CTNF 18/674,096 CTNF 92072 DETAILED ACTION Claims 1-20 are pending. Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. Specification 06-13 AIA The abstract of the disclosure is objected to because it does not describe the claimed invention . Correction is required. See MPEP § 608.01(b). Claim Rejections - 35 USC § 101 07-04-01 AIA 07-04 35 U.S.C. 101 reads as follows: Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title. Claim(s) 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a non-statutory subject matter. The claims do not fall within at least one of the four categories of patent eligible subject matter because the claimed invention is directed to the abstract idea (mental process) of data analysis. Claim 1 recites a method, i.e. a process, which is a statutory category of invention. The claim recites: determining a first plurality of data windows, wherein each of the first plurality of data windows comprises data points of the sensor trace data and is of the first window duration; determining a second plurality of data windows, wherein each of the second plurality of data windows comprises data points of the sensor trace data and is of the second window duration; determining a first plurality of statistical metric values, wherein each of the first plurality of statistical metric values is associated with data of one of the first plurality of data windows; determining a second plurality of statistical metric values, wherein each of the second plurality of statistical metric values is associated with data of one of the second plurality of data windows; determining whether the first plurality of statistical metric values satisfy a first plurality of threshold conditions; determining whether the second plurality of statistical metric values satisfy a second plurality of threshold conditions that may be performed in the human mind, or by a human using a pen and paper. Thus the claim recites an abstract idea (mental processes), see MPEP 2106.04(a) that indicates mental processes include concepts performed in the human mind including an observation, evaluation, judgment, and opinion. This judicial exception is not integrated into a practical application because the additional elements, i.e. obtaining sensor trace data and obtaining a first window duration and a second window duration (insignificant extra-solution elements – mere data gathering, see MPEP 2106.05 I A, MPEP 2106.05(g) MPEP 2106.05(d)), a semiconductor substrate processing operation performed in a process chamber (generally linking the use of the judicial exception to a particular technological environment or field of use, see MPEP 2106.05(h)) and performing a corrective action in view of the first and second pluralities of statistical metric values and first and second pluralities of threshold conditions (insignificant extra-solution activity — instructions to apply the exception using a technique recited at a high level of generality, see MPEP 2106.05(f)) does not impose any meaningful limits on practicing the abstract idea. The claim is therefore directed to an abstract idea. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, obtaining sensor trace data and obtaining a first window duration and a second window duration (insignificant extra-solution elements – mere data gathering, see MPEP 2106.05 I A, MPEP 2106.05(g) MPEP 2106.05(d)), a semiconductor substrate processing operation performed in a process chamber (generally linking the use of the judicial exception to a particular technological environment or field of use, see MPEP 2106.05(h)) and performing a corrective action in view of the first and second pluralities of statistical metric values and first and second pluralities of threshold conditions (insignificant extra-solution activity — instructions to apply the exception using a technique recited at a high level of generality, see MPEP 2106.05(f)) does not impose any meaningful limits on practicing the abstract idea and are not considered significantly more. Considering the additionally elements individually and in combination and the claim as a whole, the additional elements do not provide significantly more than the abstract idea. Thus the claim is not patent eligible. Note that semiconductor substrate processing operations performed in a process chamber are well-understood, routine and conventional, see for example Mui et al. U.S. Patent Publication No. 20040038139 [0033, 0049-0050, 00061], Lee et al. U.S. Patent Publication No. 20150063405 [0026], Anwar et al. U.S. Patent Publication No. 20160049917 [0019-0022], or Kim et al. U.S. Patent Publication No. 20230264350 and Funk et al. U.S. Patent Publication No. 20050187649 and the references cited below in the rejections under 35 U.S.C. § 103. And machine learning is well-understood, routine and conventional, see Brauer U.S. Patent Publication No. 20180075594 [0032] or Kagalwala et al. U.S. Patent No. 11300948 [claim 20]. Claim 2 recites the corrective action comprises one or more of: providing an alert to a user (insignificant extra-solution activity — see MPEP 2106.04(a)(2) III A regarding displaying information and MPEP 2106.05(d)); updating a processing recipe; updating an equipment constant; scheduling maintenance of manufacturing equipment; or updating one or more threshold conditions of the first or second plurality of threshold conditions (mental processes). Thus this claim recites an abstract idea. Claim 3 recites the first threshold condition of the first plurality of threshold conditions comprises an ideal operating range of a sensor corresponding to the sensor trace data. (specifying the abstract threshold conditions). Thus this claim recites an abstract idea. Claim 4 merely provides further detail specifying the abstract first threshold conditions. Thus this claim recites an abstract idea. Claim 5 merely specifies the abstract second threshold conditions. Thus this claim recites an abstract idea. Claim 6 recites the second window duration is larger than the first window duration, and wherein the second threshold condition is a lower value than the first threshold condition (relationships between abstract data). Thus this claim recites an abstract idea. Claim 7 merely indicates different types of abstract statistical metric. Thus this claim recites an abstract idea. Claim 8 recites performing the corrective action is responsive to a severity of threshold condition violations, wherein the severity comprises a number of threshold condition violations in connection with the first and second pluralities of threshold conditions, and one or more values by which threshold conditions of the first and second pluralities of threshold conditions are violated (insignificant extra-solution activity — instructions to apply the exception using a technique recited at a high level of generality, see MPEP 2106.05(f) — based on an abstract analysis). Thus this claim recites an abstract idea. Claim 9 recites obtaining process recipe data associated with the sensor trace data (insignificant extra-solution elements – mere data gathering, see MPEP 2106.05 I A, MPEP 2106.05(g) MPEP 2106.05(d)); and performing analysis on the process recipe data comprising comparing the process recipe data to one or more best known methods related to the process recipe data (mental process), wherein performance of the corrective action is further in view of the analysis on the process recipe data (insignificant extra-solution activity — instructions to apply the exception using a technique recited at a high level of generality, see MPEP 2106.05(f) — based on an abstract analysis). Thus this claim recites an abstract idea. Claim 10 recites obtaining a plurality of sensor trace data (insignificant extra-solution elements – mere data gathering, see MPEP 2106.05 I A, MPEP 2106.05(g) MPEP 2106.05(d)) corresponds to a plurality of semiconductor substrate processing operation performed in the process chamber (generally linking the use of the judicial exception to a particular technological environment or field of use, see MPEP 2106.05(h)); performing analysis on the plurality of sensor trace data comprising providing the plurality of sensor trace data to a trained machine learning model configured to detect one or more faults based on operational data (mental process performed with generic computer technology and a known algorithm – see MPEP 2106.04(a)(2) III C), wherein performance of the corrective action is further in view of output received from the trained machine learning model in connection with the plurality of sensor trace data (insignificant extra-solution activity — instructions to apply the exception using a technique recited at a high level of generality, see MPEP 2106.05(f) — based on an abstract analysis). Thus this claim recites an abstract idea. Claim 11 recites a non-transitory machine-readable storage medium storing instructions which, when executed, cause a processing device to perform operations, i.e. an article of manufacture, which is a statutory category of invention. However, the operations performed by the instructions are similar to those recited in claim 1 and are rejected under the same rationale. Note that a non-transitory machine-readable storage medium and processors are considered merely applying the exception with generic computer technology – see MPEP 2106.04(a)(2) III C — and not significantly more than the abstract idea. Claims 12 and 14-16 recite similar limitations to claims 2, 6, 8 and 9 and are rejected under the same respective rationales. Claim 13 recites similar limitations to claims 4 and 5 and is rejected under the same rationales as claims 4 and 5. Claim 17 recites a system, comprising memory and a processing device coupled to the memory, i.e. a machine, which is a statutory category of invention. However, the operations performed by the system are similar to those recited in claim 1 and are rejected under the same rationale. Note that memory and a processing device coupled to the memory are considered merely applying the exception with generic computer technology – see MPEP 2106.04(a)(2) III C — and not significantly more than the abstract idea. Claim 18 recites similar limitations to claims 4 and 5 and is rejected under the same rationales as claims 4 and 5. Claims 19 and 20 recite similar limitations to claims 6 and 9 and are rejected under the same respective rationales. Claim Rejections - 35 USC § 103 07-06 AIA 15-10-15 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. 07-20-aia AIA 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. 07-23-aia AIA 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. 07-21-aia AIA C laim(s) 1-2, 4-7, 11-14 and 17-19 is/are rejected under 35 U.S.C. 103 as being unpatentabl e over Miller et al. U.S. Patent No. 8606544 (hereinafter Miller ) in view of Thimmanaik et al. U.S. Patent Publication No. 20220066435 (hereinafter Thimmanaik) and further in view of Schulze et al. U.S. Patent Publication No. 20150369640 (hereinafter Schulze). Regarding claim 1, Miller teaches a method [col. 5 lines 55-60 — methods and systems are disclosed that may facilitate detecting abnormal operation in a process plant.]comprising: obtaining sensor trace data, wherein the sensor trace data corresponds to a processing operation [col. 11 lines 53-67, Fig. 2 — each of one or more of the field devices 64 and 66 may include a memory (not shown) for storing routines such as routines for implementing statistical data collection pertaining to one or more process variables sensed by sensing device and/or routines for abnormal operation detection, which will be described below; col. 8 lines 22-53 — process plant 10]; obtaining a first window duration and a second window duration; determining a first plurality of data windows, wherein each of the first plurality of data windows comprises data points of the sensor trace data and is of the first window duration [col. 28 line 48 – col. 29 line 6, Fig. 15 — FIG. 15 is a block diagram of another example abnormal operation detection (AOD) system 1100 that could be utilized in the abnormal operation detection blocks 80 and 82 of FIG. 2. The AOD system 1100 includes a first SPM block 1104 and a second SPM block 1108 coupled to a model 1112. The first SPM block 1104 receives a first process variable and generates first statistical data from the first process variable. The first statistical data could be any of various kinds of statistical data such as mean data, median data, standard deviation data, rate of change data, range data, etc., calculated from the first process variable. Such data could be calculated based on a sliding window of first process variable data or based on non-overlapping windows of first process variable data. As one example, the first SPM block 1104 may generate mean data using a most recent first process variable sample and 49 previous samples of the first process variable. In this example, a mean variable value may be generated for each new first process variable sample received by the first SPM block 1104. As another example, the first SPM block 1104 may generate mean data using non-overlapping time periods. In this example, a window of five minutes (or some other suitable time period) could be used, and a mean variable value would thus be generated every five minutes. In a similar manner, the second SPM block 1108 receives a second process variable and generates second statistical data from the second process variable in a manner similar to the SPM block 1104]; determining a second plurality of data windows, wherein each of the second plurality of data windows comprises data points of the sensor trace data and is of the second window duration [col. 28 line 48 – col. 29 line 6, Fig. 15 — FIG. 15 is a block diagram of another example abnormal operation detection (AOD) system 1100 that could be utilized in the abnormal operation detection blocks 80 and 82 of FIG. 2. The AOD system 1100 includes a first SPM block 1104 and a second SPM block 1108 coupled to a model 1112. The first SPM block 1104 receives a first process variable and generates first statistical data from the first process variable. The first statistical data could be any of various kinds of statistical data such as mean data, median data, standard deviation data, rate of change data, range data, etc., calculated from the first process variable. Such data could be calculated based on a sliding window of first process variable data or based on non-overlapping windows of first process variable data. As one example, the first SPM block 1104 may generate mean data using a most recent first process variable sample and 49 previous samples of the first process variable. In this example, a mean variable value may be generated for each new first process variable sample received by the first SPM block 1104. As another example, the first SPM block 1104 may generate mean data using non-overlapping time periods. In this example, a window of five minutes (or some other suitable time period) could be used, and a mean variable value would thus be generated every five minutes. In a similar manner, the second SPM block 1108 receives a second process variable and generates second statistical data from the second process variable in a manner similar to the SPM block 1104]; determining a first plurality of statistical metric values, wherein each of the first plurality of statistical metric values is associated with data of one of the first plurality of data windows; determining a second plurality of statistical metric values, wherein each of the second plurality of statistical metric values is associated with data of one of the second plurality of data windows [col. 28 line 48 – col. 29 line 6, Fig. 15 — The first SPM block 1104 receives a first process variable and generates first statistical data from the first process variable. The first statistical data could be any of various kinds of statistical data such as mean data, median data, standard deviation data, rate of change data, range data, etc., calculated from the first process variable. Such data could be calculated based on a sliding window of first process variable data or based on non-overlapping windows of first process variable data]; and performing a corrective action in view of the first and second pluralities of statistical metric values [col. 14 lines 50-62, Fig. 2 — the AOD system 100 may provide information to the abnormal situation prevention system 35 and/or other systems in the process plant. For example, deviation indicators generated by the deviation detector 116 could be provided to the abnormal situation prevention system 35 and/or the alert/alarm application 43 to notify an operator of the abnormal condition (corrective action, cf. instant claim 2)]. But Miller fails to clearly specify a semiconductor substrate processing operation performed in a process chamber and determining whether the first plurality of statistical metric values satisfy a plurality of threshold conditions; and performing a corrective action in view of pluralities of threshold conditions. However, Thimmanaik teaches determining whether the first plurality of statistical metric values satisfy a plurality of threshold conditions; and performing a corrective action in view of pluralities of threshold conditions [0083 — to avoid false positives, the inference results for a particular stream may be averaged (statistical metric) over a rolling time window, and an anomaly may only be detected if the average for the rolling window exceeds some threshold; 0089-0100 — the SPC method consists of a rolling or sliding window containing a few values of the scatter or standard deviation metric in FIG. 6A (e.g., 5-10 values). Moreover, for each position of the rolling window, the mean of the window is computed and then compared to the next value outside the window (e.g., for a window of size 10, the mean of the window is compared to the 11.sup.th value). If the next value (or series of values) outside the window exceeds the mean by a predetermined threshold—such as 1.5 to 2 times the mean—the value is considered to indicate an anomaly and an alert is raised (corrective action)]. Miller and Thimmanaik are analogous art. They relate to anomaly detection in industrial systems. Therefore at the time the invention was made, it would have been obvious to a person of ordinary skill in the art to modify the above method, as taught by Miller, by incorporating the above limitations, as taught by Thimmanaik. One of ordinary skill in the art would have been motivated to do this modification to avoid false positives, as suggested by Thimmanaik [0031, 0083, 0093]. But the combination of Miller and Thimmanaik fails to clearly specify a semiconductor substrate processing operation performed in a process chamber. However, Schulze teaches a semiconductor substrate processing operation performed in a process chamber [0003-0007, 0012 — the processing system(s) in which sensor monitoring is performed is a chamber used as part of a semiconductor manufacturing process. A plurality of virtual sensors are derived for each sensor, one for each recipe obtained by operation of the chamber. A system for implementing an automatic and non-disruptive sensor health monitoring scheme during execution of a recipe on a substrate within a processing chamber of a plasma processing system]. Miller, Thimmanaik and Schulze are analogous art. They relate to anomaly detection in industrial systems. Therefore at the time the invention was made, it would have been obvious to a person of ordinary skill in the art to simply substitute the semiconductor substrate processing operation/system of Schulze for the processing operation/system of Miller and Thimmanaik, for the predictable result of a method for a semiconductor substrate processing operation/system. Regarding claim 2, the combination of Miller, Thimmanaik and Schulze teaches all the limitations of the base claims as outlined above. Further, Miller teaches the corrective action comprises one or more of: providing an alert to a user [col. 14 lines 50-62, Fig. 2 — the AOD system 100 may provide information to the abnormal situation prevention system 35 and/or other systems in the process plant. For example, deviation indicators generated by the deviation detector 116 could be provided to the abnormal situation prevention system 35 and/or the alert/alarm application 43 to notify an operator of the abnormal condition]; updating a processing recipe; updating an equipment constant; scheduling maintenance of manufacturing equipment; or updating one or more threshold conditions of the first or second plurality of threshold conditions. Regarding claim 4, the combination of Miller, Thimmanaik and Schulze teaches all the limitations of the base claims as outlined above. Further, Miller teaches a first statistical metric in connection with the first window duration [col. 28 line 48 – col. 29 line 6, Fig. 15 — The first SPM block 1104 receives a first process variable and generates first statistical data from the first process variable. The first statistical data could be any of various kinds of statistical data such as mean data, median data, standard deviation data, rate of change data, range data, etc., calculated from the first process variable. Such data could be calculated based on a sliding window of first process variable data or based on non-overlapping windows of first process variable data]. Further, Thimmanaik teaches a first threshold condition of the first plurality of threshold conditions comprises an upper bound of a first value of a first statistical metric in connection with the first window duration [0083 — particular stream may be averaged over a rolling time window, and an anomaly may only be detected if the average for the rolling window exceeds some threshold… an anomaly may be detected if the average exceeds a threshold (e.g., 95% likelihood of an anomaly]. Therefore at the time the invention was made, it would have been obvious to a person of ordinary skill in the art to modify the above method, as taught by the combination of Miller, Thimmanaik and Schulze, by incorporating the above limitations, as taught by Thimmanaik. One of ordinary skill in the art would have been motivated to do this modification to avoid false positives, as suggested by Thimmanaik [0031, 0083, 0093]. Regarding claim 5, the combination of Miller, Thimmanaik and Schulze teaches all the limitations of the base claims as outlined above. Further, Miller teaches the first statistical metric in connection with the second window duration [col. 28 line 48 – col. 29 line 6, Fig. 15 — The first SPM block 1104 receives a first process variable and generates first statistical data from the first process variable. The first statistical data could be any of various kinds of statistical data such as mean data, median data, standard deviation data, rate of change data, range data, etc., calculated from the first process variable. Such data could be calculated based on a sliding window of first process variable data or based on non-overlapping windows of first process variable data]. Further, Thimmanaik teaches a threshold condition of the plurality of threshold conditions comprises an upper bound of a first value of a first statistical metric in connection with the window duration [0083 — particular stream may be averaged over a rolling time window, and an anomaly may only be detected if the average for the rolling window exceeds some threshold… an anomaly may be detected if the average exceeds a threshold (e.g., 95% likelihood of an anomaly]. Therefore at the time the invention was made, it would have been obvious to a person of ordinary skill in the art to modify the above method, as taught by the combination of Miller, Thimmanaik and Schulze, by incorporating the above limitations, as taught by Thimmanaik. One of ordinary skill in the art would have been motivated to do this modification to avoid false positives, as suggested by Thimmanaik [0031, 0083, 0093]. Regarding claim 6, the combination of Miller, Thimmanaik and Schulze teaches all the limitations of the base claims as outlined above. Further, Miller teaches second window duration and the first window duration [col. 28 line 48 – col. 29 line 6, Fig. 15 — FIG. 15 is a block diagram of another example abnormal operation detection (AOD) system 1100 that could be utilized in the abnormal operation detection blocks 80 and 82 of FIG. 2. The AOD system 1100 includes a first SPM block 1104 and a second SPM block 1108 coupled to a model 1112. The first SPM block 1104 receives a first process variable and generates first statistical data from the first process variable. The first statistical data could be any of various kinds of statistical data such as mean data, median data, standard deviation data, rate of change data, range data, etc., calculated from the first process variable. Such data could be calculated based on a sliding window of first process variable data or based on non-overlapping windows of first process variable data. As one example, the first SPM block 1104 may generate mean data using a most recent first process variable sample and 49 previous samples of the first process variable. In this example, a mean variable value may be generated for each new first process variable sample received by the first SPM block 1104. As another example, the first SPM block 1104 may generate mean data using non-overlapping time periods. In this example, a window of five minutes (or some other suitable time period) could be used, and a mean variable value would thus be generated every five minutes. In a similar manner, the second SPM block 1108 receives a second process variable and generates second statistical data from the second process variable in a manner similar to the SPM block 1104]. Further, Thimmanaik a threshold condition of the plurality of threshold conditions [0083 — particular stream may be averaged over a rolling time window, and an anomaly may only be detected if the average for the rolling window exceeds some threshold… an anomaly may be detected if the average exceeds a threshold (e.g., 95% likelihood of an anomaly]. Further, setting the second window duration is larger than the first window duration, and wherein the second threshold condition is a lower value than the first threshold condition would be obvious to one having ordinary skill in the art, see MPEP 2144.04 that states that relative dimensions are obvious. Regarding claim 7, the combination of Miller, Thimmanaik and Schulze teaches all the limitations of the base claims as outlined above. Further, Miller teaches a first statistical metric associated with the first plurality of statistical metric values comprises: a maximum value; a minimum value; an average value; a median value; a standard deviation; or a variance [col. 28 line 48 – col. 29 line 6, Fig. 15 — The first SPM block 1104 receives a first process variable and generates first statistical data from the first process variable. The first statistical data could be any of various kinds of statistical data such as mean data (average), median data, standard deviation data, rate of change data, range data, etc., calculated from the first process variable. Such data could be calculated based on a sliding window of first process variable data or based on non-overlapping windows of first process variable data]. Regarding claim 11, Miller teaches a non-transitory machine-readable storage medium storing instructions which, when executed, cause a processing device to perform operations [col. 43 lines 13-46 — systems and techniques described herein may be implemented in a standard multi-purpose processor or using specifically designed hardware or firmware as desired. When implemented in software, the software may be stored in any computer readable memory such as on a magnetic disk, a laser disk, or other storage medium, in a RAM or ROM or flash memory of a computer, processor, I/O device, field device, interface device, etc. Likewise, the software may be delivered to a user or a process control system via any known or desired delivery method including, for example, on a computer readable disk or other transportable computer storage mechanism or via communication media. Communication media typically embodies computer readable instructions]comprising: obtaining sensor trace data, wherein the sensor trace data corresponds to a processing operation [col. 11 lines 53-67, Fig. 2 — each of one or more of the field devices 64 and 66 may include a memory (not shown) for storing routines such as routines for implementing statistical data collection pertaining to one or more process variables sensed by sensing device and/or routines for abnormal operation detection, which will be described below; col. 8 lines 22-53 — process plant 10]; obtaining a first window duration and a second window duration; determining a first plurality of data windows, wherein each of the first plurality of data windows comprises data points of the sensor trace data and is of the first window duration [col. 28 line 48 – col. 29 line 6, Fig. 15 — FIG. 15 is a block diagram of another example abnormal operation detection (AOD) system 1100 that could be utilized in the abnormal operation detection blocks 80 and 82 of FIG. 2. The AOD system 1100 includes a first SPM block 1104 and a second SPM block 1108 coupled to a model 1112. The first SPM block 1104 receives a first process variable and generates first statistical data from the first process variable. The first statistical data could be any of various kinds of statistical data such as mean data, median data, standard deviation data, rate of change data, range data, etc., calculated from the first process variable. Such data could be calculated based on a sliding window of first process variable data or based on non-overlapping windows of first process variable data. As one example, the first SPM block 1104 may generate mean data using a most recent first process variable sample and 49 previous samples of the first process variable. In this example, a mean variable value may be generated for each new first process variable sample received by the first SPM block 1104. As another example, the first SPM block 1104 may generate mean data using non-overlapping time periods. In this example, a window of five minutes (or some other suitable time period) could be used, and a mean variable value would thus be generated every five minutes. In a similar manner, the second SPM block 1108 receives a second process variable and generates second statistical data from the second process variable in a manner similar to the SPM block 1104]; determining a second plurality of data windows, wherein each of the second plurality of data windows comprises data points of the sensor trace data and is of the second window duration [col. 28 line 48 – col. 29 line 6, Fig. 15 — FIG. 15 is a block diagram of another example abnormal operation detection (AOD) system 1100 that could be utilized in the abnormal operation detection blocks 80 and 82 of FIG. 2. The AOD system 1100 includes a first SPM block 1104 and a second SPM block 1108 coupled to a model 1112. The first SPM block 1104 receives a first process variable and generates first statistical data from the first process variable. The first statistical data could be any of various kinds of statistical data such as mean data, median data, standard deviation data, rate of change data, range data, etc., calculated from the first process variable. Such data could be calculated based on a sliding window of first process variable data or based on non-overlapping windows of first process variable data. As one example, the first SPM block 1104 may generate mean data using a most recent first process variable sample and 49 previous samples of the first process variable. In this example, a mean variable value may be generated for each new first process variable sample received by the first SPM block 1104. As another example, the first SPM block 1104 may generate mean data using non-overlapping time periods. In this example, a window of five minutes (or some other suitable time period) could be used, and a mean variable value would thus be generated every five minutes. In a similar manner, the second SPM block 1108 receives a second process variable and generates second statistical data from the second process variable in a manner similar to the SPM block 1104]; determining a first plurality of statistical metric values, wherein each of the first plurality of statistical metric values is associated with data of one of the first plurality of data windows; determining a second plurality of statistical metric values, wherein each of the second plurality of statistical metric values is associated with data of one of the second plurality of data windows [col. 28 line 48 – col. 29 line 6, Fig. 15 — The first SPM block 1104 receives a first process variable and generates first statistical data from the first process variable. The first statistical data could be any of various kinds of statistical data such as mean data, median data, standard deviation data, rate of change data, range data, etc., calculated from the first process variable. Such data could be calculated based on a sliding window of first process variable data or based on non-overlapping windows of first process variable data]; and performing a corrective action in view of the first and second pluralities of statistical metric values [col. 14 lines 50-62, Fig. 2 — the AOD system 100 may provide information to the abnormal situation prevention system 35 and/or other systems in the process plant. For example, deviation indicators generated by the deviation detector 116 could be provided to the abnormal situation prevention system 35 and/or the alert/alarm application 43 to notify an operator of the abnormal condition (corrective action, cf. instant claim 2)]. But Miller fails to clearly specify a semiconductor substrate processing operation performed in a process chamber and determining whether the first plurality of statistical metric values satisfy a plurality of threshold conditions; and performing a corrective action in view of pluralities of threshold conditions. However, Thimmanaik teaches determining whether the first plurality of statistical metric values satisfy a plurality of threshold conditions; and performing a corrective action in view of pluralities of threshold conditions [0083 — to avoid false positives, the inference results for a particular stream may be averaged (statistical metric) over a rolling time window, and an anomaly may only be detected if the average for the rolling window exceeds some threshold; 0089-0100 — the SPC method consists of a rolling or sliding window containing a few values of the scatter or standard deviation metric in FIG. 6A (e.g., 5-10 values). Moreover, for each position of the rolling window, the mean of the window is computed and then compared to the next value outside the window (e.g., for a window of size 10, the mean of the window is compared to the 11.sup.th value). If the next value (or series of values) outside the window exceeds the mean by a predetermined threshold—such as 1.5 to 2 times the mean—the value is considered to indicate an anomaly and an alert is raised (corrective action)]. Miller and Thimmanaik are analogous art. They relate to anomaly detection in industrial systems. Therefore at the time the invention was made, it would have been obvious to a person of ordinary skill in the art to modify the above machine-readable storage medium, as taught by Miller, by incorporating the above limitations, as taught by Thimmanaik. One of ordinary skill in the art would have been motivated to do this modification to avoid false positives, as suggested by Thimmanaik [0031, 0083, 0093]. But the combination of Miller and Thimmanaik fails to clearly specify a semiconductor substrate processing operation performed in a process chamber. However, Schulze teaches a semiconductor substrate processing operation performed in a process chamber [0003-0007, 0012 — the processing system(s) in which sensor monitoring is performed is a chamber used as part of a semiconductor manufacturing process. A plurality of virtual sensors are derived for each sensor, one for each recipe obtained by operation of the chamber. A system for implementing an automatic and non-disruptive sensor health monitoring scheme during execution of a recipe on a substrate within a processing chamber of a plasma processing system]. Miller, Thimmanaik and Schulze are analogous art. They relate to anomaly detection in industrial systems. Therefore at the time the invention was made, it would have been obvious to a person of ordinary skill in the art to simply substitute the semiconductor substrate processing operation/system of Schulze for the processing operation/system of Miller and Thimmanaik, for the predictable result of a machine-readable storage medium for a semiconductor substrate processing operation/system. Regarding claim 12, the combination of Miller, Thimmanaik and Schulze teaches all the limitations of the base claims as outlined above and this claim is otherwise rejected based on the same rationale as claim 2. Regarding claim 13, the combination of Miller, Thimmanaik and Schulze teaches all the limitations of the base claims as outlined above and this claim is otherwise rejected based on the same rationale as claims 4 and 5. Regarding claim 14, the combination of Miller, Thimmanaik and Schulze teaches all the limitations of the base claims as outlined above and this claim is otherwise rejected based on the same rationale as claim 6. Regarding claim 17, Miller teaches a system, comprising memory and a processing device coupled to the memory [col. 5 lines 55-60 — methods and systems are disclosed that may facilitate detecting abnormal operation in a process plant; col. 11 lines 45-67, Fig. 2 — maintenance workstation 74 includes a processor 74A, a memory 74B and a display device 74C. The memory 74B stores the abnormal situation prevention application 35 and the alert/alarm application 43 discussed with respect to FIG. 1 in a manner that these applications can be implemented on the processor 74A; col. 27, Fig. 13] , wherein the processing device is configured to: obtaining sensor trace data, wherein the sensor trace data corresponds to a processing operation [col. 11 lines 53-67, Fig. 2 — each of one or more of the field devices 64 and 66 may include a memory (not shown) for storing routines such as routines for implementing statistical data collection pertaining to one or more process variables sensed by sensing device and/or routines for abnormal operation detection, which will be described below; col. 8 lines 22-53 — process plant 10]; obtain a first window duration and a second window duration; determining a first plurality of data windows, wherein each of the first plurality of data windows comprises data points of the sensor trace data and is of the first window duration [col. 28 line 48 – col. 29 line 6, Fig. 15 — FIG. 15 is a block diagram of another example abnormal operation detection (AOD) system 1100 that could be utilized in the abnormal operation detection blocks 80 and 82 of FIG. 2. The AOD system 1100 includes a first SPM block 1104 and a second SPM block 1108 coupled to a model 1112. The first SPM block 1104 receives a first process variable and generates first statistical data from the first process variable. The first statistical data could be any of various kinds of statistical data such as mean data, median data, standard deviation data, rate of change data, range data, etc., calculated from the first process variable. Such data could be calculated based on a sliding window of first process variable data or based on non-overlapping windows of first process variable data. As one example, the first SPM block 1104 may generate mean data using a most recent first process variable sample and 49 previous samples of the first process variable. In this example, a mean variable value may be generated for each new first process variable sample received by the first SPM block 1104. As another example, the first SPM block 1104 may generate mean data using non-overlapping time periods. In this example, a window of five minutes (or some other suitable time period) could be used, and a mean variable value would thus be generated every five minutes. In a similar manner, the second SPM block 1108 receives a second process variable and generates second statistical data from the second process variable in a manner similar to the SPM block 1104]; determine a second plurality of data windows, wherein each of the second plurality of data windows comprises data points of the sensor trace data and is of the second window duration [col. 28 line 48 – col. 29 line 6, Fig. 15 — FIG. 15 is a block diagram of another example abnormal operation detection (AOD) system 1100 that could be utilized in the abnormal operation detection blocks 80 and 82 of FIG. 2. The AOD system 1100 includes a first SPM block 1104 and a second SPM block 1108 coupled to a model 1112. The first SPM block 1104 receives a first process variable and generates first statistical data from the first process variable. The first statistical data could be any of various kinds of statistical data such as mean data, median data, standard deviation data, rate of change data, range data, etc., calculated from the first process variable. Such data could be calculated based on a sliding window of first process variable data or based on non-overlapping windows of first process variable data. As one example, the first SPM block 1104 may generate mean data using a most recent first process variable sample and 49 previous samples of the first process variable. In this example, a mean variable value may be generated for each new first process variable sample received by the first SPM block 1104. As another example, the first SPM block 1104 may generate mean data using non-overlapping time periods. In this example, a window of five minutes (or some other suitable time period) could be used, and a mean variable value would thus be generated every five minutes. In a similar manner, the second SPM block 1108 receives a second process variable and generates second statistical data from the second process variable in a manner similar to the SPM block 1104]; determine a first plurality of statistical metric values, wherein each of the first plurality of statistical metric values is associated with data of one of the first plurality of data windows; determining a second plurality of statistical metric values, wherein each of the second plurality of statistical metric values is associated with data of one of the second plurality of data windows [col. 28 line 48 – col. 29 line 6, Fig. 15 — The first SPM block 1104 receives a first process variable and generates first statistical data from the first process variable. The first statistical data could be any of various kinds of statistical data such as mean data, median data, standard deviation data, rate of change data, range data, etc., calculated from the first process variable. Such data could be calculated based on a sliding window of first process variable data or based on non-overlapping windows of first process variable data]; and perform a corrective action in view of the first and second pluralities of statistical metric values [col. 14 lines 50-62, Fig. 2 — the AOD system 100 may provide information to the abnormal situation prevention system 35 and/or other systems in the process plant. For example, deviation indicators generated by the deviation detector 116 could be provided to the abnormal situation prevention system 35 and/or the alert/alarm application 43 to notify an operator of the abnormal condition (corrective action, cf. instant claim 2)]. But Miller fails to clearly specify a semiconductor substrate processing operation performed in a process chamber and determining whether the first plurality of statistical metric values satisfy a plurality of threshold conditions; and performing a corrective action in view of pluralities of threshold conditions. However, Thimmanaik teaches determining whether the first plurality of statistical metric values satisfy a plurality of threshold conditions; and performing a corrective action in view of pluralities of threshold conditions [0083 — to avoid false positives, the inference results for a particular stream may be averaged (statistical metric) over a rolling time window, and an anomaly may only be detected if the average for the rolling window exceeds some threshold; 0089-0100 — the SPC method consists of a rolling or sliding window containing a few values of the scatter or standard deviation metric in FIG. 6A (e.g., 5-10 values). Moreover, for each position of the rolling window, the mean of the window is computed and then compared to the next value outside the window (e.g., for a window of size 10, the mean of the window is compared to the 11.sup.th value). If the next value (or series of values) outside the window exceeds the mean by a predetermined threshold—such as 1.5 to 2 times the mean—the value is considered to indicate an anomaly and an alert is raised (corrective action)]. Miller and Thimmanaik are analogous art. They relate to anomaly detection in industrial systems. Therefore at the time the invention was made, it would have been obvious to a person of ordinary skill in the art to modify the above system, as taught by Miller, by incorporating the above limitations, as taught by Thimmanaik. One of ordinary skill in the art would have been motivated to do this modification to avoid false positives, as suggested by Thimmanaik [0031, 0083, 0093]. But the combination of Miller and Thimmanaik fails to clearly specify a semiconductor substrate processing operation performed in a process chamber. However, Schulze teaches a semiconductor substrate processing operation performed in a process chamber [0003-0007, 0012 — the processing system(s) in which sensor monitoring is performed is a chamber used as part of a semiconductor manufacturing process. A plurality of virtual sensors are derived for each sensor, one for each recipe obtained by operation of the chamber. A system for implementing an automatic and non-disruptive sensor health monitoring scheme during execution of a recipe on a substrate within a processing chamber of a plasma processing system]. Miller, Thimmanaik and Schulze are analogous art. They relate to anomaly detection in industrial systems. Therefore at the time the invention was made, it would have been obvious to a person of ordinary skill in the art to simply substitute the semiconductor substrate processing operation/system of Schulze for the processing operation/system of Miller and Thimmanaik, for the predictable result of a system for a semiconductor substrate processing operation/system. Regarding claim 18, the combination of Miller, Thimmanaik and Schulze teaches all the limitations of the base claims as outlined above and this claim is otherwise rejected based on the same rationale as claims 4 and 5. Regarding claim 19, the combination of Miller, Thimmanaik and Schulze teaches all the limitations of the base claims as outlined above and this claim is otherwise rejected based on the same rationale as claim 6 . 07-21-aia AIA C laim(s) 3 is/ are r ejected under 35 U.S.C. 103 as being unpatentable over the comb ination of Miller, Thimmanaik and Schulze in view of Rud U.S. Patent No. 6047244 (hereinafter Rud). Regardi ng claim 3, the combination of Miller, Thimmanaik and Schulze teaches all the limitations of the base claims as outlined above. Further, Miller teaches a first threshold condition of the first plurality of threshold conditions and a sensor corresponding to the sensor trace data [col. 19 lines 27-67, Fig. 8 — threshold system 260 may comprise a threshold generator 264; col. 11 lines 53-67, Fig. 2 — each of one or more of the field devices 64 and 66 may include a memory (not shown) for storing routines such as routines for implementing statistical data collection pertaining to one or more process variables sensed by sensing device and/or routines for abnormal operation detection, which will be described below; col. 6 lines 5-19]. Further, Thimmanaik teaches a first threshold condition of the first plurality of threshold conditions [0083 — to avoid false positives, the inference results for a particular stream may be averaged (statistical metric) over a rolling time window, and an anomaly may only be detected if the average for the rolling window exceeds some threshold; 0089-0100 — the SPC method consists of a rolling or sliding window containing a few values of the scatter or standard deviation metric in FIG. 6A (e.g., 5-10 values). Moreover, for each position of the rolling window, the mean of the window is computed and then compared to the next value outside the window (e.g., for a window of size 10, the mean of the window is compared to the 11.sup.th value). If the next value (or series of values) outside the window exceeds the mean by a predetermined threshold—such as 1.5 to 2 times the mean—the value is considered to indicate an anomaly and an alert is raised (corrective action)]. But the combination of Miller, Thimmanaik and Schulze fails to clearly specify an ideal operating range of a sensor. However, Rud teaches an ideal operating range of a sensor corresponding to the sensor trace data [col. 4 lines 1-28, Fig. 2 — Sensor 14 is calibrated to provide an output which can be relied upon in the range from a lower transition limit x.sub.1 to URL.sub.2. Therefore, it is desirable to use sensor 14, at least to some degree, over that level of input pressure. Similarly, since sensor 12 is calibrated to provide an output which is more accurate than sensor 14 in a region LRL.sub.1 to URL.sub.1, it is desirable to use the output from sensor 12, at least to some degree, over that entire range of input pressures]. Miller, Thimmanaik, Schulze and Rud are analogous art. They relate to anomaly detection and/or process control in industrial systems. Therefore at the time the invention was made, it would have been obvious to a person of ordinary skill in the art to modify the above method, as taught by the combination of Miller, Thimmanaik and Schulze, by incorporating the above limitations, as taught by Rud. One of ordinary skill in the art would have been motivated to do this modification in order to ensure that sensor data can be relied upon, as suggested by Rud [col. 4 lines 1-28] and to obtain the most accurate sensor data . 07-21-aia AIA C laim( s) 8 and 15 i s/are rejected under 35 U.S.C. 103 as being unpatentable over t he combination of Miller, Thimmanaik and Schulze in view of Fujikata et al. U.S. Patent Publication No. 20180294174 (hereinafter Fujikata). R egarding claim 8, the combination of Miller, Thimmanaik and Schulze teaches all the limitations of the base claims as outlined above. But the combination of Miller, Thimmanaik and Schulze fails to clearly specify performing the corrective action is responsive to a severity of threshold condition violations, wherein the severity comprises a number of threshold condition violations in connection with the first and second pluralities of threshold conditions, and one or more values by which threshold conditions of the first and second pluralities of threshold conditions are violated. However, Fujikata teaches performing the corrective action is responsive to a severity of threshold condition violations, wherein the severity comprises a number of threshold condition violations in connection with the first and second pluralities of threshold conditions, and one or more values by which threshold conditions of the first and second pluralities of threshold conditions are violated [0011, 0177, 0180 — a failure prediction method for a semiconductor manufacturing apparatus is provided. This failure prediction method includes: monitoring a temporal change in one or more feature quantities of a first device included in the semiconductor manufacturing apparatus; and stopping reception of a new substrate when a duration for which a degree of deviation of the one or more feature quantities from those (one or more feature quantities) at the normal time exceeds a first time, and/or when a number of increases and decreases per unit time in the degree of deviation of the one or more feature quantities from those at the normal time exceeds a first number]. Miller, Thimmanaik, Schulze and Fujikata are analogous art. They relate to anomaly detection and/or process control in industrial systems. Therefore at the time the invention was made, it would have been obvious to a person of ordinary skill in the art to modify the above method, as taught by the combination of Miller, Thimmanaik and Schulze, by incorporating the above limitations, as taught by Fujikata. One of ordinary skill in the art would have been motivated to do this modification in order to only perform a corrective action when it is necessary and not when there is only a minor or infrequent fault, as suggested by Fujikata [0011, 0177, 0180] thus improving efficiency by reducing the number of process interruptions. Regarding claim 15, the combination of Miller, Thimmanaik and Schulze teaches all the limitations of the base claims as outlined above and this claim is otherwise rejected based on the same rationale as claim 8 . 07-21-aia AIA C laim(s) 9, 16 and 20 is/a re rejected under 35 U.S.C. 103 as being unpatentable over the c ombination of Miller, Thimmanaik and Schulze in view of Ahmed et al. U.S. Patent Publication No. 20070192056 (hereinafter Ahmed). Rega rding claim 9, the combination of Miller, Thimmanaik and Schulze teaches all the limitations of the base claims as outlined above. Further, Miller teaches performance of the corrective action is further in view of the analysis and the sensor trace data [col. 14 lines 50-62, Fig. 2 — the AOD system 100 may provide information to the abnormal situation prevention system 35 and/or other systems in the process plant. For example, deviation indicators generated by the deviation detector 116 could be provided to the abnormal situation prevention system 35 and/or the alert/alarm application 43 to notify an operator of the abnormal condition (corrective action, cf. instant claim 2; col. 11 lines 53-67, Fig. 2 — each of one or more of the field devices 64 and 66 may include a memory (not shown) for storing routines such as routines for implementing statistical data collection pertaining to one or more process variables sensed by sensing device and/or routines for abnormal operation detection, which will be described below)]. But the combination of Miller, Thimmanaik and Schulze fails to clearly specify obtaining process recipe data; and performing analysis on the process recipe data comprising comparing the process recipe data to one or more best known methods related to the process recipe data, wherein performance of the corrective action is further in view of the analysis on the process recipe data. However, Ahmed teaches obtaining process recipe data associated with the sensor trace data; and performing analysis on the process recipe data comprising comparing the process recipe data to one or more best known methods related to the process recipe data, wherein performance of the corrective action is further in view of the analysis on the process recipe data [0031, Fig. 1 — The metrology tool system used to measure desired dimensions in microelectronic features may comprise a single metrology tool or a plurality of metrology tools connected by a network; 0041-0042, Figs. 2-3 — The preferred method and system of preparing recipes for operating a metrology tool used to measure desired dimensions in microelectronic features (sensor data)… The recipe verification program may automatically receive the summary or may manually be instructed to retrieve 58 the summary file for the desired recipe. The recipe attributes trigger the program 30 to select the proper BKM 60 from the categorized BKM database and compare the recipe and BKM and display 64 the parameters, critical parameters, mismatches or other parameter subset… After comparison 66, if the recipe is incorrect the corrections 56 are made by the recipe writer on the tool/recipe system 52 or automatically sent to tool/recipe system 54 and applied]. Miller, Thimmanaik, Schulze and Ahmed are analogous art. They relate to anomaly detection and/or process control in industrial systems. Therefore at the time the invention was made, it would have been obvious to a person of ordinary skill in the art to modify the above method, as taught by the combination of Miller, Thimmanaik and Schulze, by incorporating the above limitations, as taught by Ahmed. One of ordinary skill in the art would have been motivated to do this modification to facilitate recipes that are verified and run well and maintain consistency among recipes/measurements, as suggested by Ahmed [0010-0011]. Regarding claim 16, the combination of Miller, Thimmanaik and Schulze teaches all the limitations of the base claims as outlined above and this claim is otherwise rejected based on the same rationale as claim 9. Regarding claim 20, the combination of Miller, Thimmanaik and Schulze teaches all the limitations of the base claims as outlined above and this claim is otherwise rejected based on the same rationale as claim 9 . 07-21-aia AIA C laim(s) 10 is/a re rej ected under 35 U.S.C. 103 as being unpatentable over the combin ation of Miller, Thimmanaik and Schulze in view of Clark et al. U.S. Patent Publication No. 20200006100 (hereinafter Clark). Regarding claim 10, the combination of Miller, Thimmanaik and Schulze teaches all the limitations of the base claims as outlined above. Further, Miller teaches obtaining a plurality of sensor trace data corresponding to a plurality of processing operations [col. 11 lines 53-67, Fig. 2 — each of one or more of the field devices 64 and 66 may include a memory (not shown) for storing routines such as routines for implementing statistical data collection pertaining to one or more process variables sensed by sensing device and/or routines for abnormal operation detection, which will be described below; col. 6 lines 5-19; col. 8 lines 22-53 — process plant 10]. Further, Schulze teaches a semiconductor substrate processing operation performed in a process chamber [0003-0007, 0012 — the processing system(s) in which sensor monitoring is performed is a chamber used as part of a semiconductor manufacturing process. A plurality of virtual sensors are derived for each sensor, one for each recipe obtained by operation of the chamber. A system for implementing an automatic and non-disruptive sensor health monitoring scheme during execution of a recipe on a substrate within a processing chamber of a plasma processing system]. But the combination of Miller, Thimmanaik and Schulze fails to clearly specify performing analysis on the plurality of sensor trace data comprising providing the plurality of sensor trace data to a trained machine learning model configured to detect one or more faults based on operational data, wherein performance of the corrective action is further in view of output received from the trained machine learning model in connection with the plurality of sensor trace data. However, Clarke teaches performing analysis on the plurality of sensor trace data comprising providing the plurality of sensor trace data to a trained machine learning model configured to detect one or more faults based on operational data [0378, Figs. 21 and 26 — an example embodiment 2600 of a self-optimization component in an autonomous biologically based learning system… . As indicated above, self-optimization component functionality is to analyze the current health (e.g., performance) of a manufacturing platform/tool system 1910 and then determine if non-conformities are detected and, based on the results of the current health analysis, diagnose or rank substantially all potential causes for health deterioration of the tool system 1910 and the cause of such non-conformities, and identify a root cause of non-conformities based on learning acquired by autonomous learning system 1960 in order to provide the necessary control of the manufacturing platform to provide corrective processing.; 0391-0397, Fig. 28 — The group of autonomous tools systems 2820 .sub.1- 2820 .sub.K can be controlled by an autonomous biologically based learning tool 1960 which receives (input) and conveys (output) information 1958 to an interface 1930 that facilitates an actor 1990 to interact with the group of autonomous tools system… the autonomous system 1960 can also construct a predictive model of group time-to-failure as a function of assets 1928 of tool group or platform 2800 ; e.g., group input data, group outputs, group recipes, or group maintenance activities. In an aspect, to determine a group time-to-failure, autonomous learning system 1960 can gather failure data, including time between detected (e.g., through a set of sensor components or inspection systems) failures, associated assets 2850 .sub.1- 2850 .sub.K, outputs 2801 - 2860 K, and maintenance activities for substantially all operation tools in the set of tools 2801 - 2820 K (operational and historical data). (It should be appreciated that as a consequence of prior failure assessments, specific tools (e.g., tool system 2 2820 .sub.1 and tool system K 2820 .sub.K) in the set of tools (e.g., tools 2820 .sub.1- 2820 .sub.K) in group 2800 can be out of operation.) Collected data can be autonomously analyzed (e.g., through a processing component 1985 in autonomous learning system 1960 ) to learn a predictive function for time-to-failure as a function of the group assets (e.g., inputs, recipes, . . . ), outputs, and maintenance activities… when a group performance appears degraded, individual performances associated with individual tools can be analyzed; 0116-0125, Fig. 4 — system of platform 400 … substrate processing chambers 420 a - 420 d (individual tools/chambers); 0324, Fig. 20 — a deposition chamber in tool system 1910 ], wherein performance of the corrective action is further in view of output received from the trained machine learning model in connection with the plurality of sensor trace data [0356 — Based on the level of degradation, autonomous learning system 1960 can analyze available data assets 1928 as well as information 1958 to rank the possible faults. In an aspect, in response to an excessive level of non-conformities the autonomous learning system can provide control for corrective processing through the platform. In case of a successful corrective processing as confirmed, for example, by further measurement/metrology and associated data (e.g., data assets and patterns, relationships, and substantially any other type of understanding extracted from such combination) that preceded the corrective processing activities can be retained by autonomous learning system 1960 ; 0382 — The combination of analytic and predictive techniques can be exploited to facilitate optimization of tool system 1910 via identification of ailing trends in specific assets, or properties, as probed by sensor component 1925 , as well as information available in OKM 2610 , with suitable corrective measures generated by optimization planner component 2650 , and optimization autobots that can reside in component 2140 ]. Miller, Thimmanaik, Schulze and Clarke are analogous art. They relate to anomaly detection and/or process control in industrial systems. Therefore at the time the invention was made, it would have been obvious to a person of ordinary skill in the art to modify the above method, as taught by the combination of Miller, Thimmanaik and Schulze, by incorporating the above limitations, as taught by Clarke. One of ordinary skill in the art would have been motivated to do this modification in order to autonomously detect and correct faults using machine learning, as taught by Clarke [0077, 0109, 0126, 0214, 0223] thus automating the fault detection process. Citation of Pertinent Prior Art 07-96 AIA The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Li et al. U.S. Patent Publication No. 20190198405 that discloses a system and method for detecting mismatches among manufacturing tools using sliding time windows. Note that any citations to specific, pages, columns, lines, or figures in the prior art references and any interpretation of the reference should not be considered to be limiting in any way. A reference is relevant for all it contains and may be relied upon for all that it would have reasonably suggested to one having ordinary skill in the art. See MPEP 2123 . Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to BERNARD G. LINDSAY whose telephone number is (571)270-0665. The examiner can normally be reached Monday through Friday from 8:30 AM to 5:30 PM EST. 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. Status information for published applications may be obtained from Patent Center. Status information for unpublished applications is available through Patent Center for authorized users only. Should you have questions about access to Patent Center, 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 may call the examiner or use the USPTO Automated Interview Request (AIR) Form at https://www.uspto.gov/patents/uspto-automated- interview-request-air-form. /BERNARD G LINDSAY/ Primary Examiner, Art Unit 2119 Application/Control Number: 18/674,096 Page 2 Art Unit: 2119 Application/Control Number: 18/674,096 Page 3 Art Unit: 2119 Application/Control Number: 18/674,096 Page 4 Art Unit: 2119 Application/Control Number: 18/674,096 Page 5 Art Unit: 2119 Application/Control Number: 18/674,096 Page 6 Art Unit: 2119 Application/Control Number: 18/674,096 Page 7 Art Unit: 2119 Application/Control Number: 18/674,096 Page 8 Art Unit: 2119 Application/Control Number: 18/674,096 Page 9 Art Unit: 2119 Application/Control Number: 18/674,096 Page 10 Art Unit: 2119 Application/Control Number: 18/674,096 Page 11 Art Unit: 2119 Application/Control Number: 18/674,096 Page 12 Art Unit: 2119 Application/Control Number: 18/674,096 Page 13 Art Unit: 2119 Application/Control Number: 18/674,096 Page 14 Art Unit: 2119 Application/Control Number: 18/674,096 Page 15 Art Unit: 2119 Application/Control Number: 18/674,096 Page 16 Art Unit: 2119 Application/Control Number: 18/674,096 Page 17 Art Unit: 2119 Application/Control Number: 18/674,096 Page 18 Art Unit: 2119 Application/Control Number: 18/674,096 Page 19 Art Unit: 2119 Application/Control Number: 18/674,096 Page 20 Art Unit: 2119 Application/Control Number: 18/674,096 Page 21 Art Unit: 2119 Application/Control Number: 18/674,096 Page 22 Art Unit: 2119 Application/Control Number: 18/674,096 Page 23 Art Unit: 2119 Application/Control Number: 18/674,096 Page 24 Art Unit: 2119 Application/Control Number: 18/674,096 Page 25 Art Unit: 2119 Application/Control Number: 18/674,096 Page 26 Art Unit: 2119 Application/Control Number: 18/674,096 Page 27 Art Unit: 2119 Application/Control Number: 18/674,096 Page 28 Art Unit: 2119 Application/Control Number: 18/674,096 Page 29 Art Unit: 2119 Application/Control Number: 18/674,096 Page 30 Art Unit: 2119 Application/Control Number: 18/674,096 Page 31 Art Unit: 2119 Application/Control Number: 18/674,096 Page 32 Art Unit: 2119 Application/Control Number: 18/674,096 Page 33 Art Unit: 2119 Application/Control Number: 18/674,096 Page 34 Art Unit: 2119 Application/Control Number: 18/674,096 Page 35 Art Unit: 2119 Application/Control Number: 18/674,096 Page 36 Art Unit: 2119 Application/Control Number: 18/674,096 Page 37 Art Unit: 2119 Application/Control Number: 18/674,096 Page 38 Art Unit: 2119 Application/Control Number: 18/674,096 Page 39 Art Unit: 2119
Prosecution Insights