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 .
Response to Amendment
Applicant has submitted amendments to the claims 03/10/2026.
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.
Claim(s) 1-11 and 14-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhao et al (US PUB. 20180348717, herein Zhao) in view of Masampally et al (US PUB. 20230195853, herein Masampally) in further view of Moon et al (WO 2023090510, herein Moon).
Regarding claim 1, Zhao teaches A system comprising:
a processor (0010) to:
receive unconditioned data comprising a set of process variables, wherein the set of process variables is indicative of one or more characteristics associated with a process (0011 “To initialize the inferential model, the computer systems, methods, and program products: (i) selects process variables for the subject industrial process, and (ii) configures one of the selected process variables as an output process variable that represents output of the inferential model”);
supplement the unconditioned data with an auxiliary set of process variables to obtain modified unconditioned data, the auxiliary set at least comprising a process variable missing in the unconditioned data (0006 “the systems and methods optionally select an important measurable process variable (referred to as a “reference variable”). The data measurements for the selected reference variable are used to train the dynamic predictive inferential model”, 0045 “the systems and methods may apply a unique reference variable approach with subspace identification and PLS techniques to build and train the predictive inferential model”), [wherein the modified unconditioned data comprises the auxiliary set of process variables in place of the missing process variable]
identify a conditioned set of process variables from within the modified unconditioned data, wherein the conditioned set of process variables is capable of empirically representing the one or more characteristics associated with the process (0045 “the systems and methods build and train the predictive inferential models using historical data of the plant process, which may be automatically screened, sliced, and data selection techniques applied to remove bad segments from the data”)
provide the conditioned set of process variables to a [plurality] of inferential modellers (0002 “Inferential models or soft-sensors have been widely used in petroleum and chemical industries for process control and operation optimization”, 0088 “method 246 builds the predictive inferential model using the lab data in two major step”, 0094).
The cited prior art do not teach plurality of inferential modellers, wherein each of the inferential modellers is to configure one or more soft sensors based on the conditioned set of process variables and select a soft sensor, from among the one or more soft sensors, for being deployed to predict runtime conformance metric for the process, the runtime conformance metric being associated with an outcome of the process.
Masampally teaches provide the conditioned set of process variables to a plurality of inferential modellers, wherein each of the inferential modellers is to configure one or more soft sensors based on the conditioned set of process variables (0031 “model building unit 118 is configured to creating a plurality of soft-sensors for the desired blend property as shown in the block diagram of FIG. 4. A data integrator 134 is used to integrate the data according to the requirement for data preprocessing techniques. The extracted relevant data needs to be preprocessed before using this data as an input to the model building unit” 0029 “The data extractor unit 116 extracts data from these data sources and provides inputs to the model building unit 118, the model selection unit 122 and the model retuning unit 124. The model building unit 118 is used to create soft-sensors for various properties of interest in the blend as explained in FIG. 4. The model retuning unit 124 retunes the soft-sensors with the addition data as explained using FIG. 9.”)
and select a soft sensor, from among the one or more soft sensors, for being deployed to predict runtime conformance metric for the process, the runtime conformance metric being associated with an outcome of the process (0029 “The model selection unit 122 is used to identify the best or most accurate soft-sensor available in a model database 130. The selection of soft-sensor is based on but not limited to a root mean squared error, mean absolute error, mean absolute percentage error, etc. The model selection unit 122 selects the accurate soft-sensor and passes this information to blending rules optimizer unit 120 that obtains the best mixing rule for each feature of the soft-sensor that is used for predicting the property of a mixture or a blend. The model selection unit 122 selects the accurate soft-sensor and this soft-sensor is used for predicting the property of blend in real-time using the model prediction unit 126.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the instant application to have modified the soft sensor teachings of Zhao with the selection of soft sensor teachings of Masampally since Masampally teaches a means for identifying the best or most accurate soft-sensor and then obtains the best mixing rule for each feature of the soft-sensor that is used for predicting the property of a mixture or blend (0029).
The cited prior art do not teach supplement the unconditioned data with an auxiliary set of process variables to obtain modified unconditioned data, the auxiliary set at least comprising a process variable missing in the unconditioned data wherein the modified unconditioned data comprises the auxiliary set of process variables in place of the missing process variable.
Moon teaches supplement the unconditioned data with an auxiliary set of process variables to obtain modified unconditioned data, the auxiliary set at least comprising a process variable missing in the unconditioned data wherein the modified unconditioned data comprises the auxiliary set of process variables in place of the missing process variable (page 10 paragraph 10, “the processor 150 may identify at least one missing data processing method to process the missing data corresponding to at least one section based on the missing data information. The processor 150 may complement the missing data by considering parameter information for adjusting the processing degree of the missing data according to information on the missing data. Parameter information according to the present embodiment may include information on a section including missing data, information on a method for processing missing data, conditions for processing missing data, and the like”, 12:9 “the processor 150 processes a plurality of collected data, respectively, obtains a plurality of processed data, combines the plurality of processed data, processes abnormal data among the combined data, and processes the processed data among the combined data. Information on missing data including abnormal data may be identified, and the missing data may be processed using at least one missing data processing method based on the information on the missing data. The processor 150 may process the missing data and integrate the data ( 1030 )”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the instant application to have modified the teachings of Zhao, and Masampally with the teachings of Moon since Moon teaches a means for processing of missing data in order for better results from data utilization technology (page 2).
Regarding claim 2, the cited prior art teach The system of claim 1.
The cited prior art teach wherein the processor (Zhao 0010) is to:
compute a correlation score for one or more process variables present in the modified unconditioned data, the correlation score being computed by statistical analysis of relationships between each of the one or more process variables (Zhao 0083 “there are often continuously measured process variables available that are natively highly correlated with the selected output process variable (product properties) 317 contained in the lab data. For example, a temperature at top of a distillation column can be highly correlated with the product purity from the top of the column. For another example, a pressure-compensated-temperature (PCT) process variable at the top of a distillation column can be highly correlated with product quality, and is often used for quality control as a substitute of quality measurements at the column”);
compare the correlation score of each the one or more process variables with a threshold correlation score (Zhao 0083 “For example, a temperature at top of a distillation column can be highly correlated with the product purity from the top of the column. For another example, a pressure-compensated-temperature (PCT) process variable at the top of a distillation column can be highly correlated with product quality”) to identify one or more uncorrelated process variables present in the modified unconditioned data (Masampally 0032 “Pairwise linearly correlated descriptors are identified by the Pearson correlation coefficient. When the absolute value of the correlation coefficient for two descriptors is greater than or equal to a 0.9, then the two descriptors are matched as a pair, and the one that is highly correlated to all the other descriptors is deleted”);
and based on the comparison, select the one or more uncorrelated process variables, from the modified unconditioned data, to form the conditioned set of process variables (Masampally 0032 “Pairwise linearly correlated descriptors are identified by the Pearson correlation coefficient. When the absolute value of the correlation coefficient for two descriptors is greater than or equal to a 0.9, then the two descriptors are matched as a pair, and the one that is highly correlated to all the other descriptors is deleted”).
Regarding claim 3, the cited prior art teach The system of claim 2.
Masampally teaches wherein the processor is to:
ascertain presence of at least one outlier process variable within the set of process variables, wherein the at least one outlier process variable is anomalous from other one or more process variables present in the set of process variables, and wherein the anomaly is ascertained by statistically analysing each of the process variables present in the set of process variables (0032 “As part of preprocessing, all the descriptors with at least one missing value are ignored for further analysis. 180 such descriptors are removed to obtain a data with 516 descriptors. Descriptors with constant value or a standard deviation of zero are removed to obtain the data with 255 descriptors. Pairwise linearly correlated descriptors are identified by the Pearson correlation coefficient. When the absolute value of the correlation coefficient for two descriptors is greater than or equal to a 0.9, then the two descriptors are matched as a pair, and the one that is highly correlated to all the other descriptors is deleted.”);
and supplement the unconditioned data with the auxiliary set of process variables, in response to the ascertaining the presence of the anomaly (0032 “Data with of 68 descriptors is left for further analysis”).
Regarding claim 4, the cited prior art teach The system of claim 1.
Masampally teaches wherein the one or more soft sensors is to represent a relationship between the set of process variables and the runtime conformance metric (0029 “The model selection unit 122 is used to identify the best or most accurate soft-sensor available in a model database 130. The selection of soft-sensor is based on but not limited to a root mean squared error, mean absolute error, mean absolute percentage error, etc. The model selection unit 122 selects the accurate soft-sensor and passes this information to blending rules optimizer unit 120 that obtains the best mixing rule for each feature of the soft-sensor that is used for predicting the property of a mixture or a blend. The model selection unit 122 selects the accurate soft-sensor and this soft-sensor is used for predicting the property of blend in real-time using the model prediction unit 126.”).
Regarding claim 5, the cited prior art teach The system of claim 4.
Masampally teaches wherein the plurality of inferential modellers configure each of the one or more soft sensors based on a historical conformance metric, the historical conformance metric corresponding to the runtime conformance metric (0033 “the soft-sensor is built for predicting the desired property using 15 descriptors and the results are as demonstrated in graphical representation of FIG. 6A and 6B. FIG. 6A and 6B shows comparison of soft-sensor predictions with actual data and the density plot of corresponding errors for pure component data. These soft-sensors are considered as soft-sensors for predicting the desired property of the components used in blending process. A soft-sensor is then selected from amongst the plurality of soft-sensors for the desired property of the plurality of components used for blending based on accuracy of the soft-sensors”).
Regarding claim 6, the cited prior art teach The system of claim 5.
Masampally teaches wherein the processor is to:compare a test conformance metric, predicted by each of the soft sensors based on the conditioned set of process variable, with the historical conformance metric to validate the one or more soft sensors, wherein the historical conformance metric is associated with one or more past observed outcomes of the process; and based on the comparison, select the soft sensor, from among the one or more soft sensors (0033 “the soft-sensor is built for predicting the desired property using 15 descriptors and the results are as demonstrated in graphical representation of FIG. 6A and 6B. FIG. 6A and 6B shows comparison of soft-sensor predictions with actual data and the density plot of corresponding errors for pure component data. These soft-sensors are considered as soft-sensors for predicting the desired property of the components used in blending process. A soft-sensor is then selected from amongst the plurality of soft-sensors for the desired property of the plurality of components used for blending based on accuracy of the soft-sensors”).
Regarding claim 7, Zhao teaches A method comprising:
receiving unconditioned data comprising one or more process variables, each indicating at least one characteristic associated with an industrial process (0011 “To initialize the inferential model, the computer systems, methods, and program products: (i) selects process variables for the subject industrial process, and (ii) configures one of the selected process variables as an output process variable that represents output of the inferential model”);
computing a correlation score for each of the one or more process variables and the one or more auxiliary process variables, present in the modified unconditioned data, to determine a conditioned set of process variables, wherein the conditioned set of process variables is capable of representing the at least one characteristic associated with the industrial process (0083 “Such a set of intermittently sampled lab data is not sufficient to build a dynamic (predictive) inferential model. In practice, however, there are often continuously measured process variables available that are natively highly correlated with the selected output process variable (product properties) 317 contained in the lab data. For example, a temperature at top of a distillation column can be highly correlated with the product purity from the top of the column. For another example, a pressure-compensated-temperature (PCT) process variable at the top of a distillation column can be highly correlated with product quality, and is often used for quality control as a substitute of quality measurements at the column”);
providing the conditioned set of process variables to a [plurality] of inferential modellers (0002 “Inferential models or soft-sensors have been widely used in petroleum and chemical industries for process control and operation optimization”, 0088 “method 246 builds the predictive inferential model using the lab data in two major step”, 0094).
The cited prior art do not teach determining to impute one or more process variables, from among the one or more process variables present in the unconditioned data, with one or more auxiliary process variables to obtain modified unconditioned data wherein the modified unconditioned data comprises the one or more auxiliary process variables in place of missing one or more process variables in the unconditioned data, plurality of inferential modellers wherein each of the inferential modellers is to condition one or more soft sensors based on the conditioned set of process variables; and selecting a soft sensor, from among the one or more soft sensors, for predicting runtime conformance metric for the process, the runtime conformance metric being associated with an outcome of the industrial process.
Masampally teaches providing the conditioned set of process variables to a [plurality] of inferential modellers wherein each of the inferential modellers is to condition one or more soft sensors based on the conditioned set of process variables (0031 “model building unit 118 is configured to creating a plurality of soft-sensors for the desired blend property as shown in the block diagram of FIG. 4. A data integrator 134 is used to integrate the data according to the requirement for data preprocessing techniques. The extracted relevant data needs to be preprocessed before using this data as an input to the model building unit” 0029 “The data extractor unit 116 extracts data from these data sources and provides inputs to the model building unit 118, the model selection unit 122 and the model retuning unit 124. The model building unit 118 is used to create soft-sensors for various properties of interest in the blend as explained in FIG. 4. The model retuning unit 124 retunes the soft-sensors with the addition data as explained using FIG. 9.”)
and selecting a soft sensor, from among the one or more soft sensors, for predicting runtime conformance metric for the process, the runtime conformance metric being associated with an outcome of the industrial process (0029 “The model selection unit 122 is used to identify the best or most accurate soft-sensor available in a model database 130. The selection of soft-sensor is based on but not limited to a root mean squared error, mean absolute error, mean absolute percentage error, etc. The model selection unit 122 selects the accurate soft-sensor and passes this information to blending rules optimizer unit 120 that obtains the best mixing rule for each feature of the soft-sensor that is used for predicting the property of a mixture or a blend. The model selection unit 122 selects the accurate soft-sensor and this soft-sensor is used for predicting the property of blend in real-time using the model prediction unit 126.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the instant application to have modified the soft sensor teachings of Zhao with the selection of soft sensor teachings of Masampally since Masampally teaches a means for identifying the best or most accurate soft-sensor and then obtains the best mixing rule for each feature of the soft-sensor that is used for predicting the property of a mixture or blend (0029).
The cited prior art do not teach determining to impute one or more process variables, from among the one or more process variables present in the unconditioned data, with one or more auxiliary process variables to obtain modified unconditioned data wherein the modified unconditioned data comprises the one or more auxiliary process variables in place of missing one or more process variables in the unconditioned data.
Moon teaches determining to impute one or more process variables, from among the one or more process variables present in the unconditioned data, with one or more auxiliary process variables to obtain modified unconditioned data wherein the modified unconditioned data comprises the one or more auxiliary process variables in place of missing one or more process variables in the unconditioned data (page 10 paragraph 10, “the processor 150 may identify at least one missing data processing method to process the missing data corresponding to at least one section based on the missing data information. The processor 150 may complement the missing data by considering parameter information for adjusting the processing degree of the missing data according to information on the missing data. Parameter information according to the present embodiment may include information on a section including missing data, information on a method for processing missing data, conditions for processing missing data, and the like”, 12:9 “the processor 150 processes a plurality of collected data, respectively, obtains a plurality of processed data, combines the plurality of processed data, processes abnormal data among the combined data, and processes the processed data among the combined data. Information on missing data including abnormal data may be identified, and the missing data may be processed using at least one missing data processing method based on the information on the missing data. The processor 150 may process the missing data and integrate the data ( 1030 )”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the instant application to have modified the teachings of Zhao, and Masampally with the teachings of Moon since Moon teaches a means for processing of missing data in order for better results from data utilization technology (page 2).
Regarding claim 8, the cited prior art teach The method of claim 7.
The cited prior art teach wherein the determining to impute the one or more process variables comprises: determining an impute state of an impute function, wherein the impute state comprises: a YES state to indicate the impute function to allow imputing the one or more process variables with the one or more auxiliary process variables (Zhao 0006 “the systems and methods optionally select an important measurable process variable (referred to as a “reference variable”). The data measurements for the selected reference variable are used to train the dynamic predictive inferential model”, 0045 “the systems and methods may apply a unique reference variable approach with subspace identification and PLS techniques to build and train the predictive inferential model”); and a NO state to indicate the impute function to restrict imputing the one or more process variables with the one or more auxiliary process variables (Masampally 0032 “Pairwise linearly correlated descriptors are identified by the Pearson correlation coefficient. When the absolute value of the correlation coefficient for two descriptors is greater than or equal to a 0.9, then the two descriptors are matched as a pair, and the one that is highly correlated to all the other descriptors is deleted. Data with of 68 descriptors is left for further analysis””).
Regarding claim 9, the cited prior art teach The method of claim 8.
The cited prior art teach the method further comprising:on ascertaining the impute state to be the YES state, imputing the one or more process variables with the one or more auxiliary process variables to obtain the modified unconditioned data, the one or more auxiliary process variables at least comprising a process variable missing in the unconditioned data (Zhao 0006 “the systems and methods optionally select an important measurable process variable (referred to as a “reference variable”). The data measurements for the selected reference variable are used to train the dynamic predictive inferential model”, 0045 “the systems and methods may apply a unique reference variable approach with subspace identification and PLS techniques to build and train the predictive inferential model”); and on ascertaining the impute state to be the NO state, removing the one or more process variables from the unconditioned data to obtain the modified unconditioned data (Masampally 0032 “Pairwise linearly correlated descriptors are identified by the Pearson correlation coefficient. When the absolute value of the correlation coefficient for two descriptors is greater than or equal to a 0.9, then the two descriptors are matched as a pair, and the one that is highly correlated to all the other descriptors is deleted” 0032 “Data with of 68 descriptors is left for further analysis”).
Regarding claim 10, the cited prior art teach The method of claim 9.
Masampally teaches wherein the determining to impute the one or more process variables further comprises: determining an outlier state of an outlier function, wherein the outlier state comprises: a YES state to indicate the outlier function to allow detecting presence of one or more outlier process variables among the one or more process variables present in the unconditioned data, wherein the one or more outlier process variables are process variables which are inconsistent with the other process variables present in the unconditioned data; and a NO state to indicate the outlier function to restrict detecting presence of the one or more outlier process variables (0032 “the structure-property data extracted from molecular structures of pure components of a blend has 696 features, also called as descriptors in this case. As part of preprocessing, all the descriptors with at least one missing value are ignored for further analysis. 180 such descriptors are removed to obtain a data with 516 descriptors. Descriptors with constant value or a standard deviation of zero are removed to obtain the data with 255 descriptors. Pairwise linearly correlated descriptors are identified by the Pearson correlation coefficient. When the absolute value of the correlation coefficient for two descriptors is greater than or equal to a 0.9, then the two descriptors are matched as a pair, and the one that is highly correlated to all the other descriptors is deleted. Data with of 68 descriptors is left for further analysis”, ).
Regarding claim 11, the cited prior art teach The method of claim 10.
Zhao teaches the method further comprising replacing the one or more outlier process variables with the one or more auxiliary process variables on ascertaining the outlier state to be the YES state (0006 “the systems and methods optionally select an important measurable process variable (referred to as a “reference variable”). The data measurements for the selected reference variable are used to train the dynamic predictive inferential model”, 0045 “the systems and methods may apply a unique reference variable approach with subspace identification and PLS techniques to build and train the predictive inferential model”).
Regarding claim 14, the cited prior art teach The method of claim 7.
wherein computing the correlation score comprises:
performing a statistical analysis to determine a correlation between each of the one or more process variables and the one or more auxiliary process variables present in the modified unconditioned data; based on the statistical analysis, obtaining the correlation score indicating an extent of correlation for the one or more process variables and the one or more auxiliary process variables present in the modified unconditioned data (Zhao 0083 “there are often continuously measured process variables available that are natively highly correlated with the selected output process variable (product properties) 317 contained in the lab data. For example, a temperature at top of a distillation column can be highly correlated with the product purity from the top of the column. For another example, a pressure-compensated-temperature (PCT) process variable at the top of a distillation column can be highly correlated with product quality, and is often used for quality control as a substitute of quality measurements at the column”);
comparing the correlation score, of each the one or more process variables and the one or more auxiliary process variables, with a threshold correlation score (Zhao 0083 “For example, a temperature at top of a distillation column can be highly correlated with the product purity from the top of the column. For another example, a pressure-compensated-temperature (PCT) process variable at the top of a distillation column can be highly correlated with product quality”) to identify one or more uncorrelated process variables present in the modified unconditioned data (Masampally 0032 “Pairwise linearly correlated descriptors are identified by the Pearson correlation coefficient. When the absolute value of the correlation coefficient for two descriptors is greater than or equal to a 0.9, then the two descriptors are matched as a pair, and the one that is highly correlated to all the other descriptors is deleted”);
and based on the comparison, selecting the one or more uncorrelated process variables, from the modified unconditioned data, to form the conditioned set of process variables (Masampally 0032 “Pairwise linearly correlated descriptors are identified by the Pearson correlation coefficient. When the absolute value of the correlation coefficient for two descriptors is greater than or equal to a 0.9, then the two descriptors are matched as a pair, and the one that is highly correlated to all the other descriptors is deleted”, 0032 “Data with of 68 descriptors is left for further analysis”).
Regarding claim 15, the cited prior art teach The method of claim 7.
Masampally teaches wherein to determine the conditioned set of process variables, the method further comprises:determining a relevance score for each of the one or more process variables and the one or more auxiliary process variables present in the modified unconditioned data, the relevance score indicating suitability of each of the one or more process variables and the one or more auxiliary process variables for being used in modelling the one or more soft sensors; comparing the relevance score of each of the one or more process variables and the one or more auxiliary process variables with a threshold relevance score; and based on the comparison, identifying one or more process variables, from among the one or more process variables and the one or more auxiliary process variables, suitable for being used in modelling the one or more soft sensors (0032 “As part of preprocessing, all the descriptors with at least one missing value are ignored for further analysis. 180 such descriptors are removed to obtain a data with 516 descriptors. Descriptors with constant value or a standard deviation of zero are removed to obtain the data with 255 descriptors. Pairwise linearly correlated descriptors are identified by the Pearson correlation coefficient. When the absolute value of the correlation coefficient for two descriptors is greater than or equal to a 0.9, then the two descriptors are matched as a pair, and the one that is highly correlated to all the other descriptors is deleted” 0032 “Data with of 68 descriptors is left for further analysis”).
Regarding claim 16 Zhao teaches A non-transitory computer-readable medium comprising instructions for modeling one or more soft sensors, the instructions being executable by a processing resource (0010) to:
analyse unconditioned data using an auxiliary set of process variables comprising one or more process variables, to determine absence of at least one process variable, wherein each of the one or more process variables indicates at least one characteristic associated with a process (0011 “To initialize the inferential model, the computer systems, methods, and program products: (i) selects process variables for the subject industrial process, and (ii) configures one of the selected process variables as an output process variable that represents output of the inferential model”);
based on the determination, remove the at least one process variable from the unconditioned data to obtain modified unconditioned data (0045 “the systems and methods build and train the predictive inferential models using historical data of the plant process, which may be automatically screened, sliced, and data selection techniques applied to remove bad segments from the data”);
identify a conditioned set of process variables from within the modified unconditioned data, wherein the conditioned set of process variables is capable of empirically representing the at least one characteristics associated with the process (0045 “the systems and methods build and train the predictive inferential models using historical data of the plant process, which may be automatically screened, sliced, and data selection techniques applied to remove bad segments from the data”);
provide the conditioned set of process variables to a [plurality] of inferential modellers (0002 “Inferential models or soft-sensors have been widely used in petroleum and chemical industries for process control and operation optimization”, 0088 “method 246 builds the predictive inferential model using the lab data in two major step”, 0094).
The cited prior art do not teach wherein the modified unconditioned data comprises an auxiliary process variable of the auxiliary set of process variables in place of the at least one process variable, a plurality of inferential modellers wherein each of the inferential modellers is to develop one or more soft sensors based on the conditioned set of process variables; and select a soft sensor, from among the one or more soft sensors, for predicting runtime conformance metric for the process, the runtime conformance metric being associated with an outcome of the process.
Masampally teaches provide the conditioned set of process variables to a [plurality] of inferential modellers wherein each of the inferential modellers is to develop one or more soft sensors based on the conditioned set of process variables (0031 “model building unit 118 is configured to creating a plurality of soft-sensors for the desired blend property as shown in the block diagram of FIG. 4. A data integrator 134 is used to integrate the data according to the requirement for data preprocessing techniques. The extracted relevant data needs to be preprocessed before using this data as an input to the model building unit” 0029 “The data extractor unit 116 extracts data from these data sources and provides inputs to the model building unit 118, the model selection unit 122 and the model retuning unit 124. The model building unit 118 is used to create soft-sensors for various properties of interest in the blend as explained in FIG. 4. The model retuning unit 124 retunes the soft-sensors with the addition data as explained using FIG. 9.”);
and select a soft sensor, from among the one or more soft sensors, for predicting runtime conformance metric for the process, the runtime conformance metric being associated with an outcome of the process (0029 “The model selection unit 122 is used to identify the best or most accurate soft-sensor available in a model database 130. The selection of soft-sensor is based on but not limited to a root mean squared error, mean absolute error, mean absolute percentage error, etc. The model selection unit 122 selects the accurate soft-sensor and passes this information to blending rules optimizer unit 120 that obtains the best mixing rule for each feature of the soft-sensor that is used for predicting the property of a mixture or a blend. The model selection unit 122 selects the accurate soft-sensor and this soft-sensor is used for predicting the property of blend in real-time using the model prediction unit 126.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the instant application to have modified the soft sensor teachings of Zhao with the selection of soft sensor teachings of Masampally since Masampally teaches a means for identifying the best or most accurate soft-sensor and then obtains the best mixing rule for each feature of the soft-sensor that is used for predicting the property of a mixture or blend (0029).
The cited prior art do not teach wherein the modified unconditioned data comprises an auxiliary process variable of the auxiliary set of process variables in place of the at least one process variable.
Moon teaches wherein the modified unconditioned data comprises an auxiliary process variable of the auxiliary set of process variables in place of the at least one process variable (page 10 paragraph 10, “the processor 150 may identify at least one missing data processing method to process the missing data corresponding to at least one section based on the missing data information. The processor 150 may complement the missing data by considering parameter information for adjusting the processing degree of the missing data according to information on the missing data. Parameter information according to the present embodiment may include information on a section including missing data, information on a method for processing missing data, conditions for processing missing data, and the like”, 12:9 “the processor 150 processes a plurality of collected data, respectively, obtains a plurality of processed data, combines the plurality of processed data, processes abnormal data among the combined data, and processes the processed data among the combined data. Information on missing data including abnormal data may be identified, and the missing data may be processed using at least one missing data processing method based on the information on the missing data. The processor 150 may process the missing data and integrate the data ( 1030 )”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the instant application to have modified the teachings of Zhao, and Masampally with the teachings of Moon since Moon teaches a means for processing of missing data in order for better results from data utilization technology (page 2).
Regarding claim 17, the cited prior art teach The non-transitory computer-readable medium of claim 16.
The cited prior art teach wherein to identify the conditioned set of process variables, the instructions are executable by the processing resource to:
perform a correlation analysis to compute a correlation score for each of the one or more process variables present in the modified unconditioned data, wherein the correlation score is to indicate a correlation among the one or more process variables, the correlation score being computed by statistical analysis of relationships between each of the one or more process variables present in the modified unconditioned data (Zhao 0083 “there are often continuously measured process variables available that are natively highly correlated with the selected output process variable (product properties) 317 contained in the lab data. For example, a temperature at top of a distillation column can be highly correlated with the product purity from the top of the column. For another example, a pressure-compensated-temperature (PCT) process variable at the top of a distillation column can be highly correlated with product quality, and is often used for quality control as a substitute of quality measurements at the column”);
compare the correlation score of each the one or more process variables with a threshold correlation score (Zhao 0083 “For example, a temperature at top of a distillation column can be highly correlated with the product purity from the top of the column. For another example, a pressure-compensated-temperature (PCT) process variable at the top of a distillation column can be highly correlated with product quality”) to identify one or more uncorrelated process variables present in the modified unconditioned data (Masampally 0032 “Pairwise linearly correlated descriptors are identified by the Pearson correlation coefficient. When the absolute value of the correlation coefficient for two descriptors is greater than or equal to a 0.9, then the two descriptors are matched as a pair, and the one that is highly correlated to all the other descriptors is deleted”);
and based on the comparison, select the one or more uncorrelated process variables, from the modified unconditioned data, to obtain the conditioned set of process variables (Masampally 0032 “Pairwise linearly correlated descriptors are identified by the Pearson correlation coefficient. When the absolute value of the correlation coefficient for two descriptors is greater than or equal to a 0.9, then the two descriptors are matched as a pair, and the one that is highly correlated to all the other descriptors is deleted”).
Regarding claim 18, the cited prior art teach The non-transitory computer-readable medium of claim 16.
Masampally teaches wherein to remove the at least one process variable from the unconditioned data, the instructions are executable by the processing resource to: detect presence of at least one outlier process variable within the unconditioned data, wherein the at least one outlier process variable is anomalous from the other one or more process variables present in the unconditioned data, and wherein the anomality is ascertained by statistically analysing each of the process variables present in the unconditioned data; and based on the analysis, determine to remove the at least one outlier process variable from the unconditioned data to obtain the modified unconditioned data (0032 “As part of preprocessing, all the descriptors with at least one missing value are ignored for further analysis. 180 such descriptors are removed to obtain a data with 516 descriptors. Descriptors with constant value or a standard deviation of zero are removed to obtain the data with 255 descriptors. Pairwise linearly correlated descriptors are identified by the Pearson correlation coefficient. When the absolute value of the correlation coefficient for two descriptors is greater than or equal to a 0.9, then the two descriptors are matched as a pair, and the one that is highly correlated to all the other descriptors is deleted.”).
Regarding claim 19, the cited prior art teach The non-transitory computer-readable medium of claim 16.
Masampally teaches wherein the instructions are executable by the processing resource to:predict a test conformance metric, by the one or more soft sensors, based on the conditioned set of process variables; compare the test conformance metric, predicted by the one or more soft sensors, with one or more historical conformance metrics, wherein the one or more historical conformance metrics is associated with one or more past observed outcomes of the process; and based on the comparison, select the soft sensor, from among the one or more soft sensors (0033 “the soft-sensor is built for predicting the desired property using 15 descriptors and the results are as demonstrated in graphical representation of FIG. 6A and 6B. FIG. 6A and 6B shows comparison of soft-sensor predictions with actual data and the density plot of corresponding errors for pure component data. These soft-sensors are considered as soft-sensors for predicting the desired property of the components used in blending process. A soft-sensor is then selected from amongst the plurality of soft-sensors for the desired property of the plurality of components used for blending based on accuracy of the soft-sensors”).
Regarding claim 20, the cited prior art teach The non-transitory computer-readable medium of claim 19.
Masampally teaches wherein the soft sensor is to predict the runtime conformance metric during runtime of the process (0033 “the soft-sensor is built for predicting the desired property using 15 descriptors and the results are as demonstrated in graphical representation of FIG. 6A and 6B. FIG. 6A and 6B shows comparison of soft-sensor predictions with actual data and the density plot of corresponding errors for pure component data. These soft-sensors are considered as soft-sensors for predicting the desired property of the components used in blending process. A soft-sensor is then selected from amongst the plurality of soft-sensors for the desired property of the plurality of components used for blending based on accuracy of the soft-sensors”).
Claim(s) 12 and 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhao et al (US PUB. 20180348717, herein Zhao) in view of Masampally et al (US PUB. 20230195853, herein Masampally) in further view of Moon et al (WO 2023090510, herein Moon) in further view of Castillo Castillo et al (US PUB. 20190332101, herein Castillo)
Regarding claim 12, the cited prior art teach The method of claim 7.
The cited prior art do not teach the method further comprising resampling the one or more process variables and the one or more auxiliary process variables, based on a resampling factor, for arranging the one or more process variables and the one or more auxiliary process variables into one or more subsets.
Castillo teaches the method further comprising resampling the one or more process variables and the one or more auxiliary process variables, based on a resampling factor, for arranging the one or more process variables and the one or more auxiliary process variables into one or more subsets (0080 “resampling selected batch variables with a base sampling rate in the batch process, such as one measurement sample per minute; and [0081] e) exporting selected and pre-processed batch dataset for further analysis in batch alignment offline and online”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the instant application to have modified the teachings of Zhao, Masampally and Moon with the teachings of Castillo since Castillo teaches a means for “removing outliers batch data that are unsuitable for batch data alignment” through its resampling and screening process (0076 0080).
Regarding claim 13, the cited prior art teach The method of claim 12.
Castillo teaches the method further comprising scaling each of the one or more subsets, based on a scaling factor, to be compatible for computing the correlation score (0186 “as illustrated in step 104 of FIG. 1A, for batch alignment and required analysis and modeling, the method 100 may scale batch variables' measurements. In the example embodiments, the 3-way batch data shown in FIG. 2D is unfolded in an “observation-wise” way into a 2-dimension matrix (i.e., each column of the unfolded matrix corresponds to a variable/tag, and the time series from each batch are appended at the bottom of data matrix). Then, each column is mean centered and scaled to unit variance. If there are missing values, they are filled with the last known value using a “zero-order hold” strategy. If the standard deviation value of a batch variable (a column) is very small (e.g. less than 1E-4), the unit value of 1.0 is used instead (i.e., these are flat trajectories)”, 0075 “The method (and system) may include scaling loaded batch data for batch alignment. The method (and system) may include screening and removing outlier (outlying) batch data from the loaded original raw batch data. The method (and system) may include selecting a reference batch as the basis of the batch alignment.”, 0031).
Response to Arguments
Applicant’s arguments, filed 3/10/2026, with respect to the rejection(s) of claim(s) 1 under 35 USC 103 have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of Zhao et al (US PUB. 20180348717, herein Zhao) in view of Masampally et al (US PUB. 20230195853, herein Masampally) in further view of Moon et al (WO 2023090510, herein Moon).
Applicant argues on pages 10-11 that the cited prior art does not teach the amendments to the claims. Examiner agrees. However, as a result of further search and consideration, Moon has been introduced. Moon teaches a supplementing data that has missing data by performing processing of the missing data and integrate the data that is determined (page 10 and 12).
Moon teaches supplement the unconditioned data with an auxiliary set of process variables to obtain modified unconditioned data, the auxiliary set at least comprising a process variable missing in the unconditioned data wherein the modified unconditioned data comprises the auxiliary set of process variables in place of the missing process variable (page 10 paragraph 10, “the processor 150 may identify at least one missing data processing method to process the missing data corresponding to at least one section based on the missing data information. The processor 150 may complement the missing data by considering parameter information for adjusting the processing degree of the missing data according to information on the missing data. Parameter information according to the present embodiment may include information on a section including missing data, information on a method for processing missing data, conditions for processing missing data, and the like”, 12:9 “the processor 150 processes a plurality of collected data, respectively, obtains a plurality of processed data, combines the plurality of processed data, processes abnormal data among the combined data, and processes the processed data among the combined data. Information on missing data including abnormal data may be identified, and the missing data may be processed using at least one missing data processing method based on the information on the missing data. The processor 150 may process the missing data and integrate the data ( 1030 )”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the instant application to have modified the teachings of Zhao, and Masampally with the teachings of Moon since Moon teaches a means for processing of missing data in order for better results from data utilization technology (page 2). This corresponds to the broadest reasonable interpretation of the argued limitations.
Therefore, claim 1 and its dependent claims are rejected. Claims 7 and 16 have similar limitations and are similarly argued and are similarly rejected along with their respective dependent claims.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to TAMEEM SIDDIQUEE whose telephone number is (571)272-1627. The examiner can normally be reached M-F 8:00-4:00.
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 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.
/TAMEEM D SIDDIQUEE/
Primary Examiner
Art Unit 2116
Prosecution Insights