DETAILED ACTION
This Office Action is sent in response to the Applicant’s Communication received on 02/19/2026 for application number 17/945,391. The Office hereby acknowledges receipt of the following and placed of record in file: Specification, Drawings, Abstract, Oath/Declaration, IDS, and Claims.
Claims 1-20 are pending.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Arguments
Claim Objections
Applicant argues that the amendments to Claim 12 obviates the objections. Therefore, Applicant respectfully requests the objections to Claim 12 be withdrawn.
The Examiner agrees. The Claim 12 objection is withdrawn.
35 USC 101
On page 9 of the remarks section, the Applicant argues that the amended Claims recite an improvement to systems for populating incomplete datasets by imputing missing values. Specification at [0002] - [0003] and [0021] - [0022]. Notably, with previous systems utilizing machine learning, missing values can create biases and analysis errors. Id. The Specification explains the issues with prior solutions for overcoming this problem, for instance: "[a] non-ideal strategy for using incomplete datasets is to ignore the missing value(s), for example, by discarding entire rows and/or columns containing missing values." Id. at [0021]. Accordingly, the present application details a solution for overcoming these deficiencies. Id. at [0002] - [0003] and [0021] - [0022]. Claim 1 notably reflects this improvement. Applicant respectfully submits that the Claims are, therefore, directed toward a technical improvement for imputing data to incomplete datasets through the recursive selection and training of specific machine learning models. As such, the claimed technology constitutes a practical application because it is a clear advancement and improvement in technology over prior systems as reflected in the Specification and Claims.
The Examiner respectfully disagrees. Instant application paragraphs [0002], [0003], [0021], and [0022] have high-level steps of an improvement. It is to be noted, if the specification sets forth in detail an improvement in technology, the claim must be evaluated to ensure that the claim itself reflects the detailed steps leading to disclosed improvement. That is, the claim includes the components or steps of the invention that provide the improvement described in the specification. In this regard, the claims lack many of the inventive steps pertaining to the disclosed improvement. For example, but not limited to, instant specification paragraphs [0056]-[0061], discloses inventive steps that are not reflected in the claim. Such as, “it may be appropriate for a user to manually fill in missing feature values based on an estimate or other knowledge”, “this (conditional) step may be considered initial dataset ‘priming’ so that the rest of the method 600 may utilize machine learning to impute additional feature values”, “model may be selected based on an automatic determination of the associated data type”, “the indices of the rows of data that are currently filled for the current feature may be extracted and separated from the indices of the rows of data that are not currently filled”, and “the information in the filled dataset indices may then be applied to other rows of data from the features that have already been filled by previous imputation rounds or from rows not originally containing missing”. Therefore, the specification sets forth in detail steps pertaining to an improvement in technology, but the claim itself does not reflect the detailed steps leading to said disclosed improvement.
The Applicant further argues that the present claims recite an improvement to "system performance based upon adjustments to parameters of a machine learning model associated with tasks or workstreams." For example, the present Claims recite "a group of imputation models comprising a deep learning model for categorical variable imputation, a regression model for continuous variable imputation, and a classification model for binary variable imputation" that work together to impute missing data. Specifically, the imputation model "corresponding to the determined data type," is "select[ed]," "train[ed]," and then "predict[s] missing values," at each recursive iteration "until the dataset is filled." Applicant submits that the specific interaction between the imputation models and the recursive process as recited in the claims allows for the improvement when populating incomplete datasets. Therefore, Applicant submits that the present claims recite a technical improvement because they are an improvement of "system performance based upon adjustments to parameters of a machine learning model associated with tasks or workstreams."
The Examiner respectfully disagrees. The claimed limitation "a group of imputation models comprising a deep learning model for categorical variable imputation, a regression model for continuous variable imputation, and a classification model for binary variable imputation" was analyzed under Step 2A Prong Two as an additional element that merely limits the judicial exception to particular fields of use or technological environments. Therefore, the cited additional element does not integrate the judicial exception into a practical application and cannot provide for an inventive concept. Furthermore, the claimed limitations corresponding to the cited “select[ed]”, "predict[s] missing values", and "until the dataset is filled" steps were analyzed under Step 2A Prong One as being abstract ideas. The cited actions of recursively imputing values until the dataset is filled, selecting models, and predicting based on feature values are limitations recited at a high-level generality and, under the Broadest Reasonable Interpretation (BRI), can be interpreted as procedures of human observation, evaluations, judgements, or opinions. There are no explicit steps or details recited that meaningfully limit the claimed limitations to falling outside the grouping of abstract ideas. The claimed limitations can be performed mentally with the aid of pen and paper, and are therefore mental processes. The claimed limitation corresponding to the “train[ed]” step was analyzed under Step 2A Prong Two as an additional element merely limiting the judicial exception to the particular field of use or technological environment of machine learning training. Therefore, the cited additional element does not integrate the judicial exception into a practical application and cannot provide for an inventive concept.
Therefore, the 35 USC 101 rejection is maintained.
35 USC 103
On page 8 of the remarks section, Applicant argues that Resnick and Chu fail to teach or suggest at least "selecting an imputation model corresponding to the determined data type from a group of imputation models comprising a deep learning model for categorical variable imputation, a regression model for continuous variable imputation, and a classification model for binary variable imputation" and "training the selected imputation model using feature values corresponding to filled dataset indices of populated values of the feature having the lowest count of the missing feature values" as recited or analogously recited in amended independent Claims 1, 13, and 19.
The Examiner respectfully disagrees. First, the Applicant’s argument regarding the limitation "selecting an imputation model corresponding to the determined data type from a group of imputation models comprising a deep learning model for categorical variable imputation, a regression model for continuous variable imputation, and a classification model for binary variable imputation" is moot because the new ground of rejection relies on newly introduced references applied to the prior rejection of record. Second, Resnick does indeed teach the limitation "training the selected imputation model using feature values corresponding to filled dataset indices of populated values of the feature having the lowest count of the missing feature values" in paragraph 0028, “existing fields (e.g., fields that are not empty) for each feature may be used (using feature values corresponding to filled dataset indices of populated values) as the outcome variable and the rest of the features could be used as the input variables. Such a machine learning model would then be able to predict what data is missing for each missing field for each case of the feature having the lowest count of the missing feature values”, and paragraph 0031, “Updating 170 the imputation model (training the selected imputation model) may include completely retraining the imputation model based on the updated data in the computer-based reasoning model in similar manner to what is described elsewhere herein”. For further clarification, in paragraph 0024, reference Resnick discloses, “Determining 130 imputation order, may then include determining 130 the cases with the fewest (or, in some embodiments, most) missing features can then have the missing features imputed first”.
Therefore, the 35 USC 103 rejection is maintained.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-3 and 5-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Claims 1-3 and 5-12 are directed to a method. Claims 13-18 are directed to a system. Claims 19-20 are directed to a non-transitory computer-readable medium. Therefore, all claims are directed to one of the four statutory categories of patent eligible subject matter.
Claim 1
Step 2A Prong 1:
Claim 1 recites:
“populating the one or more missing features in the dataset using the received procedure instructions;” Populating the one or more missing features in the dataset using the received procedure instructions is an action that can be performed mentally with the aid of pen and paper, and is therefore a mental process.
“until the dataset is filled, recursively imputing missing values in the dataset by: sorting the dataset by a count of the missing feature values for the plurality of features;” Recursively imputing missing values in the dataset by: sorting the dataset by a count of the missing feature values for the plurality of features is an action that can be performed mentally with the aid of pen and paper, and is therefore a mental process.
“determining a data type of the feature in the sorted dataset having a lowest count of missing feature values;” Determining a data type of the feature in the sorted dataset having a lowest count of missing feature values is an action that can be performed mentally with the aid of pen and paper, and is therefore a mental process.
“selecting an imputation model corresponding to the determined data type [from a group of imputation models comprising a deep learning model for categorical variable imputation, a regression model for continuous variable imputation, and a classification model for binary variable imputation];” Selecting, from one or more models, an imputation model corresponding to the determined data type is an action that can be performed mentally with the aid of pen and paper, and is therefore a mental process.
“predicting, [using the trained imputation model], and based on the feature values corresponding to filled dataset indices, missing values of the feature having the lowest count of the missing feature values;” Predicting, based on the feature values corresponding to filled dataset indices, missing values of the feature having the lowest count of the missing feature values is an action that can be performed mentally with the aid of pen and paper, and is therefore a mental process.
“imputing the predicted missing values into the dataset;” Imputing the predicted missing values into the dataset is an action that can be performed mentally with the aid of pen and paper, and is therefore a mental process.
Step 2A Prong Two
This judicial exception is not integrated into a practical application because the additional elements are as follows:
“A computer-implemented method for imputing missing values in a dataset using machine learning models;” Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“receiving a dataset having a plurality of features with missing feature values;” Mere data gathering recited at a high level of generality, and thus are insignificant extra-solution activity (MPEP 2106.05(g)).
“when not all of the features in the dataset have fully populated feature values: receiving, from a user, procedure instructions for populating missing values for a feature of the plurality of features having a first lowest count of the missing feature values;” Mere data gathering recited at a high level of generality, and thus are insignificant extra-solution activity (MPEP 2106.05(g)).
“from a group of imputation models comprising a deep learning model for categorical variable imputation, a regression model for continuous variable imputation, and a classification model for binary variable imputation;” The limitation amounts to merely indicating a field of use or technological environment in which to apply a judicial exception. This does not amount to significantly more than the exception itself (MPEP 2106.05(h)).
“training the selected imputation model using feature values corresponding to filled dataset indices of populated values of the feature having the lowest count of the missing feature values;” The limitation amounts to merely indicating a field of use or technological environment in which to apply a judicial exception. This does not amount to significantly more than the exception itself (MPEP 2106.05(h)).
“using the trained imputation model;” Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“outputting a filled dataset;” Insignificant extra-solution as the limitation amounts to necessary data outputting (MPEP 2106.05(g)(3)).
Step 2B:
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements are as follows:
“A computer-implemented method for imputing missing values in a dataset using machine learning models;” Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (MPEP 2106.05(f)) which cannot provide an inventive concept.
“receiving a dataset having a plurality of features with missing feature values;” Mere data gathering recited at a high level of generality, and thus are insignificant extra-solution activity. See MPEP 2106.05(g). The additional element of “receiving” does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of receiving steps amounts to no more than mere data gathering. This element amounts to receiving data over a network and are well-understood, routine, conventional activity. See MPEP 2106.05(d), subsection II (i). This cannot provide an inventive concept.
“when not all of the features in the dataset have fully populated feature values: receiving, from a user, procedure instructions for populating missing values for a feature of the plurality of features having a first lowest count of the missing feature values;” Mere data gathering recited at a high level of generality, and thus are insignificant extra-solution activity. See MPEP 2106.05(g). The additional element of “receiving” does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of receiving steps amounts to no more than mere data gathering. This element amounts to receiving data over a network and are well-understood, routine, conventional activity. See MPEP 2106.05(d), subsection II (i). This cannot provide an inventive concept.
“from a group of imputation models comprising a deep learning model for categorical variable imputation, a regression model for continuous variable imputation, and a classification model for binary variable imputation;” The limitation amounts to merely indicating a field of use or technological environment in which to apply a judicial exception. This does not amount to significantly more than the exception itself (MPEP 2106.05(h)) and cannot provide an inventive concept.
“training the selected imputation model using feature values corresponding to filled dataset indices of populated values of the feature having the lowest count of the missing feature values;” The limitation amounts to merely indicating a field of use or technological environment in which to apply a judicial exception. This does not amount to significantly more than the exception itself (MPEP 2106.05(h)) and cannot provide an inventive concept.
“using the trained imputation model;” Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (MPEP 2106.05(f)) which cannot provide an inventive concept.
“outputting a filled dataset;” Insignificant extra-solution as the limitation amounts to necessary data outputting (MPEP 2106.05(g)(3)). This falls under Well-Understood, Routine, Conventional activity -see MPEP 2106.05(d)(II)(vi).
Even when considered in combination, these additional elements represent mere instructions to apply an exception and therefore do not provide an inventive concept. The claim is ineligible.
Claim 2
Step 2A Prong Two
This judicial exception is not integrated into a practical application because the additional elements are as follows:
“wherein the receiving the procedure instructions comprises receiving mean instructions, median instructions, mode instructions, or a user-supplied value to populate one or more missing features in the dataset;” Mere data gathering recited at a high level of generality, and thus are insignificant extra-solution activity (MPEP 2106.05(g)).
Step 2B:
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements are as follows:
“wherein the receiving the procedure instructions comprises receiving mean instructions, median instructions, mode instructions, or a user-supplied value to populate one or more missing features in the dataset;” Mere data gathering recited at a high level of generality, and thus are insignificant extra-solution activity. See MPEP 2106.05(g). The additional element of “receiving” does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of receiving steps amounts to no more than mere data gathering. This element amounts to receiving data over a network and are well-understood, routine, conventional activity. See MPEP 2106.05(d), subsection II (i). This cannot provide an inventive concept.
Even when considered in combination, these additional elements represent mere instructions to apply an exception and therefore do not provide an inventive concept. The claim is ineligible.
Claim 3
Step 2A Prong Two
This judicial exception is not integrated into a practical application because the additional elements are as follows:
“wherein the data type comprises a category, a continuous variable, or a binary value;” The limitation amounts to merely indicating a field of use or technological environment in which to apply a judicial exception. This does not amount to significantly more than the exception itself (MPEP 2106.05(h)).
Step 2B:
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements are as follows:
“wherein the data type comprises a category, a continuous variable, or a binary value;” The limitation amounts to merely indicating a field of use or technological environment in which to apply a judicial exception. This does not amount to significantly more than the exception itself (MPEP 2106.05(h)) and cannot provide an inventive concept.
Even when considered in combination, these additional elements represent mere instructions to apply an exception and therefore do not provide an inventive concept. The claim is ineligible.
Claim 5
Step 2A Prong 1:
Claim 5 recites:
“wherein the dataset is copied to enable imputing missing values into a copied dataset without modifying an original dataset;” Copying the dataset to enable imputing missing values into a copied dataset without modifying an original dataset is an action that can be performed mentally with the aid of pen and paper, and is therefore a mental process.
Step 2A Prong Two and Step 2B:
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception under step 2B. Thus, the judicial exception is not integrated into a practical application (see MPEP 2106.04(d) I.), failing step 2A prong 2. The claim is ineligible.
Claim 6
Step 2A Prong Two
This judicial exception is not integrated into a practical application because the additional elements are as follows:
“wherein one or more models are received from the user;” Mere data gathering recited at a high level of generality, and thus are insignificant extra-solution activity (MPEP 2106.05(g)).
Step 2B:
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements are as follows:
“wherein one or more models are received from the user;” Mere data gathering recited at a high level of generality, and thus are insignificant extra-solution activity. See MPEP 2106.05(g). The additional element of “receiving” does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of receiving steps amounts to no more than mere data gathering. This element amounts to receiving data over a network and are well-understood, routine, conventional activity. See MPEP 2106.05(d), subsection II (i). This cannot provide an inventive concept.
Even when considered in combination, these additional elements represent mere instructions to apply an exception and therefore do not provide an inventive concept. The claim is ineligible.
Claim 7
Step 2A Prong 1:
Claim 7 recites:
“wherein recursively imputing missing values in the dataset further comprises one or more of: identifying dataset indices for a feature having a lowest count of the missing feature values;” Identifying dataset indices for a feature having a lowest count of the missing feature values is an action that can be performed mentally with the aid of pen and paper, and is therefore a mental process.
“identifying the filled dataset indices for populated values of the feature having the lowest count of the missing feature values;” Identifying the filled dataset indices for populated values of the feature having the lowest count of the missing feature values is an action that can be performed mentally with the aid of pen and paper, and is therefore a mental process.
Step 2A Prong Two and Step 2B:
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception under step 2B. Thus, the judicial exception is not integrated into a practical application (see MPEP 2106.04(d) I.), failing step 2A prong 2. The claim is ineligible.
Claim 8
Step 2A Prong 1:
Claim 8 recites:
“wherein identifying dataset indices comprises identifying row indices;” Identifying row indices is an action that can be performed mentally with the aid of pen and paper, and is therefore a mental process.
Step 2A Prong Two and Step 2B:
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception under step 2B. Thus, the judicial exception is not integrated into a practical application (see MPEP 2106.04(d) I.), failing step 2A prong 2. The claim is ineligible.
Claim 9
Step 2A Prong 1:
Claim 9 recites:
“wherein sorting the dataset by a count of the missing feature values for the plurality of features comprises sorting the dataset in ascending order of the count of the missing feature values;” Sorting the dataset in ascending order of the count of the missing feature values is an action that can be performed mentally with the aid of pen and paper, and is therefore a mental process.
“wherein recursively imputing missing values in the dataset is performed corresponding to the ascending order of the count of the missing feature values;” Recursively imputing missing values in the dataset performed corresponding to the ascending order of the count of the missing feature values is an action that can be performed mentally with the aid of pen and paper, and is therefore a mental process.
Step 2A Prong Two and Step 2B:
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception under step 2B. Thus, the judicial exception is not integrated into a practical application (see MPEP 2106.04(d) I.), failing step 2A prong 2. The claim is ineligible.
Claim 10
Step 2A Prong Two
This judicial exception is not integrated into a practical application because the additional elements are as follows:
“wherein the dataset comprises a tabular format;” The limitation amounts to merely indicating a field of use or technological environment in which to apply a judicial exception. This does not amount to significantly more than the exception itself (MPEP 2106.05(h)).
Step 2B:
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements are as follows:
“wherein the dataset comprises a tabular format;” The limitation amounts to merely indicating a field of use or technological environment in which to apply a judicial exception. This does not amount to significantly more than the exception itself (MPEP 2106.05(h)) and cannot provide an inventive concept.
Even when considered in combination, these additional elements represent mere instructions to apply an exception and therefore do not provide an inventive concept. The claim is ineligible.
Claim 11
Step 2A Prong Two
This judicial exception is not integrated into a practical application because the additional elements are as follows:
“wherein the training comprises using populated rows of feature having the lowest count of the missing feature values as targets to train the selected imputation model;” The limitation amounts to merely indicating a field of use or technological environment in which to apply a judicial exception. This does not amount to significantly more than the exception itself (MPEP 2106.05(h)).
Step 2B:
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements are as follows:
“wherein the training comprises using populated rows of feature having the lowest count of the missing feature values as targets to train the selected imputation model;” The limitation amounts to merely indicating a field of use or technological environment in which to apply a judicial exception. This does not amount to significantly more than the exception itself (MPEP 2106.05(h)) and cannot provide an inventive concept.
Even when considered in combination, these additional elements represent mere instructions to apply an exception and therefore do not provide an inventive concept. The claim is ineligible.
Claim 12
Step 2A Prong Two
This judicial exception is not integrated into a practical application because the additional elements are as follows:
“outputting a machine learning pipeline used for imputing the predicted missing values into the dataset;” Insignificant extra-solution as the limitation amounts to necessary data outputting (MPEP 2106.05(g)(3)).
Step 2B:
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements are as follows:
“outputting a machine learning pipeline used for imputing the predicted missing values into the dataset;” Insignificant extra-solution as the limitation amounts to necessary data outputting (MPEP 2106.05(g)(3)). This falls under Well-Understood, Routine, Conventional activity -see MPEP 2106.05(d)(II)(vi).
Even when considered in combination, these additional elements represent mere instructions to apply an exception and therefore do not provide an inventive concept. The claim is ineligible.
Claims 14 and 16-18 are system claims that recite identical limitations to method claims 2, 7, 9, and 11, respectively. Therefore, claims 14 and 16-18 are rejected using the same rationale as claims 2, 7, 9, and 11.
Claim 13
Step 2A Prong 1:
Claim 13 recites:
“populate the one or more missing features in the dataset using the received procedure instructions;” Populating the one or more missing features in the dataset using the received procedure instructions is an action that can be performed mentally with the aid of pen and paper, and is therefore a mental process.
“until the dataset is filled, recursively impute missing values in the dataset by: sorting the dataset by a count of the missing feature values for the plurality of features;” Recursively imputing missing values in the dataset by: sorting the dataset by a count of the missing feature values for the plurality of features is an action that can be performed mentally with the aid of pen and paper, and is therefore a mental process.
“determining a data type of the feature in the sorted dataset having a lowest count of missing feature values;” Determining a data type of the feature in the sorted dataset having a lowest count of missing feature values is an action that can be performed mentally with the aid of pen and paper, and is therefore a mental process.
“selecting an imputation model corresponding to the determined data type [from a group of imputation models comprising a deep learning model for categorical variable imputation, a regression model for continuous variable imputation, and a classification model for binary variable imputation];” Selecting, from one or more models, an imputation model corresponding to the determined data type is an action that can be performed mentally with the aid of pen and paper, and is therefore a mental process.
“predicting, [using the trained imputation model], and based on the feature values corresponding to filled dataset indices, missing values of the feature having the lowest count of the missing feature values;” Predicting, based on the feature values corresponding to filled dataset indices, missing values of the feature having the lowest count of the missing feature values is an action that can be performed mentally with the aid of pen and paper, and is therefore a mental process.
“imputing the predicted missing values into the dataset;” Imputing the predicted missing values into the dataset is an action that can be performed mentally with the aid of pen and paper, and is therefore a mental process.
Step 2A Prong Two
This judicial exception is not integrated into a practical application because the additional elements are as follows:
“A system, comprising: a processor and memory comprising instructions;” Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“receive a dataset having a plurality of features with missing feature values;” Mere data gathering recited at a high level of generality, and thus are insignificant extra-solution activity (MPEP 2106.05(g)).
“when not all of the features in the dataset have fully populated feature values: receive, from a user, procedure instructions for populating missing values for a feature of the plurality of features having a first lowest count of the missing feature values;” Mere data gathering recited at a high level of generality, and thus are insignificant extra-solution activity (MPEP 2106.05(g)).
“from a group of imputation models comprising a deep learning model for categorical variable imputation, a regression model for continuous variable imputation, and a classification model for binary variable imputation;” The limitation amounts to merely indicating a field of use or technological environment in which to apply a judicial exception. This does not amount to significantly more than the exception itself (MPEP 2106.05(h)).
“training the selected imputation model using feature values corresponding to filled dataset indices of populated values of the feature having the lowest count of the missing feature values;” The limitation amounts to merely indicating a field of use or technological environment in which to apply a judicial exception. This does not amount to significantly more than the exception itself (MPEP 2106.05(h)).
“using the trained imputation model;” Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“outputting a filled dataset;” Insignificant extra-solution as the limitation amounts to necessary data outputting (MPEP 2106.05(g)(3)).
Step 2B:
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements are as follows:
“A system, comprising: a processor and memory comprising instructions;” Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (MPEP 2106.05(f)) which cannot provide an inventive concept.
“receive a dataset having a plurality of features with missing feature values;” Mere data gathering recited at a high level of generality, and thus are insignificant extra-solution activity. See MPEP 2106.05(g). The additional element of “receiving” does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of receiving steps amounts to no more than mere data gathering. This element amounts to receiving data over a network and are well-understood, routine, conventional activity. See MPEP 2106.05(d), subsection II (i). This cannot provide an inventive concept.
“when not all of the features in the dataset have fully populated feature values: receive, from a user, procedure instructions for populating missing values for a feature of the plurality of features having a first lowest count of the missing feature values;” Mere data gathering recited at a high level of generality, and thus are insignificant extra-solution activity. See MPEP 2106.05(g). The additional element of “receiving” does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of receiving steps amounts to no more than mere data gathering. This element amounts to receiving data over a network and are well-understood, routine, conventional activity. See MPEP 2106.05(d), subsection II (i). This cannot provide an inventive concept.
“from a group of imputation models comprising a deep learning model for categorical variable imputation, a regression model for continuous variable imputation, and a classification model for binary variable imputation;” The limitation amounts to merely indicating a field of use or technological environment in which to apply a judicial exception. This does not amount to significantly more than the exception itself (MPEP 2106.05(h)) and cannot provide an inventive concept.
“training the selected imputation model using feature values corresponding to filled dataset indices of populated values of the feature having the lowest count of the missing feature values;” The limitation amounts to merely indicating a field of use or technological environment in which to apply a judicial exception. This does not amount to significantly more than the exception itself (MPEP 2106.05(h)) and cannot provide an inventive concept.
“using the trained imputation model;” Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (MPEP 2106.05(f)) which cannot provide an inventive concept.
“outputting a filled dataset;” Insignificant extra-solution as the limitation amounts to necessary data outputting (MPEP 2106.05(g)(3)). This falls under Well-Understood, Routine, Conventional activity -see MPEP 2106.05(d)(II)(vi).
Even when considered in combination, these additional elements represent mere instructions to apply an exception and therefore do not provide an inventive concept. The claim is ineligible.
Claim 15
Step 2A Prong Two
This judicial exception is not integrated into a practical application because the additional elements are as follows:
“wherein the data type comprises a category, a continuous variable, or a binary value;” The limitation amounts to merely indicating a field of use or technological environment in which to apply a judicial exception. This does not amount to significantly more than the exception itself (MPEP 2106.05(h)).
Step 2B:
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements are as follows:
“wherein the data type comprises a category, a continuous variable, or a binary value;” The limitation amounts to merely indicating a field of use or technological environment in which to apply a judicial exception. This does not amount to significantly more than the exception itself (MPEP 2106.05(h)) and cannot provide an inventive concept.
Even when considered in combination, these additional elements represent mere instructions to apply an exception and therefore do not provide an inventive concept. The claim is ineligible.
Claim 19
Step 2A Prong 1:
Claim 19 recites:
“sorting the dataset by a count of missing feature values for a plurality of features in the dataset;” Sorting the dataset by a count of missing feature values for a plurality of features in the dataset is an action that can be performed mentally with the aid of pen and paper, and is therefore a mental process.
“determining a data type of the feature in the sorted dataset having a lowest count of missing feature values;” Determining a data type of the feature in the sorted dataset having a lowest count of missing feature values is an action that can be performed mentally with the aid of pen and paper, and is therefore a mental process.
“selecting an imputation model corresponding to the determined data type [from a group of imputation models comprising a deep learning model for categorical variable imputation, a regression model for continuous variable imputation, and a classification model for binary variable imputation];” Selecting, from one or more models, an imputation model corresponding to the determined data type is an action that can be performed mentally with the aid of pen and paper, and is therefore a mental process.
“predicting, [using the trained imputation model], and based on the feature values corresponding to filled dataset indices, missing values of the feature having the lowest count of the missing feature values;” Predicting, based on the feature values corresponding to filled dataset indices, missing values of the feature having the lowest count of the missing feature values is an action that can be performed mentally with the aid of pen and paper, and is therefore a mental process.
“imputing the predicted missing values into the dataset until the dataset is filled;” Imputing the predicted missing values into the dataset is an action that can be performed mentally with the aid of pen and paper, and is therefore a mental process.
Step 2A Prong Two
This judicial exception is not integrated into a practical application because the additional elements are as follows:
“A non-transitory computer-readable medium comprising a set of instructions that, in response to being executed by a processor circuit, cause the processor circuit to perform a method of recursively imputing missing values in a received dataset by;” Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“from a group of imputation models comprising a deep learning model for categorical variable imputation, a regression model for continuous variable imputation, and a classification model for binary variable imputation;” The limitation amounts to merely indicating a field of use or technological environment in which to apply a judicial exception. This does not amount to significantly more than the exception itself (MPEP 2106.05(h)).
“training the selected imputation model using feature values corresponding to filled dataset indices of populated values of the feature having the lowest count of the missing feature values;” The limitation amounts to merely indicating a field of use or technological environment in which to apply a judicial exception. This does not amount to significantly more than the exception itself (MPEP 2106.05(h)).
“using the trained imputation model;” Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (MPEP 2106.05(f)).
“outputting a filled dataset;” Insignificant extra-solution as the limitation amounts to necessary data outputting (MPEP 2106.05(g)(3)).
Step 2B:
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements are as follows:
“A non-transitory computer-readable medium comprising a set of instructions that, in response to being executed by a processor circuit, cause the processor circuit to perform a method of recursively imputing missing values in a received dataset by;” Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (MPEP 2106.05(f)) which cannot provide an inventive concept.
“from a group of imputation models comprising a deep learning model for categorical variable imputation, a regression model for continuous variable imputation, and a classification model for binary variable imputation;” The limitation amounts to merely indicating a field of use or technological environment in which to apply a judicial exception. This does not amount to significantly more than the exception itself (MPEP 2106.05(h)) and cannot provide an inventive concept.
“training the selected imputation model using feature values corresponding to filled dataset indices of populated values of the feature having the lowest count of the missing feature values;” The limitation amounts to merely indicating a field of use or technological environment in which to apply a judicial exception. This does not amount to significantly more than the exception itself (MPEP 2106.05(h)) and cannot provide an inventive concept.
“using the trained imputation model;” Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (MPEP 2106.05(f)) which cannot provide an inventive concept.
“outputting a filled dataset;” Insignificant extra-solution as the limitation amounts to necessary data outputting (MPEP 2106.05(g)(3)). This falls under Well-Understood, Routine, Conventional activity -see MPEP 2106.05(d)(II)(vi).
Even when considered in combination, these additional elements represent mere instructions to apply an exception and therefore do not provide an inventive concept. The claim is ineligible.
Claim 20
Step 2A Prong Two
This judicial exception is not integrated into a practical application because the additional elements are as follows:
“receiving procedure instructions comprising mean instructions, median instructions, mode instructions, or a user-supplied value to populate one or more missing features in the dataset;” Mere data gathering recited at a high level of generality, and thus are insignificant extra-solution activity (MPEP 2106.05(g)).
Step 2B:
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements are as follows:
“receiving procedure instructions comprising mean instructions, median instructions, mode instructions, or a user-supplied value to populate one or more missing features in the dataset;” Mere data gathering recited at a high level of generality, and thus are insignificant extra-solution activity. See MPEP 2106.05(g). The additional element of “receiving” does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of receiving steps amounts to no more than mere data gathering. This element amounts to receiving data over a network and are well-understood, routine, conventional activity. See MPEP 2106.05(d), subsection II (i). This cannot provide an inventive concept.
Even when considered in combination, these additional elements represent mere instructions to apply an exception and therefore do not provide an inventive concept. The claim is ineligible.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1-3, 7-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Resnick et al. (US 20210406707 A1), hereinafter Resnick, in view of Chu et al. (US 20130226842 A1), hereinafter Chu and Lin et al. (Using Deep Learning to Predict Mortality in Myocardial Infarction Patients, Published May 2022), hereinafter Lin.
Regarding claim 1, Resnick teaches,
A computer-implemented method for imputing missing values in a dataset using machine learning models, the method comprising: receiving a dataset having a plurality of features with missing feature values [Abstract, Techniques are provided for imputation in computer-based reasoning systems; Para 0096, Receiving 420 current context may include receiving the context data needed for a determination to be made using the computer-based reasoning model; Para 0100, detecting gaps in the training data and/or vehicle control rules];
when not all of the features in the dataset have fully populated feature values: receiving, from a user, procedure instructions for populating missing values for a feature of the plurality of features having a first lowest count of the missing feature values; and populating the one or more missing features in the dataset using the received procedure instructions [Para 0026, determining 130 which cases to impute data based on… the order in which to impute data may include determining… the fewest number of features to impute (e.g., if there is just one case with a single field to impute, that case may have its data imputed first); Para 0100, detecting gaps in the training data and/or vehicle control rules and indicating those during operation of the vehicle (for example, via prompt and/or spoken or graphical user interface) or offline (for example, in a report, on a graphical display, etc.) to indicate what additional training is needed… when the computer-based reasoning system does not find context “close enough” to the current context to make a confident decision on an action to take, it may indicate this and suggest that an operator might take manual control of the vehicle, and that operation of the vehicle may provide additional context and action data for the computer-based reasoning system];
recursively imputing missing values in the dataset by: sorting the dataset by a count of the missing feature values for the plurality of features [Para 0026, the process 100 will proceed by modifying 150 that particular case, updating 170 the imputation model, and then recomputing… imputation order information; Para 0031, Updating 170 the imputation model may include completely retraining the imputation model based on the updated data in the computer-based reasoning model in similar manner to what is described elsewhere herein];
determining a data type of the feature in the sorted dataset having a lowest count of missing feature values; selecting an imputation model corresponding to the determined data type from a group of imputation models comprising categorical variable imputation (Para 0151, k nearest neighbors), a regression model for continuous variable imputation (Para 0151, k nearest neighbors) [Para 0026, determining 130 which cases to impute data based on… the order in which to impute data may include determining… the fewest number of features to impute (e.g., if there is just one case with a single field to impute, that case may have its data imputed first); Para 0028, After determining 130 which cases to impute data and/or the order in which to impute data, the imputed data is determined 140 based on the case with the missing data and the imputation model. The imputation model may be any appropriate statistical or other machine learning model; Para 0151, processes 100 and/or 400 may determine (e.g., in response to a request) the search result (e.g., k nearest neighbors, most probable cases in gaussian process regression, etc.) in the computer-based reasoning model for use in the financial system computer-based reasoning model. Based on those search results, the process can cause control of a financial system computer-based reasoning system using process 400… if the data elements are related to financial system actions, then the financial system computer-based reasoning model trained on that data will control the financial system… The financial system computer-based reasoning model is then used to determine 430 an action to take. The action is then performed by the control system (e.g., caused by the financial system computer-based reasoning system)… the financial system computer-based reasoning model may be used to assess financial system decisions, predict outcomes, etc… the chosen action(s) are then performed by a control system];
training the selected imputation model using feature values corresponding to filled dataset indices of populated values of the feature having the lowest count of the missing feature values; predicting, using the trained imputation model, and based on the feature values corresponding to filled dataset indices, missing values of the feature having the lowest count of the missing feature values and imputing the predicted missing values into the dataset [Para 0024, Determining 130 imputation order, may then include determining 130 the cases with the fewest (or, in some embodiments, most) missing features can then have the missing features imputed first; Para 0028, existing fields (e.g., fields that are not empty) for each feature may be used as the outcome variable and the rest of the features could be used as the input variables. Such a machine learning model would then be able to predict what data is missing for each missing field for each case; Para 0031, Updating 170 the imputation model may include completely retraining the imputation model based on the updated data in the computer-based reasoning model in similar manner to what is described elsewhere herein];
Resnick does not teach until the dataset is filled, imputing missing values; a deep learning model and a classification model for binary variable imputation; outputting a filled dataset.
Chu teaches,
until the dataset is filled, imputing missing values [Para 0010, The missing value is imputed for each of the one or more predictor variables using the data from the one or more data sources and one or more built imputation models to generate a completed data set];
outputting a filled dataset [Para 0032, the missing value imputation system 110 imputes missing values and outputs completed data 210].
Chu is analogous to the claimed invention as they both relate to data completion. Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Resnick’s teachings to incorporate the teachings of Chu and provide outputting a filled dataset in order to allow a machine learning system to make predictions using sparse datasets.
Resnick-Chu does not teach a deep learning model and a classification model for binary variable imputation.
Lin teaches,
a deep learning model and a classification model for binary variable imputation [Sect I, para 4, we aim to improve the prediction of mortality in myocardial infarction patients by experimenting with various data processing methods and deep learning algorithms; Sect III, para 8, In the experiment, the data with many missing values were deleted, and the data with missing values less than 30% were filled by imputation. The imputation was used as the primary method to avoid discarding data including "Mean Imputation", "K-Nearest Neighbors", and "Multiple Imputation"; Sec III, para 11, By the way, the unbalanced data also has a great impact on the model prediction. When training binary data, it is often found that the “positive” and “negative” samples are not equal];
Lin is analogous to the claimed invention as they both relate to data imputation. Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Resnick’s teachings to incorporate the teachings of Lin and provide a deep learning model and a classification model for binary variable imputation in order to [Lin, Sect I, para 4 and Sect III, para 8] improve model prediction and avoid discarding data.
Regarding claim 2, Resnick-Chu-Lin teach the limitations of claim 1.
Resnick further teaches,
wherein the receiving the procedure instructions comprises receiving mean instructions, median instructions, mode instructions, or a user-supplied value to populate one or more missing features in the dataset [Para 0123, the training data could be what a particular user does at certain times of day and/or in particular sequences; Para 0158, Data that represents neither a threat nor anomalous behavior (e.g., non-malicious access attempts, non-malicious emails, etc.) may also be used to train the computer-based reasoning model… when a new… user… is ready for assessment, the features associated with that new… user… may be used as input in the trained cybersecurity computer-based reasoning system. The cybersecurity computer-based reasoning system may then determine the probability or likelihood that the user… is or represents a threat or anomalous behavior].
Regarding claim 3, Resnick-Chu-Lin teach the limitations of claim 1.
Resnick further teaches,
wherein the data type comprises a category, a continuous variable [Para 0022, the word “feature” is being used to describe a data field as across all or some of the cases in the computer-based reasoning model. The word “field,” in this context, is being used to describe the value of an individual case for a particular feature. For example, a feature for a theoretical computer-based reasoning model for self-driving cars may be “speed”. The field value for a particular case for the feature of speed may be the actual speed, such as thirty-five miles per hour], or a binary value.
Regarding claim 7, Resnick-Chu-Lin teach the limitations of claim 1.
Resnick further teaches,
wherein recursively imputing missing values in the dataset further comprises one or more of: identifying dataset indices for a feature having a lowest count of the missing feature values [Para 0020, a separate data structure can be used to store indications of which fields are missing from cases; Para 0024, Determining 130 imputation order, may then include determining 130 the cases with the fewest… missing features can then have the missing features imputed first. For example, cases with two missing features may have the missing data imputed before cases with three missing features, and so on]; and identifying the filled dataset indices for populated values of the feature having the lowest count of the missing feature values.
Regarding claim 8, Resnick-Chu-Lin teach the limitations of claim 1.
Resnick further teaches,
wherein identifying dataset indices comprises identifying row indices [Para 0020, a separate data structure can be used to store indications of which fields are missing from cases].
PNG
media_image1.png
271
540
media_image1.png
Greyscale
Regarding claim 9, Resnick-Chu-Lin teach the limitations of claim 1.
Resnick further teaches,
wherein sorting the dataset by a count of the missing feature values for the plurality of features comprises sorting the dataset in ascending order of the count of the missing feature values, and wherein recursively imputing missing values in the dataset is performed corresponding to the ascending order of the count of the missing feature values [Para 0026, determining 130 which cases to impute data based on… the order in which to impute data may include determining… the fewest number of features to impute (e.g., if there is just one case with a single field to impute, that case may have its data imputed first)… the process 100 will proceed by modifying 150 that particular case, updating 170 the imputation model, and then recomputing… imputation order information].
Regarding claim 10, Resnick-Chu-Lin teach the limitations of claim 1.
Resnick further teaches,
wherein the dataset comprises a tabular format [Para 0012, FIG. 5 is a table depicting missing fields for cases in a computer-based reasoning model; Para 0020, FIG. 5 depicts a set of cases 520-523, each with an indication of what the values for each of the features 511-513].
PNG
media_image1.png
271
540
media_image1.png
Greyscale
Regarding claim 11, Resnick-Chu-Lin teach the limitations of claim 1.
Resnick further teaches,
wherein the training comprises using populated rows of feature having the lowest count of the missing feature values as targets to train the selected imputation model [Para 0024, Determining 130 imputation order, may then include determining 130 the cases with the fewest… missing features can then have the missing features imputed first. For example, cases with two missing features may have the missing data imputed before cases with three missing features, and so on; Para 0028, existing fields (e.g., fields that are not empty) for each feature may be used as the outcome variable and the rest of the features could be used as the input variables. Such a machine learning model would then be able to predict what data is missing for each missing field for each case; Para 0031, Updating 170 the imputation model may include completely retraining the imputation model based on the updated data in the computer-based reasoning model in similar manner to what is described elsewhere herein].
Regarding claim 12, Resnick-Chu-Lin teach the limitations of claim 1.
Chu further teaches,
outputting a machine learning pipeline used for imputing the predicted missing values into the dataset [Para 0032, the missing value imputation system 110 imputes missing values and outputs completed data 210].
Chu is analogous to the claimed invention as they both relate to data completion. Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Resnick’s teachings to incorporate the teachings of Chu and provide outputting a filled dataset in order to allow a machine learning system to make predictions using sparse datasets.
Claims 14 and 16-18 are system claims that recite identical limitations to method claims 2, 7, 9, and 11, respectively. Therefore, claims 14 and 16-18 are rejected using the same rationale as claims 2, 7, 9, and 11.
Regarding claim 13, Resnick teaches,
A system [Abstract, Techniques are provided for imputation in computer-based reasoning systems], comprising: a processor and memory comprising instructions that when executed by the processor [Para 0179, Computer system 300 also includes a main memory 306, such as a random access memory (RAM) or other dynamic storage device, coupled to bus 302 for storing information and instructions to be executed by processor 304] cause the processor to:
receive a dataset having a plurality of features with missing feature values [Abstract, Techniques are provided for imputation in computer-based reasoning systems; Para 0096, Receiving 420 current context may include receiving the context data needed for a determination to be made using the computer-based reasoning model; Para 0100, detecting gaps in the training data and/or vehicle control rules];
when not all of the features in the dataset have fully populated feature values: receive procedure instructions for populating missing values for a feature of the plurality of features having a first lowest count of the missing feature values; and populate the one or more missing features in the dataset using the received procedure instructions [Para 0026, determining 130 which cases to impute data based on… the order in which to impute data may include determining… the fewest number of features to impute (e.g., if there is just one case with a single field to impute, that case may have its data imputed first); Para 0100, detecting gaps in the training data and/or vehicle control rules and indicating those during operation of the vehicle (for example, via prompt and/or spoken or graphical user interface) or offline (for example, in a report, on a graphical display, etc.) to indicate what additional training is needed… when the computer-based reasoning system does not find context “close enough” to the current context to make a confident decision on an action to take, it may indicate this and suggest that an operator might take manual control of the vehicle, and that operation of the vehicle may provide additional context and action data for the computer-based reasoning system];
recursively impute missing values in the dataset by: sorting the dataset by a count of the missing feature values for the plurality of features [Para 0026, the process 100 will proceed by modifying 150 that particular case, updating 170 the imputation model, and then recomputing… imputation order information; Para 0031, Updating 170 the imputation model may include completely retraining the imputation model based on the updated data in the computer-based reasoning model in similar manner to what is described elsewhere herein];
determining a data type of the feature in the sorted dataset having a lowest count of missing feature values; selecting an imputation model corresponding to the determined data type from a group of imputation models comprising categorical variable imputation (Para 0151, k nearest neighbors), a regression model for continuous variable imputation (Para 0151, k nearest neighbors) [Para 0026, determining 130 which cases to impute data based on… the order in which to impute data may include determining… the fewest number of features to impute (e.g., if there is just one case with a single field to impute, that case may have its data imputed first); Para 0028, After determining 130 which cases to impute data and/or the order in which to impute data, the imputed data is determined 140 based on the case with the missing data and the imputation model. The imputation model may be any appropriate statistical or other machine learning model; Para 0151, processes 100 and/or 400 may determine (e.g., in response to a request) the search result (e.g., k nearest neighbors, most probable cases in gaussian process regression, etc.) in the computer-based reasoning model for use in the financial system computer-based reasoning model. Based on those search results, the process can cause control of a financial system computer-based reasoning system using process 400… if the data elements are related to financial system actions, then the financial system computer-based reasoning model trained on that data will control the financial system… The financial system computer-based reasoning model is then used to determine 430 an action to take. The action is then performed by the control system (e.g., caused by the financial system computer-based reasoning system)… the financial system computer-based reasoning model may be used to assess financial system decisions, predict outcomes, etc… the chosen action(s) are then performed by a control system];
training the selected imputation model using feature values corresponding to filled dataset indices of populated values of the feature having the lowest count of the missing feature values; predicting, using the trained imputation model, and based on the feature values corresponding to filled dataset indices, missing values of the feature having the lowest count of the missing feature values; and imputing the predicted missing values into the dataset [Para 0024, Determining 130 imputation order, may then include determining 130 the cases with the fewest (or, in some embodiments, most) missing features can then have the missing features imputed first; Para 0028, existing fields (e.g., fields that are not empty) for each feature may be used as the outcome variable and the rest of the features could be used as the input variables. Such a machine learning model would then be able to predict what data is missing for each missing field for each case; Para 0031, Updating 170 the imputation model may include completely retraining the imputation model based on the updated data in the computer-based reasoning model in similar manner to what is described elsewhere herein];
Resnick does not teach until the dataset is filled, imputing missing values; a deep learning model and a classification model for binary variable imputation; outputting a filled dataset.
Chu teaches,
until the dataset is filled, imputing missing values [Para 0010, The missing value is imputed for each of the one or more predictor variables using the data from the one or more data sources and one or more built imputation models to generate a completed data set];
outputting a filled dataset [Para 0032, the missing value imputation system 110 imputes missing values and outputs completed data 210].
Chu is analogous to the claimed invention as they both relate to data completion. Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Resnick’s teachings to incorporate the teachings of Chu and provide outputting a filled dataset in order to allow a machine learning system to make predictions using sparse datasets.
Resnick-Chu does not teach a deep learning model and a classification model for binary variable imputation.
Lin teaches,
a deep learning model and a classification model for binary variable imputation [Sect I, para 4, we aim to improve the prediction of mortality in myocardial infarction patients by experimenting with various data processing methods and deep learning algorithms; Sect III, para 8, In the experiment, the data with many missing values were deleted, and the data with missing values less than 30% were filled by imputation. The imputation was used as the primary method to avoid discarding data including "Mean Imputation", "K-Nearest Neighbors", and "Multiple Imputation"; Sec III, para 11, By the way, the unbalanced data also has a great impact on the model prediction. When training binary data, it is often found that the “positive” and “negative” samples are not equal];
Lin is analogous to the claimed invention as they both relate to data imputation. Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Resnick’s teachings to incorporate the teachings of Lin and provide a deep learning model and a classification model for binary variable imputation in order to [Lin, Sect I, para 4 and Sect III, para 8] improve model prediction and avoid discarding data.
Regarding claim 15, Resnick-Chu-Lin teach the limitations of claim 13.
Resnick further teaches,
wherein the data type comprises a category, a continuous variable [Para 0022, the word “feature” is being used to describe a data field as across all or some of the cases in the computer-based reasoning model. The word “field,” in this context, is being used to describe the value of an individual case for a particular feature. For example, a feature for a theoretical computer-based reasoning model for self-driving cars may be “speed”. The field value for a particular case for the feature of speed may be the actual speed, such as thirty-five miles per hour], or a binary value.
Regarding claim 19, Resnick teaches,
A non-transitory computer-readable medium comprising a set of instructions that, in response to being executed by a processor circuit [Para 0179, Such instructions, when stored in non-transitory storage media accessible to processor 304, render computer system 300 into a special-purpose machine that is customized to perform the operations specified in the instructions], cause the processor circuit to perform a method of recursively imputing missing values in a received dataset [Abstract, Techniques are provided for imputation in computer-based reasoning systems; Para 0096, Receiving 420 current context may include receiving the context data needed for a determination to be made using the computer-based reasoning model; Para 0100, detecting gaps in the training data and/or vehicle control rules] by:
sorting the dataset by a count of missing feature values for a plurality of features in the dataset [Para 0026, the process 100 will proceed by modifying 150 that particular case, updating 170 the imputation model, and then recomputing… imputation order information];
determining a data type of the feature in the sorted dataset having a lowest count of missing feature values; selecting an imputation model corresponding to the determined data type from a group of imputation models comprising categorical variable imputation (Para 0151, k nearest neighbors), a regression model for continuous variable imputation (Para 0151, k nearest neighbors) [Para 0026, determining 130 which cases to impute data based on… the order in which to impute data may include determining… the fewest number of features to impute (e.g., if there is just one case with a single field to impute, that case may have its data imputed first); Para 0028, After determining 130 which cases to impute data and/or the order in which to impute data, the imputed data is determined 140 based on the case with the missing data and the imputation model. The imputation model may be any appropriate statistical or other machine learning model; Para 0151, processes 100 and/or 400 may determine (e.g., in response to a request) the search result (e.g., k nearest neighbors, most probable cases in gaussian process regression, etc.) in the computer-based reasoning model for use in the financial system computer-based reasoning model. Based on those search results, the process can cause control of a financial system computer-based reasoning system using process 400… if the data elements are related to financial system actions, then the financial system computer-based reasoning model trained on that data will control the financial system… The financial system computer-based reasoning model is then used to determine 430 an action to take. The action is then performed by the control system (e.g., caused by the financial system computer-based reasoning system)… the financial system computer-based reasoning model may be used to assess financial system decisions, predict outcomes, etc… the chosen action(s) are then performed by a control system];
training the selected imputation model using feature values corresponding to filled dataset indices of populated values of the feature having a lowest count of the missing feature values; predicting, using the trained imputation model, and based on the feature values corresponding to filled dataset indices, missing values of the feature having the lowest count of the missing feature values; and imputing the predicted missing values into the dataset [Para 0024, Determining 130 imputation order, may then include determining 130 the cases with the fewest (or, in some embodiments, most) missing features can then have the missing features imputed first; Para 0028, existing fields (e.g., fields that are not empty) for each feature may be used as the outcome variable and the rest of the features could be used as the input variables. Such a machine learning model would then be able to predict what data is missing for each missing field for each case; Para 0031, Updating 170 the imputation model may include completely retraining the imputation model based on the updated data in the computer-based reasoning model in similar manner to what is described elsewhere herein];
Resnick does not teach imputing missing values until the dataset is filled;
outputting a filled dataset.
Chu teaches,
imputing missing values until the dataset is filled [Para 0010, The missing value is imputed for each of the one or more predictor variables using the data from the one or more data sources and one or more built imputation models to generate a completed data set];
outputting a filled dataset [Para 0032, the missing value imputation system 110 imputes missing values and outputs completed data 210].
Chu is analogous to the claimed invention as they both relate to data completion. Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Resnick’s teachings to incorporate the teachings of Chu and provide outputting a filled dataset in order to allow a machine learning system to make predictions using sparse datasets.
Resnick-Chu does not teach a deep learning model and a classification model for binary variable imputation.
Lin teaches,
a deep learning model and a classification model for binary variable imputation [Sect I, para 4, we aim to improve the prediction of mortality in myocardial infarction patients by experimenting with various data processing methods and deep learning algorithms; Sect III, para 8, In the experiment, the data with many missing values were deleted, and the data with missing values less than 30% were filled by imputation. The imputation was used as the primary method to avoid discarding data including "Mean Imputation", "K-Nearest Neighbors", and "Multiple Imputation"; Sec III, para 11, By the way, the unbalanced data also has a great impact on the model prediction. When training binary data, it is often found that the “positive” and “negative” samples are not equal];
Lin is analogous to the claimed invention as they both relate to data imputation. Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Resnick’s teachings to incorporate the teachings of Lin and provide a deep learning model and a classification model for binary variable imputation in order to [Lin, Sect I, para 4 and Sect III, para 8] improve model prediction and avoid discarding data.
Regarding claim 20, Resnick-Chu-Lin teach the limitations of claim 19.
Resnick further teaches,
receiving procedure instructions comprising mean instructions, median instructions, mode instructions, or a user-supplied value to populate one or more missing features in the dataset [Para 0123, the training data could be what a particular user does at certain times of day and/or in particular sequences; Para 0158, Data that represents neither a threat nor anomalous behavior (e.g., non-malicious access attempts, non-malicious emails, etc.) may also be used to train the computer-based reasoning model… when a new… user… is ready for assessment, the features associated with that new… user… may be used as input in the trained cybersecurity computer-based reasoning system. The cybersecurity computer-based reasoning system may then determine the probability or likelihood that the user… is or represents a threat or anomalous behavior].
Claim(s) 5 is rejected under 35 U.S.C. 103 as being unpatentable over Resnick, in view of Chu and Lin, and in further view of Phung et al. (A deep learning technique for imputing missing healthcare data, published 2019), hereinafter Phung.
Regarding claim 5, Resnick-Chu-Lin teach the limitations of claim 1.
Resnick-Chu do not teach wherein the dataset is copied to enable imputing missing values into a copied dataset without modifying an original dataset.
Phung teaches,
wherein the dataset is copied to enable imputing missing values into a copied dataset without modifying an original dataset [Sect II (B), para 1, In order to build a deep learning model for data imputation, we built upon representation learning techniques… Figure 1 shows the high level architecture and process of our ODAE… The trained ODAE will attempt to reconstruct the original input, according to the learned relationships, including the originally missing values; Sect II (B), para 2, our ODEA first projects our inputs, including missing values, into a high-dimensional latent subspace then based on the values on that subspace we obtain the estimates for original values, including prediction for missing values; Sect II (B), para 5, In order to force the model to learn the true distribution of each variables, we trained the model with a modified loss function between the reconstructed output (ˆx) and the precorrupted input (x)].
Phung is analogous to the claimed invention as they both relate to imputation models. Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Resnick’s teachings to incorporate the teachings of Phung and provide a copied dataset for imputing missing values [Sect II (B), para 1] in order to improve result complexity by learning meaningful relationships between output and input.
Claim(s) 6 is rejected under 35 U.S.C. 103 as being unpatentable over Resnick, in view of Chu and Lin, and in further view of Settels et al. (US 20250149127 A1), hereinafter Settels.
Regarding claim 6, Resnick-Chu-Lin teach the limitations of claim 1.
Resnick-Chu-Lin do not teach wherein one or more models are received from the user.
Settels teaches,
wherein one or more models are received from user [Para 0065, the prediction model providing unit 112 can comprise or refer to an input unit through which the prediction model can be received, for instance, by a user that inputs or indicates which prediction model should be used].
Settels is analogous to the claimed invention as they both relate to prediction models. Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Resnick’s teachings to incorporate the teachings of Settels and provide models received from users to improve the robustness of the machine learning system.
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 SYED RAYHAN AHMED whose telephone number is (571)270-0286. The examiner can normally be reached Mon-Fri ET.
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, David Yi can be reached at (571) 270-7519. 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.
/SYED RAYHAN AHMED/Examiner, Art Unit 2126
/DAVID YI/Supervisory Patent Examiner, Art Unit 2126
Prosecution Insights