [0041] and Fig. 4. The remaining features are similar to those discussed above with respect to claim 1 and thus are rendered obvious by Cheng in view of Woo and Wu as discussed above.), and is configured to:
perform a period calculation operation, wherein the period calculation operation comprises: calculating the sets of process data and the metrology data according to an autocorrelation function and a confidence interval function of the autocorrelation function so as to find out a memorizing length, a forecasting length and a full-periodic pattern length for the long sequence time-series prediction framework; perform a modeling operation, wherein the modeling operation comprises: using the memorizing length, the forecasting length and the full-periodic pattern length to establish a virtual metrology model based on the long sequence time-series prediction framework, wherein the virtual metrology model based on the long sequence time-series prediction framework comprises at least one deep learning network model; and performing a calculating operation, wherein the calculating operation comprises: obtaining at least one of another set of process data and another actual measurement value of the manufacturing device, and executing one of a first step and a second step according to whether the another actual measurement value is obtained, thereby calculating one of a phase-one virtual metrology value and a phase-two virtual metrology value of the manufacturing device; wherein the first step comprises calculating the phase-one virtual metrology value by the another set of process data according to the virtual metrology model based on the long sequence time-series prediction framework, and the second step comprises calculating the phase-two virtual metrology value of the manufacturing device by the another set of process data and the another actual measurement value according to the virtual metrology model based on the long sequence time-series prediction framework (Please see analysis in claim 1.) .
Regarding claim 12: The virtual metrology system based on the long sequence time-series prediction framework of claim 10,
wherein the period calculation operation further comprises: performing a first period calculating step, wherein the first period calculating step comprises defining a searching range, and the searching range is a positive integer greater than 1; performing a second period calculating step, wherein the second period calculating step comprises setting a lag value to 1; performing a third period calculating step, wherein the third period calculating step comprises calculating the sets of process data and the metrology data according to the autocorrelation function and the confidence interval function of the autocorrelation function to generate an autocorrelation function value and a confidence interval; performing a fourth period calculating step, wherein the fourth period calculating step comprises adding the lag value by 1 to generate an added lag value, and then setting the lag value to the added lag value; and performing a fifth period calculating step, wherein the fifth period calculating step comprises judging whether the lag value exceeds the searching range to generate a judgment result, and then determining the full-periodic pattern length according to the judgment result (Please see analysis in claim 3.).
Regarding claims 14: The virtual metrology system based on the long sequence time-series prediction framework of claim 10,
wherein in the calculating operation, in response to determining that the another actual measurement value is not obtained, performing the first step to calculate the phase-one virtual metrology value of the manufacturing device; and in response to determining that the another actual measurement value is obtained, performing the second step to calculate the phase-two virtual metrology value of the manufacturing device (Please see analysis in claim 5.).
Regarding claim 15: The virtual metrology system based on the long sequence time-series prediction framework of claim 14,
wherein the first step comprises: converting another set of process data of the manufacturing device into a set of format length process data according to the memorizing length and the forecasting length, and then inputting the set of format length process data of the manufacturing device into the virtual metrology model based on the long sequence time-series prediction framework, thereby calculating the phase-one virtual metrology value of the manufacturing device (Please see analysis in claim 6.).
Regarding claim 16: The virtual metrology system based on the long sequence time-series prediction framework of claim 14,
wherein the second step comprises: performing a strategy selection confirming step on the another actual measurement value of the manufacturing device to generate a confirmation result, and performing one of a first strategy step and a second strategy step according to the confirmation result to update the virtual metrology model based on the long sequence time-series prediction framework; and inputting the another set of process data of the manufacturing device into the virtual metrology model based on the long sequence time-series prediction framework, thereby calculating the phase-two virtual metrology value of the manufacturing device (Please see analysis in claim 7.).
Regarding claim 17: The virtual metrology system based on the long sequence time-series prediction framework of claim 16,
wherein the strategy selection confirming step comprises: confirming whether the manufacturing device performs a manual activation operation; wherein in response to determining that the confirmation result is no, the second step further comprises: confirming whether the virtual metrology model based on the long sequence time-series prediction framework needs to be refreshed to generate a refreshing confirmation result, and determining whether to perform the first strategy step according to the refreshing confirmation result; wherein in response to determining that the confirmation result is yes, the second step performs the second strategy step; wherein the manual activation operation comprises that the manufacturing device is expected to change significantly (Please see analysis in claim 8.).
Regarding claim 18: The virtual metrology system based on the long sequence time-series prediction framework of claim 17,
wherein in the second step, the first strategy step comprises updating the virtual metrology model based on the long sequence time-series prediction framework according to the memorizing length and the forecasting length; and the second strategy step comprises reperforming the period calculation operation to find another memorizing length, another forecasting length and another full-periodic pattern length, and then updating the virtual metrology model based on the long sequence time-series prediction framework according to the another memorizing length, the another forecasting length and the another full-periodic pattern length (Please see analysis in claim 9.).
Claims 2 and 11 are rejected under 35 U.S.C. 103 as being unpatentable over Cheng in view of Woo and Wu, and further in view of U.S. Patent Application Publication No. 2023/0013746 to Lancaster et al. (“Lancaster”) and U.S. Patent Application Publication No. 2025/0077882 to Vladislav Luzin (“Luzin”).
Regarding claim 2: The virtual metrology method based on the long sequence time-series prediction framework of claim 1,
wherein the manufacturing device comprises a production equipment (Cheng discloses monitoring production equipment in a semiconductor or TFT-LCD factory. Cheng at pars. [0005], [0015], and [0036].),
a factory equipment (Cheng discloses monitoring a workpiece (e.g., wafer) (“factory equipment”) in a semiconductor or TFT-LCD factory. Cheng at pars. [0005], [0015], and [0035].) and
each of the phase-one virtual metrology value generated in the first step and the phase-two virtual metrology value generated in the second step is configured to control the manufacturing device, thereby updating the actual measurement values of the power meter (Cheng discloses updating the actual measurement values (e.g., replacing or appending to measurement values) for workpieces (e.g., second workpieces) produced after the virtual metrology models are created. Cheng at par. [0035] and claim 1. Thus, Cheng discloses “updating the actual measurement values.”),
the sets of process data comprise production line information of the production equipment, factory information of the factory equipment, microgrid information of the microgrid equipment and environmental information (Cheng discloses collecting process data for production equipment (“production line information of the production equipment”) and workpieces (“factory information of the factory equipment”). Cheng at pars. [0015] and [0035]-[0036].), and
Cheng in view of Woo and Wu does not explicitly disclose that its system includes a “microgrid equipment” or a “power meter” or that the process data includes “microgrid information of the microgrid equipment and environmental information” and that the “power meter” values are updated.
a microgrid equipment (Lancaster discloses modules 12 that can include semiconductor fabrication and can use a microgrid (“microgrid equipment”) as an energy source. Lancaster at [0027]-[0028], [0030], and [0065]. Lancaster is analogous art because it reasonably pertinent to the problem faced by the inventor, which is to supply power (e.g., from a microgrid) to the production line. See MPEP 2141.01(a).I. It would have been obvious and one skilled in the art would have included microgrid equipment, as suggested by Lancaster, in the semiconductor fabrication system of Cheng in view of Woo and Wu in order to select power from the most economical energy source. Lancaster at pars. [0029]-[0030]. Because microgrids are known in the art as sources of power, there would have been a reasonable chance of success. See MPEP 2143.I.G.).
the measurement device comprises a power meter (Cheng in view of Woo, Wu, and Lancaster does not expressly disclose measuring power. However, in a same field of endeavor, measuring process variables in a semiconductor production environment (and thus analogous art), Luzin discloses measuring the source power (which will require a “power meter”) of a production machine as one of the process variables. Luzin at par. [0044]. It would have been obvious and one skilled in the art would have included the source power as part of the metrology data of Cheng in view of Woo, Wu, and Lancaster in order to “improv[e] the underlying process control systems within the fab.” Luzin at par. [0044]. Because the systems relate to measuring process variables, there would have been a reasonable chance of success. See MPEP 2143.I.G.).
the sets of process data comprise … microgrid information of the microgrid equipment and environmental information (Because the production machine of Luzon discussed above will be connected to the microgrid, the measured source power will correspond to “microgrid information of the microgrid equipment.” Luzin also discloses to measure the “chamber pressure” and “wall temperature” (“environmental information”) of the production machine. Luzin at par. [0044].).
Regarding claim 11: The virtual metrology system based on the long sequence time-series prediction framework of claim 10,
wherein the manufacturing device comprises a production equipment, a factory equipment and a microgrid equipment, the measurement device comprises a power meter, the sets of process data comprise production line information of the production equipment, factory information of the factory equipment, microgrid information of the microgrid equipment and environmental information, and each of the phase-one virtual metrology value generated in the first step and the phase-two virtual metrology value generated in the second step is configured to control the manufacturing device, thereby updating the actual measurement values of the power meter (Please see analysis in claim 2.).
Allowable Subject Matter
Claims 4 and 13 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
U.S. Patent Application No. 2024/0394522A1 to Ekambaram et al. discloses long sequence time-series forecasting.
U.S. Patent Application No. 2021/0056430 to Wu et al. discloses processing of time-series data to provide time-series models for forecasting.
Cheng, Fan-Tien, et al. "Industry 4.1 for wheel machining automation." IEEE Robotics and Automation Letters 1.1 (2016): 332-339. Cheng et al. discloses use of automatic virtual metrology to achieve zero defects in manufacturing.
Chen, Zonglei, et al. "Long sequence time-series forecasting with deep learning: A survey." Information Fusion 97 (2023): 101819. Chen et al. discloses different methods to provide long sequence tine-series forecasting with deep learning.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BHASKAR KAKARLA whose telephone number is (571)272-8221. The examiner can normally be reached Mon-Thurs.
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, Kenneth M. Lo can be reached at 571-272-9774. 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.
/B.K./Examiner, Art Unit 2116
/KENNETH M LO/ Supervisory Patent Examiner, Art Unit 2116
Prosecution Insights