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 .
DETAILED ACTION
The Amendment filed on 8/14/2026 has been received and entered. Application No. 18/735,456 Claims 1-20 are now pending. Claims 1, 9 and 15 have been amended.
Response to Amendment
Applicant’s amendment necessitated new grounds of rejection.
This action is made final in view of the new grounds of rejection.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sun et al. (U.S. Pub 2025/0217716) hereinafter Sun in view of JANDIAL et al. (U.S. Pub 2024/0330682) hereinafter Jan, in view of Kundapur et al. (U.S. Pat 11,836,153) hereinafter Kunda, in view of Pomroy et al. (U.S. Pat 7,974,942) hereinafter Pom.
As per Claim 1, Sun teaches A computer-implemented method for training a model to perform tabular data imputation, the method comprising: obtaining initial tabular training data for imputing data for a tabular data object defined for a user interface form of an application, (Fig. 1, ¶70 wherien the model setup component 104 may obtain the model setup parameters in any of various manners. As one possibility, the model setup component 104 may obtain at least some of the model setup parameters via a GUI that enables a user to specify values for certain model setup parameters by typing or otherwise entering the values into the GUI, selecting the values for the model setup parameters from a list of available options that are presented via the GUI, or uploading a data file that contains the values for the model setup parameters, among other possible ways that a user may input model setup parameters via a GUI. In this respect, the model setup component 104 may cause a client device 110 associated with a user to present the GUI for specifying the values for certain model setup parameters and may then receive setup data from the client device 110 that includes values for certain model setup parameters, among other possible ways that the model setup component 104 may obtain model setup parameters via a GUI.)
wherein the initial tabular training data includes rows of data collected from entries for the user interface form submitted by users of the application; (Fig. 3C, ¶106, ¶107 wherien n example second GUI view 300b comprising a target variable input element 325, which may be utilized, by a user via a client device 110, to input and/or edit values for a target time-series variable that are intended for use in training the ensemble model. As illustrated, the target variable data input element 322 may take the form of a text or numeral input table, such as a spreadsheet, but other input elements suitable for inputting time-series variable values are certainly possible)
generating tabular training data by invoking a second model trained over the initial tabular training data, wherein generating tabular training data comprises up-sampling the initial tabular training data (Fig. 10A, ¶190 wherien the data for the target time-series variable based on the obtained data for one or more offset variables so as to produce updated input data (i.e., “normalized” or “baseline” input data) for the target time-series variable, which may involve increasing or decreasing the input values of the given time-series data variable. In this respect, if the obtained values for a given offset variable have a different time resolution than the defined time resolution for the given ensemble model, then along similar lines to the above, the back-end computing platform 102 may down-sample (e.g., via aggregation) or up-sample (e.g., via interpolation) the obtained values for the given offset variable in order to align the time resolution of that obtained data with the defined time resolution of the given ensemble model.)
and training a first model by inputting the generated tabular training data as a predictor and by applying techniques to output predicted values of the user interface form. (Fig. 10B, ¶199 wherien the second GUI view 1000b may include one or more data representations that provide a user who is viewing the second GUI view 1000b with one or more indications of the predicted sequence of forecast values for a target time-series variable ([X.sub.P1: X.sub.P12]), as forecasted by the executed ensemble model. In an example, the second GUI view 1000b includes a text or numerical based data table 1030, including raw data representations of the predicted sequence of forecast values for a target time-series variable, organized by the reference times at which the forecasted values are forecasted. In another example, the second GUI view 1000b may include a visualization-based indication 1040 of the predicted sequence of forecast values for a target time-series variable, such as a plot, a graph, a chart, etc. Other known data-representations for the predicted sequence of forecast values for a target time-series variable are contemplated and may be presented via the second GUI view 1000b, as well)
However, Sun does not explicitly teach generating noisy tabular training data by invoking a second model trained over the initial tabular training data, wherein generating noisy tabular training data comprises training data according to learned application-specific masking rules defined as part of the second model, the application-specific masking rules being generated for the user interface form of the application; and training a first model by inputting the generated noisy tabular training data as a predictor and by applying denoising techniques to output predicted field values for fields of the user interface form.
Jan generating noisy tabular training data by invoking a second model trained over the initial tabular training data, (Fig. 2B, ¶31 wherein collected tabular data 205, in some embodiments, comprises a tabular data format wherein each row of the collected tabular data 205 define a single tabular data record 260 and each of the columns 270 corresponds to an individual feature (shown as features 271, 272, 273, 274, 275 and 276), where each feature is an individual property or attribute something (or someone) associated with a record 260. The feature values that populate the set of features (271-276) for each record thus describes characteristic of object (such as a person, for example) associated with that particular record. Feature values can be continuous variables (e.g., numeric values and/or other continuous ordered information) and/or discrete values (e.g., categorical, class, and/or other feature information that can only assume certain values).)
wherein generating noisy tabular training data comprises training data according to learned application-specific masking rules defined as part of the second model, the application-specific masking rules being generated for the user interface form of the application; and (Fig. 2B, ¶32 the collected tabular data 205 is corrupted by the noise masking function 210, which introduces noise elements (shown as noise 280) that mask the values of one or more features in each tabular data record 260. In some embodiments, noise 280 is applied to mask features randomly and/or based on a predefined probability distribution. In some embodiments, the noise masking function 210 sets a maximum threshold with respect to the maximum number of features masked by noise 280 in any one record 260. In some embodiments the maximum threshold is based on a function of the number of features each record 260 includes. For example, in some embodiments, the noise masking function 210 randomly introduces noise 280 to mask one or more features, but no more than a maximum percentage (e.g. 30%) defined by the maximum threshold. In other embodiments, a threshold for limiting the application of noise 280 may be based on other criteria. As discussed below, because the masking of features with noise 280 is random, over the course of training, the denoising variational autoencoder 114 learns the intra-feature correlations between different sets of the features (271-276).)
training a first model by inputting the generated noisy tabular training data as a predictor and by applying denoising techniques to output predicted field values for fields of the user interface form. (Fig. 2A, Fig. 4, ¶33, ¶50 wherien the encoder model 220-decoder model 224 pair of the denoising variational autoencoder 114 is trained to predict the values of masked features in each record of noised tabular data 215 to produce a de-noised reconstruction of records of the collected tabular data 205 as they were prior to the introduction of the noise 280 by the noise masking function 210, and generate de-noised tabular data 230 comprising those reconstructed tabular data records. In some embodiments, the encoder model 220 and decoder model 224 are trained together. A reconstruction loss function is computed by a reconstruction loss optimizer 240 based on the differences between the original collected tabular data 205 and the de-noised tabular data 230. The reconstruction loss optimizer 240 iteratively adjusts both encoder model 220 and decoder model 224 using the reconstruction loss as feedback to reduce the reconstruction loss, thus improving the ability of the denoising variational autoencoder 114 to produce de-noised tabular data 230 that preserves the inter-feature correlations found in the collected tabular data records 130.)
It would have been obvious to one having ordinary skill in the art at the time the invention was filed to utilize the teaching of generating synthetic tabular data for machine learning and other applications of Jan with the teaching of building and executing an ensemble model for forecasting time-series data of Sun because Jan teaches an improved systems and methods for machine learning based generation of synthetic tabular data by providing for, among other things, a machine learning model based technologies for generating synthetic tabular data that closely replicates the inter-feature correlations found in tabular data collected from real data sources. One or more of the embodiments presented in this disclosure address the shortcomings of existing synthetic data generating techniques by taking advantage of the well-structured nature of tabular data to utilize the introduction of noise in order to learn inter-feature correlations, which is not a technique suggested by prior techniques. These embodiments involve using a variational autoencoder to learn inter-feature correlations found in tabular data collected from real data sources, and then using the trained variational autoencoder to train a generator model of a Generative Adversarial Network (GAN) to generate synthetic tabular data that exhibits the inter-feature correlation distribution found in the tabular data collected from real data sources. (¶2, ¶3)
However. Sun as modified does not explicitly teach data collected from data objects defined through the user interface based on entries submitted by the user of the application;
Kunda teaches data collected from data objects defined through the user interface based on entries submitted by the user of the application; (Fig. 2, col. 6 lines 54-65 wherein extensible data model 212 may provide custom data objects 216 that allow intelligent talent platform to read an undefined data object from remote systems and output such data objects back to the remote systems. The custom data objects 216 may include user-defined entries, and each entry may include custom identification fields, data type, and data values)
It would have been obvious to one having ordinary skill in the art at the time the invention was filed to utilize the teaching of bidirectional high-volume data synchronization of Kunda with the teaching of building and executing an ensemble model for forecasting time-series data of Sun as modified because Kunda teaches an improved system and method for data storages in multiple systems and data synchronization among the same, and in particular to a system, method, and storage medium including executable computer programs for bidirectional high-volume data synchronization between intelligent platform and remote system with minimal latency wherein data objects stored in the information systems used by the organization and in the intelligent talent platform may be updated at each of the information systems or at the intelligent talent platform from time to time. Further, the data objects stored in the information systems and the intelligent talent platform may be related in the sense that the data object in one system may have been derived from another data object in another system. To ensure the data consistency among related data objects stored at different information systems, there are needs to automatically synchronize these related data objects bidirectionally between the intelligent talent platform and the information systems of the customer organizations (referred to hereinafter as the remote systems). The synchronization needs to be performed at large scale with little to no human user intervention. (col. 1 lines 13-20 and col. 2 lines 45-60)
Sun as modified previously taught up-sampling. However, Sun as modified does not explicitly teach tabular training data comprises the initial tabular training data by applying masking over the initial tabular training data to generate additional tabular data including masked copies of rows of the initial tabular training data.
Pom tabular training data comprises the initial tabular training data by applying masking over the initial tabular training data to generate additional tabular data including masked copies of rows of the initial tabular training data,(Fig. 1, Fig. 2, col. 4 lines 27-45, col. 6 lines 20-28 & lines 55-67, col. 7 lines 1-3 wherein Data masking system 10 includes at least one original database 22, at least one copied database 24 which is created by copying at least a portion of the original database 22, a computer 28, and a masking engine 20 for interfacing between the copied database 24 and the computer 28 wherein original database 22 contains a number of data records 30, with each data record 30 containing at least one data field 32, at least some of which are target data fields 34 wherein the user would indicate the data elements to be masked (typically tables and fields) and would specify the data transformation (e.g. credit card number generator) to be used when masking. Additional configuration parameters such as credit card type and randomization pattern could also be specified. Multiple transformations are specified in the same way (table, field, data transformation and parameters) allowing complex masking rules to be configured incrementally wherein the dependency analyzer determines that Full Name is dependent upon First and Last name and therefore is automatically configured to run after masking of First and Last name has completed wherien the masking engine 20 runs the masking project based on the configurations from steps (104) to (114) on copied database 24 to result in a masked database 26 (which replaces copied database 24) containing masked data records 36, where the confidential data fields 34 from the original database 22 are now masked data fields 38)
It would have been obvious to one having ordinary skill in the art at the time the invention was filed to utilize the teaching of data masking system of Pom with the teaching of building and executing an ensemble model for forecasting time-series data of Sun as modified because Pom teaches an improved data masking is conducted for all required confidential data fields by populating the empty delta data records 406 with the masked data according to the data transformations configured at steps (108) and (110) in the user selection process previously described. These masked delta data records 408 will be later used in the merge step (310) to create the masked primary data record 412. Through the use of delta data records, performance is enhanced over the "update engine" masking engine transformer as bulk loading of the original data record is significantly faster than writing row-by-row updates to it. (Col. 8 lines 1-11)
As per Claim 2, the rejection of claim 1 is hereby incorporated by reference; Sun as modified further teaches wherein each row of the initial tabular training data includes input field values for the fields of the user interface form stored for the user interface form of the application at a data storage. (Fig. 3A-3D, ¶101, ¶104, ¶107 wherein a set of input elements (e.g., fillable text fields, dropdown lists, etc.) that enable the user to input setup parameters for input to the back-end computing platform 102/data storage layer, via the functionality of the model setup component 104. For example, the first GUI view 300a may include one or more input fields for inputting model setup parameters, such as, but not limited to, (i) a time-series variable input field 302 that provides a field for a user to indicate a time-series variable for which a user requests one or more forecast values, (ii) a time resolution input element 304 that provides a field for a user to indicate a time resolution for a given ensemble model, (iii) forecast window input element 312 that provides a field for a user to indicate a time window in which the user desires forecast values for the time-series variable (e.g., the time-series variable input at the time-series variable input field 302), (iv) a shorter-term forecast sub-window input field 316 that provides a field for a user to indicate a forecast window for one or more shorter-term time-series models, and (v) a longer-term forecast sub-window input field 318 that provides a field for a user to indicate a forecast window for one or more longer-term time-series models wherein GUI view 300c comprising an influencing variable input element 330 that enables a user to input and/or edit values for any influencing variables that are intended for use in training the ensemble model.; as taught by Sun)
As per Claim 3, the rejection of claim 1 is hereby incorporated by reference; Sun as modified further teaches wherein the application-specific masking rules are applied to the initial tabular training data to up-sample the initial tabular training data to generate the noisy tabular training data by using data from the noise tabular training data as the predictor, (Fig. 10A, ¶190 wherien the data for the target time-series variable based on the obtained data for one or more offset variables so as to produce updated input data (i.e., “normalized” or “baseline” input data) for the target time-series variable, which may involve increasing or decreasing the input values of the given time-series data variable. In this respect, if the obtained values for a given offset variable have a different time resolution than the defined time resolution for the given ensemble model, then along similar lines to the above, the back-end computing platform 102 may down-sample (e.g., via aggregation) or up-sample (e.g., via interpolation) the obtained values for the given offset variable in order to align the time resolution of that obtained data with the defined time resolution of the given ensemble model.as taught by Sun)
wherein, based on using the second model, a respective number of masked copies generated per row of the initial tabular training data is generated, wherein the respective number of masked copies differs between two row of data in the initial tabular training data. . (Fig. 2A, Fig. 4, ¶33, ¶50 wherien the encoder model 220-decoder model 224 pair of the denoising variational autoencoder 114 is trained to predict the values of masked features in each record of noised tabular data 215 to produce a de-noised reconstruction of records of the collected tabular data 205 as they were prior to the introduction of the noise 280 by the noise masking function 210, and generate de-noised tabular data 230 comprising those reconstructed tabular data records. In some embodiments, the encoder model 220 and decoder model 224 are trained together. A reconstruction loss function is computed by a reconstruction loss optimizer 240 based on the differences between the original collected tabular data 205 and the de-noised tabular data 230 wherien the encoder model 220 and decoder model 224 are trained together. A reconstruction loss function is computed by a reconstruction loss optimizer 240 based on the differences between the original collected tabular data 205 and the de-noised tabular data 230 wherien The reconstruction loss optimizer 240 iteratively adjusts both encoder model 220 and decoder model 224 using the reconstruction loss as feedback to reduce the reconstruction loss, thus improving the ability of the denoising variational autoencoder 114 to produce de-noised tabular data 230 that preserves the inter-feature correlations found in the collected tabular data records 130.; as taught by Jan)
As per Claim 4, the rejection of claim 1 is hereby incorporated by reference; Sun as modified further teaches wherein generating the noisy tabular training data comprises: obtaining interaction data collected in relation to user interactions for filling in data in the fields of the user interface form, (Fig. 3B, Fig. 6, ¶156 wherien GUI view 300b comprising a target variable input element 325, which may be utilized, by a user via a client device 110, to input and/or edit values for a target time-series variable that are intended for use in training the ensemble model wherien the user may then interact with the model configuration GUI of the time-series forecasting tool to input configuration parameters for the new ensemble model. For example, the user may use the model configuration GUI to specify which time-series models to include in the ensemble model by selecting the time-series models from the generated sets of time-series models that are presented via the model configuration GUI, among other possible ways that the time-series models may be specified via the model configuration GUI.; as taught by Sun)
wherein the interaction data includes an order of interactions with fields and data entries, wherein the interaction data includes respective position of the fields on the user interface form when displayed at a user interface of a display device; (¶156 wherien the model configuration GUI may present the different sets of time-series models in the form of separate lists (e.g., a first list for the shorter-term models and a second list for the longer-term models), or as a single, combined list where the target timeframe for each of the listed models is indicated in some way, among other possible ways that the generated sets of time-series models may be presented. As another example, the user may use the model configuration GUI to specify corresponding weights for at least some of the selected time-series models by typing the weights into the model configuration GUI or selecting the weights from a list of available options that are presented via the model configuration GUI, among other possible ways that the weights for the time-series models may be input via the model configuration GUI; as taught by Sun )
identifying patterns for filling in data in the user interface form by analyzing the obtained interaction data; and (Fig. 3A. ¶104 wherein the first GUI view 300a may include a set of input elements (e.g., fillable text fields, dropdown lists, etc.) that enable the user to input setup parameters for input to the back-end computing platform 102 via the functionality of the model setup component 104. For example, the first GUI view 300a may include one or more input fields for inputting model setup parameters, such as, but not limited to, (i) a time-series variable input field 302 that provides a field for a user to indicate a time-series variable for which a user requests one or more forecast values, (ii) a time resolution input element 304 that provides a field for a user to indicate a time resolution for a given ensemble model, (iii) forecast window input element 312 that provides a field for a user to indicate a time window in which the user desires forecast values for the time-series variable (e.g., the time-series variable input at the time-series variable input field 302), (iv) a shorter-term forecast sub-window input field 316 that provides a field for a user to indicate a forecast window for one or more shorter-term time-series models, and (v) a longer-term forecast sub-window input field 318 that provides a field for a user to indicate a forecast window for one or more longer-term time-series models; as taught by Sun )
generating a set of masked copies per row of the initial tabular training data to be included in the noisy tabular training data. (Fig. 2A, Fig. 4, ¶33, ¶50 wherien the encoder model 220-decoder model 224 pair of the denoising variational autoencoder 114 is trained to predict the values of masked features in each record of noised tabular data 215 to produce a de-noised reconstruction of records of the collected tabular data 205 as they were prior to the introduction of the noise 280 by the noise masking function 210, and generate de-noised tabular data 230 comprising those reconstructed tabular data records. In some embodiments, the encoder model 220 and decoder model 224 are trained together. A reconstruction loss function is computed by a reconstruction loss optimizer 240 based on the differences between the original collected tabular data 205 and the de-noised tabular data 230 wherien the encoder model 220 and decoder model 224 are trained together. A reconstruction loss function is computed by a reconstruction loss optimizer 240 based on the differences between the original collected tabular data 205 and the de-noised tabular data 230 wherien The reconstruction loss optimizer 240 iteratively adjusts both encoder model 220 and decoder model 224 using the reconstruction loss as feedback to reduce the reconstruction loss, thus improving the ability of the denoising variational autoencoder 114 to produce de-noised tabular data 230 that preserves the inter-feature correlations found in the collected tabular data records 130.; as taught by Jan)
As per Claim 5, the rejection of claim 1 is hereby incorporated by reference; Sun as modified further teaches comprising: receiving first input data from a user including a first field value for a first field on the user interface form provided on a user interface of the application; (Fig. 3A, ¶104, ¶154, ¶184, ¶193 wherien the first GUI view 300a may include a set of input elements (e.g., fillable text fields, dropdown lists, etc.) that enable the user to input setup parameters for input to the back-end computing platform 102 via the functionality of the model setup component 104. For example, the first GUI view 300a may include one or more input fields for inputting model setup parameters, such as, but not limited to, (i) a time-series variable input field 302 that provides a field for a user to indicate a time-series variable for which a user requests one or more forecast values, (ii) a time resolution input element 304 that provides a field for a user to indicate a time resolution for a given ensemble model, (iii) forecast window input element 312 that provides a field for a user to indicate a time window in which the user desires forecast values for the time-series variable (e.g., the time-series variable input at the time-series variable input field 302), (iv) a shorter-term forecast sub-window input field 316 that provides a field for a user to indicate a forecast window for one or more shorter-term time-series models, and (v) a longer-term forecast sub-window input field 318 that provides a field for a user to indicate a forecast window for one or more longer-term time-series models; as taught by Sun)
in response to receiving the first input data, invoking the first model to predict values for one or more other user interface fields of the user interface form based on the first field value for the first field, the first model being for tabular data imputation; (Fig. 9, ¶194 wherein after obtaining and preparing the input data for use in executing the given ensemble model, the back-end computing platform 102 may execute the given ensemble model using the input data and thereby cause the given ensemble model to predict and output a sequence of forecast values for the target time-series variable. For instance, the back-end computing platform 102 may provide the input data as input to the given ensemble model, which may then function to (i) provide the input data to each of its underlying time-series models and thereby causing each of the underlying time-series models to output a respective prediction comprising a forecasted sequence of values of the target time-series variable for a target timeframe (e.g., a shorter-term or longer-term target timeframe), which is sometimes referred to as “fitting” the time-series models to the input data, (ii) blend the respective predictions of the underlying time-series models together in accordance with the model configuration parameters of the given ensemble model. ; as taught by Sun)
providing one or more predicted field data values for the one or more other user interface fields on the user interface form as recommendations for the user; (Fig. 7, ¶161, ¶162 wherien the GUI view 700 includes a shorter-term timeframe model selection input field 701 and a longer-term timeframe selection input field 702, each of which may be an input field (e.g., a dropdown list, a text input field, etc.) configured to receive input for a specification of one or more candidate models, of the respective sets of models, for selection for inclusion in an ensemble model. Further, in some examples, the GUI view 700 includes a model weight input field 710, wherein a user may provide a specification of one or more weights “W,” with which to weigh the output of an individual model, within the ensemble model, for compiling the resultant ensemble model. Further still, in some examples, the GUI view 700 may include a selector input field 712, which may be a simple input, such as a button, that is selected to indicate that the input to the other fields (e.g., fields 701, 702, 710) is complete and a user presented with the GUI view 700 wishes to submit data, based on a specification of the inputs to fields 701, 702, 710, to the back-end computing platform 102, for generating an ensemble model; as taught by Sun)
receiving second input data from the user including a second field value for a second field of the one or more other user interface fields, wherein the second input data is confirming or modifying a respective predicted field data value for the second field; (Fig. 10, ¶165, ¶178, ¶179 wherien the user may use the model execution GUI to specify which ensemble model to execute by selecting the ensemble model from a list of options that are presented via the model configuration GUI (if there are multiple ensemble models available) and/or clicking a selectable button for executing the ensemble model, among other possible ways that the user input a request to execute a particular ensemble model via the model execution GUI wherein the back-end computing platform 102 installed with the model building component 105 could automatically select the time-series models and/or corresponding weights for the new ensemble model, or at least could make an initial selection of the time-series models and/or corresponding weights for the new ensemble model that is then presented to the user as a recommendation which can either be adopted, modified, or rejected by the user ; as taught by Sun)
in response to receiving the second field value from the user, automatically invoking the first model to predict a third field value for a third field of the user interface form based on the first field value received from the user for the first field and the second field for the second field; and (¶165 wherien it is possible that the back-end computing platform 102 installed with the model building component 105 could automatically select the time-series models and/or corresponding weights for the new ensemble model, or at least could make an initial selection of the time-series models and/or corresponding weights for the new ensemble model that is then presented to the user as a recommendation which can either be adopted, modified, or rejected by the user. In this respect, the back-end computing platform 102 could automatically select the time-series models and corresponding weights for the new ensemble model based on any of various factors, including but not limited to the performance measures that are determined during the hyperparameter tuning process. For example, for each of the first and second sets of time-series models, the back-end computing platform 102 could use the performance measures of the time-series models as a basis for selecting a given subset of the time-series models in the set (e.g., based on a performance-measure threshold, a ranking based on performance measure, or a combination thereof), and if the selected subset includes multiple time-series models, the back-end computing platform 102 could then either assign each such time-series model an equal weight (e.g., a weight having a value that is equal to 1 divided by the number of models) or could determine the respective weights of the time-series models based on the respective performance measures of the time-series models (e.g., models with higher performance measures are assigned higher weights and models with lower performance measures are assigned lower weights), among other possibilities; as taught by Sun)
providing the third field value for the third field on the user interface form in additional to previously provided predicted or confirmed field data values for fields of the user interface form. (Fig. 10B, ¶199 wherein the second GUI view 1000b may include one or more data representations that provide a user who is viewing the second GUI view 1000b with one or more indications of the predicted sequence of forecast values for a target time-series variable ([X.sub.P1: X.sub.P12]), as forecasted by the executed ensemble model. In an example, the second GUI view 1000b includes a text or numerical based data table 1030, including raw data representations of the predicted sequence of forecast values for a target time-series variable, organized by the reference times at which the forecasted values are forecasted. In another example, the second GUI view 1000b may include a visualization-based indication 1040 of the predicted sequence of forecast values for a target time-series variable, such as a plot, a graph, a chart, etc. Other known data-representations for the predicted sequence of forecast values for a target time-series variable are contemplated and may be presented via the second GUI view 1000b, as well; as taught by Sun)
As per Claim 6, the rejection of claim 5 is hereby incorporated by reference; Sun as modified further teaches wherein the first model predicts the data for the third field of the user interface form based on only the first and second input data received from the user without using other field data values from the provided one or more predicted field data values as recommendations for the user interface form. (Fig. 10B, ¶165, ¶199 wherien it is possible that the back-end computing platform 102 installed with the model building component 105 could automatically select the time-series models and/or corresponding weights for the new ensemble model, or at least could make an initial selection of the time-series models and/or corresponding weights for the new ensemble model that is then presented to the user as a recommendation which can either be adopted, modified, or rejected by the user. In this respect, the back-end computing platform 102 could automatically (without using other fields) select the time-series models and corresponding weights for the new ensemble model based on any of various factors, including but not limited to the performance measures that are determined during the hyperparameter tuning process. For example, for each of the first and second sets of time-series models (first and second input data), the back-end computing platform 102 could use the performance measures of the time-series models as a basis for selecting a given subset of the time-series models in the set (e.g., based on a performance-measure threshold, a ranking based on performance measure, or a combination thereof), and if the selected subset includes multiple time-series models, the back-end computing platform 102 could then either assign each such time-series model an equal weight (e.g., a weight having a value that is equal to 1 divided by the number of models) or could determine the respective weights of the time-series models based on the respective performance measures of the time-series models (e.g., models with higher performance measures are assigned higher weights and models with lower performance measures are assigned lower weights), among other possibilities wherein the second GUI view 1000b may include one or more data representations that provide a user who is viewing the second GUI view 1000b with one or more indications of the predicted sequence of forecast values for a target time-series variable ([X.sub.P1: X.sub.P12]), as forecasted by the executed ensemble model; as taught by Sun)
As per Claim 7, the rejection of claim 5 is hereby incorporated by reference; Sun as modified further teaches comprising: in response to receiving fourth input data from the user including a fourth field value for a fourth field of the user interface form, the fourth field being different from the first and second fields, invoking the first model to predict data for at least one other field of the user interface form based on the first field value, the second field value, and the fourth field value. (Fig. 11, ¶208 wherien an example first GUI view 1100 for the model evaluation GUI that shows a view of a VoV comparison is, in accordance with the present disclosure is illustrated. As illustrated, an indication of a data table 1110 is presented via the first GUI view 1100. For example, the data table 1110 may include past real data and then multiple sets of predicted sequences of forecast values for a target time-series variable, based on different executions of the ensemble model. For example and as shown, the data table 1110 may show model forecast data values for a given time-series variable for the years 2023 and 2024 and show two predicted sequences of forecast values for a target time-series variable for each. The two differing predicted sequences of forecast values for a target time-series variable are from different executions of the ensemble mode (e.g., an August execution and a September execution). Thus, by presenting this data side-by-side, a user can draw a comparison of the output of the ensemble model, at different times. ; as taught by Sun)
As per Claim 8, the rejection of claim 7 is hereby incorporated by reference; Sun as modified further teaches wherein the first model is trained based on a denoising techniques applied to noisy tabular training data, (Fig. 1, ¶26 wherien server applications 110 include a denoising variational autoencoder training processes 112 that is executed to train a denoising variational autoencoder 114. The denoising variational autoencoder 114 is trained by denoising variational autoencoder training processes 112 using tabular data records (e.g. from collected tabular data records 130) that are partially corrupted by the introduction of noise, to predict the value of features masked by the noise in order to reproduce the original tabular data records reflecting the value of features as they were in the original tabular data records before the noise was introduced.; as taught by Jan)
wherein the noisy tabular training data is generated for a tabular data object stored at a storage associated with the user interface by using the second model, therein the tabular data object includes data objects corresponding to user interface fields of the user interface form. (Fig. 7, ¶26, ¶66 wherein While learning to denoise the corrupted tabular data records, the denoising variational autoencoder 114 ultimately also learns the multivariant inter-feature correlations present between the features of the collected tabular data records 130. Then, using the trained denoising variational autoencoder 114, the generator model 122 is trained using a DVAE-TGAN training process 118, which can be implemented as a server application 110 executed by the servicer(s) 108. The generator model 122 is trained to operate as a conditional generative network by the DVAE-TGAN framework 116 using an adversarial principle to produce synthesize tabular data records 132 that are realistic in that they preserve multivariant inter-feature correlations and other characteristics exhibited by the collected tabular data records 130. The synthesize tabular data records 132 can be used by application 103 to efficiently train machine learning model 105 and/or perform other tasks such as, but not limited to, performing simulations and/or beta testing of applications or systems wherien if possible values for a feature in column i of synthesized tabular data 720 has the three possible values of A, B, and C, then the condition vector 710 instructs the generator model 122 to produce synthesized tabular data 720 having the feature in column i with the value specified by the condition vector 710. This set of synthesized tabular data 720 is stored to the synthesized tabular data records 132, or otherwise made available to an application, such as application 103 and/or a server applications 110, to perform tasks such as, but not limited to, training a machine learning model (e.g., such as machine learning model 105) and/or perform other tasks such as, but not limited to, performing simulations and/or beta testing of applications or systems. ; as taught by Jan)
Claim 9 is similar in scope to Claim 1; therefore, Claim 9 is rejected under the same rationale as Claim 1.
Claim 10 is similar in scope to Claim 2; therefore, Claim 10 is rejected under the same rationale as Claim 2.
Claim 11 is similar in scope to Claim 3; therefore, Claim 11 is rejected under the same rationale as Claim 3.
Claim 12 is similar in scope to Claim 4; therefore, Claim 12 is rejected under the same rationale as Claim 4.
Claim 13 is similar in scope to Claim 5; therefore, Claim 13 is rejected under the same rationale as Claim 5.
Claim 14 is similar in scope to Claim 6; therefore, Claim 14 is rejected under the same rationale as Claim 6.
Claim 15 is similar in scope to Claim 1; therefore, Claim 15 is rejected under the same rationale as Claim 1.
Claim 16 is similar in scope to Claim 2; therefore, Claim 16 is rejected under the same rationale as Claim 2.
Claim 17 is similar in scope to Claim 3; therefore, Claim 17 is rejected under the same rationale as Claim 3.
Claim 18 is similar in scope to Claim 4; therefore, Claim 18 is rejected under the same rationale as Claim 4.
Claim 19 is similar in scope to Claim 5; therefore, Claim 19 is rejected under the same rationale as Claim 5.
Claim 20 is similar in scope to Claim 6; therefore, Claim 20 is rejected under the same rationale as Claim 6.
Response to Arguments
Applicant's arguments have been considered but are moot in view of the new ground(s) of rejection wherein Kunda is relied upon to teach the limitation reciting “data collected from data objects defined through the user interface based on entries submitted by the user of the application;” and Pom is relied upon to teach the limitation “tabular training data comprises the initial tabular training data by applying masking over the initial tabular training data to generate additional tabular data including masked copies of rows of the initial tabular training data.”.
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 extension fee 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 date of this final action.
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. See PTO-Form 892 for listed of cited references.
Inquiry
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ANGIE BADAWI whose telephone number is (571)270-7590. The examiner can normally be reached Monday thru Wednesday 9:00am - 5:00pm EST with Thursdays and Fridays off.
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, Fred Ehichioya can be reached at (571) 272-4034. 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.
/ANGIE BADAWI/Primary Examiner, Art Unit 2179
