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 .
This action is in response to communications filed on 06/22/2026. Claims 1-20 are pending and have been examined.
Priority
Applicant’s claim for the benefit of a prior-filed application under 35 U.S.C. 119(e) or under 35 U.S.C. 120, 121, 365(c), or 386(c) is acknowledged.
Information Disclosure Statement
Information disclosure statements (IDS) submitted were filed on 06/22/2026 and 08/25/2026. Each submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, each information disclosure statement is being considered by the examiner.
Response to Arguments
Previous objections to the specification have been withdrawn in view of amendments.
Previous objections to the claims have been withdrawn in view of amendments.
Previous claim interpretation has been withdrawn in view of amendments.
Previous rejections under 35 USC 112 have been withdrawn in view of amendments.
Previous rejections under 35 USC 101 have been withdrawn in view of amendments.
Applicant’s arguments with respect to amended features have been considered but are moot in view of the new grounds of rejection. See Galloway et al. (US 20180260706 A1) below.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1, 8, and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Litt et al. (US 6658287 B1) in view of Echauz et al. (US 20020103512 A1) and Galloway et al. (US 20180260706 A1).
As per independent claim 1, Litt teaches a computing system comprising:
one or more processors and a non-transitory computer-readable medium storing computer-executable program instructions that, when executed by the processor, cause the processor (e.g. in column 7 lines 21-47 and column 28 lines 15-23, “software programs(s) executed by a processor… a processor readable memory medium storing instructions, which when executed by a processor, perform”) to perform operations comprising:
accessing predictor data samples from a data repository (e.g. in column 5 lines 14-48, column 11 lines 45-48, and column 28 lines 15-23, “large set of independent, instantaneous and historical features are extracted from the intracranial EEG, real-time brain activity data and/or other physiologic data…for each individual patient… features are extracted… "feature library" is a collection of features which are extracted by algorithms from raw brain activity data”), wherein the predictor data samples including a set of time series values of predictor variables that respectively correspond to actions performed by an entity or observations of the entity (e.g. in column 5 lines 14-48, column 7 lines 56, column 11 lines 45-48, column 25 lines 44-64, and column 28 lines 15-23, “observation window during which time processing of the brain activity signal is continuous… pre-ictal time frame for seizure prediction… large set of independent, instantaneous and historical features are extracted from the intracranial EEG, real-time brain activity data and/or other physiologic data…for each individual patient… memory… features are extracted… "feature library" is a collection of features which are extracted by algorithms from raw brain activity data… feature behavior… a processor readable memory medium”);
determining wavelet predictor variable data by, at least, applying a wavelet transform to the time series values of the predictor variables in the predictor data samples, the wavelet predictor variable data comprising a first set of value input data for a first scale and a second set of value input data for a second scale (e.g. in column 12 lines 40-44 and column 25 lines 44-59, “a window length of 30 seconds [i.e. first scale]… feature vector for a particular patient is generated that contains windowed (i.e. calculated over a particular time window, such as 1.25 seconds [i.e. second scale]) features such as…a single scale of the wavelet transform”);
determining a set of probabilities for a target event by applying a set of timing-prediction models trained according to respective time windows to the first set of value input data and the second set of value input data (e.g. in column 17 lines 38-49 and column 18 lines 25-35, “the WNN module is effectively 4 separate WNNs, each trained on a corresponding prediction horizon. The number of prediction horizons and their corresponding time interval may vary” and figure 7), wherein each timing-prediction model of the set of timing-prediction models is configured to generate a respective probability of the set of probabilities indicating a probability of the target event occurring in a time window associated with the timing-prediction model (e.g. in column 18 lines 25-35 and column 21 lines 32-43, “number of prediction horizons and their corresponding time interval… providing as output a time-based probability measure, a patient or physician may set thresholds for the probability of a seizure over a prediction horizon”);
determining an event prediction from the set of probabilities (e.g. in column 10 lines 4-21, “provide…several continuous outputs representing probabilities for multiple time horizons”); and
performing an action based on the event prediction (e.g. in column 10 lines 4-21, “system is programmable to respond to the output of the intelligent prediction subsystem to take one or more actions”),
but does not specifically teach wherein a first/second set of value input data includes shift value input data and performing the action including modifying, based on the event prediction, access to one or more restricted functions of an interactive computing environment by the entity.
However, Echauz teaches a first/second set of value input data including shift value input data (e.g. in paragraphs 80, 203, 209, 242-244, and 251, “in the wavelet analysis different window lengths are used (i.e, different scales)… the wavelet transform breaks the data signal into shifted and scaled versions of the mother wavelet used… wavelet transform is run over the data for four or more different scales… allow the creation of feature vectors from features extracted with different sliding window sizes and sometimes also with different window shiftings”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Litt to include the teachings of Echauz because one of ordinary skill in the art would have recognized the benefit of incorporating relevant wavelet properties,
but does not specifically teach performing the action including modifying, based on the event prediction, access to one or more restricted functions of an interactive computing environment by the entity.
However, Galloway teaches performing an action including modifying, based on an event prediction, access to one or more restricted functions of an interactive computing environment by an entity (e.g. in paragraphs 14 and 30, and claim 8, “identity analysis system may use the probability to determine whether there is a potential change in a status or condition of an individual… In response to the machine learning model determining that the electrocardiogram is not that of the subject, an identity analysis system may take several different paths. For example, if the person is not the intended subject, then a notification or appropriate action (e.g., denying access) is made… the identity analysis system 110 may be located on a personal device such as a mobile device, personal computer, smart watch… deny access to one or more functions in response to determining that the output not matching the expected range of outputs for the target subject”, i.e. restricted functions to a target subject). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of the combination to include the teachings of Galloway because one of ordinary skill in the art would have recognized the benefit of facilitating identity analysis.
Claim 8 is the method claim corresponding to system claim 1, and is rejected under the same reasons set forth.
Claim 15 is the medium claim corresponding to system claim 1, and is rejected under the same reasons set forth and the combination further teaches non-transitory computer-readable medium, comprising computer-executable program instructions that, when executed by a processor, cause the processor to perform operations (e.g. Litt, in column 28 lines 15-23, “a processor readable memory medium storing instructions, which when executed by a processor, perform”).
Claims 2, 9, and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Litt et al. (US 6658287 B1) in view of Echauz et al. (US 20020103512 A1) and Galloway et al. (US 20180260706 A1) and further in view of Leppanen et al. (US 20140357291 A1).
As per claim 2, the rejection of claim 1 is incorporated, but the combination does not specifically teach determining that the set of time series values of the predictor data samples are missing a time series value for at least one time instance of a time series; setting the time series value for the at least one time instance to zero; generating a missing value indicator for the time series, the missing value indicator having a value of zero for the at least one time instance and a value of one for other time instances of the time series; and based on the missing value indicator and the wavelet predictor variable data, calculating confidence values that correspond to wavelet coefficients for the time series data, wherein the wavelet variable predictor data further comprise the confidence values. However, the combination teaches datum including time series associated with wavelet predictor variable data/coefficients (e.g. Litt, in column 5 lines 14-48, column 18 lines 25-35, and column 25 lines 44-64, “observation window during which time processing of the brain activity signal is continuous… pre-ictal time frame for seizure prediction… large set of independent, instantaneous and historical features are extracted from the intracranial EEG, real-time brain activity data and/or other physiologic data… for each individual patient… feature vector for a particular patient is generated… wavelet transform”, i.e. wavelet coefficients; Echauz, in paragraph 209, “wavelet transform is run over the data for four or more different scales”) and Leppanen teaches determining that a set of datum values of data samples are missing a datum value for at least one datum instance of a datum (e.g. in paragraph 58, “If any measurements are missing”); setting the value for the at least one instance to zero (e.g. in paragraph 58, “If any measurements are missing, the corresponding weights in matrix W may be set to zero”); generating a missing value indicator for the datum, the missing value indicator having a value of zero for the at least one datum instance and a value of one for other datum instances of the datum (e.g. in paragraph 58, “the weights can be all set to 1. If any measurements are missing, the corresponding weights in matrix W may be set to zero”); and based on the missing value indicator and variable data, calculating confidence values that correspond to coefficients for the datum data, wherein the variable data further comprise the confidence values (e.g. in paragraph 58, “Scaling… a matrix W of weights is generated, such as by the processor 104, the elements of which define how each of the distances in matrix D is weighted in the calculations… the weights can be all set to 1. If any measurements are missing, the corresponding weights [i.e. coefficients] in matrix W may be set to zero. In addition, if there is not confidence in some of the distance estimates, this can be reflected in the weight matrix W. For example, if the signal strengths of device A, as recorded by device B, differ significantly from the signal strengths of device B, as recorded by device A, a lower weight may be used in conjunction with the distance estimate”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of the combination to include the teachings of Leppanen because one of ordinary skill in the art would have recognized the benefit of accounting for relevant aspects of datum.
Claim 9 is the method claim corresponding to system claim 2 and is rejected under the same reasons set forth.
Claim 16 is the medium claim corresponding to system claim 2 and is rejected under the same reasons set forth.
Claims 3-6, 10-13, and 17-19 are rejected under 35 U.S.C. 103 as being unpatentable over Litt et al. (US 6658287 B1) in view of Echauz et al. (US 20020103512 A1) and Galloway et al. (US 20180260706 A1) and further in view of Merrill et al. (US 20200265336 A1).
As per claim 3, the rejection of claim 1 is incorporated, but the combination does not specifically teach generate explanatory data for the event prediction. However, Merrill teaches generate explanatory data for an event prediction (e.g. in paragraphs 22, 29-30, 37-38, 65, and 125, “contribution values for a feature…are computed using a specific method as described in Merrill, et al., “Generalized Integrated Gradients: A practical method for explaining diverse ensemble… produce a…prediction… models to be used in applications that require transparency and explanations, such as in financial services, where regulation and prudence require model-based decisions be explained to consumers, risk managers, and regulators… output explanation module 124 functions to generate information based on the influence of features”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of the combination to include the teachings of Merrill because one of ordinary skill in the art would have recognized the benefit of facilitating transparency and/or meeting regulations.
As per claim 4, the rejection of claim 3 is incorporated and the combination further teaches generate the explanatory data by: determining a set of wavelet values of the wavelet predictor variable data that, when the set of timing-prediction models is applied to the set of wavelet values, result in a maximum value for the event prediction (e.g. Merrill, in paragraphs 19, 22, 35, 37, and claim 16, “reference data set is a set of healthy patients, a set of defendants found innocent, a set of signals from sensors indicating a safe lane change, a set of admitted students [i.e. a maximum value]… Adverse Action information is comprised of input variables and their contribution to the difference in score… wherein the model explanation information identifies model disparity between the evaluation input data set and the reference input data set”); determining, for a wavelet of the wavelet predictor variable data, a points lost value as a difference between the maximum value and a value of the event prediction generated by replacing the wavelet in the set of wavelet values with a current value of the wavelet (e.g. Merrill, in paragraphs 19, 22, 35, 37, and claim 16, “reference data set is a set of healthy patients, a set of defendants found innocent, a set of signals from sensors indicating a safe lane change, a set of admitted students… Adverse Action information is comprised of input variables and their contribution to the difference in score… wherein the model explanation information identifies model disparity between the evaluation input data set and the reference input data set”, i.e. points lost); and generating explanatory data for the event prediction based, at least in part, upon the points lost value for the wavelet prediction (e.g. Merrill, in paragraph 37 and claim 16, “generated information includes Adverse Action information. In some variations, the Adverse Action information is comprised of input variables and their contribution to the difference… wherein the model explanation information identifies model disparity between the evaluation input data set and the reference input data set”).
As per claim 5, the rejection of claim 4 is incorporated and the combination further teaches wherein the wavelet transform comprises a set of wavelets, wherein the wavelet predictor variable data is generated by, at least, applying the set of wavelets of the wavelet transform to the predictor data samples, and wherein the set of wavelet values of the wavelet predictor variable data correspond to the set of wavelets (e.g. Litt, in column 5 lines 14-48, column 18 lines 25-35, and column 25 lines 44-64, “observation window during which time processing of the brain activity signal is continuous… pre-ictal time frame for seizure prediction… large set of independent, instantaneous and historical features are extracted from the intracranial EEG, real-time brain activity data and/or other physiologic data… for each individual patient… feature vector for a particular patient is generated… wavelet transform”; Echauz, in paragraph 209, “wavelet transform is run over the data for four or more different scales”).
As per claim 6, the rejection of claim 3 is incorporated and the combination further teaches wherein the set of time series values comprises a first set of time series values and wherein the one or more processors are configured to generate the explanatory data by: generate the explanatory data by: identifying a baseline set of time series values (e.g. Litt, in column 5 lines 14-48, “observation window during which time processing of the brain activity signal is continuous… pre-ictal time frame for seizure prediction… large set of independent, instantaneous and historical features are extracted from the intracranial EEG, real-time brain activity data and/or other physiologic data… for each individual patient”; Merrill, in paragraphs 19, 22, 35, 37, and claim 16, “reference data set is a set of healthy patients, a set of defendants found innocent, a set of signals from sensors indicating a safe lane change, a set of admitted students… Adverse Action information is comprised of input variables and their contribution to the difference in score… wherein the model explanation information identifies model disparity between the evaluation input data set and the reference input data set”); evaluating an integrated gradients calculation along a path in attribute space from the baseline set of time series values to the first set of time series values (e.g. Litt, in column 5 lines 14-48, “observation window during which time processing of the brain activity signal is continuous… pre-ictal time frame for seizure prediction… large set of independent, instantaneous and historical features are extracted from the intracranial EEG, real-time brain activity data and/or other physiologic data… for each individual patient”; Merrill, in paragraph 35, “performing an integrated gradients process to compute the feature contributions on segments of a path or plurality of paths between each element of an evaluation input data set and each element of a reference input data set”); determining an allocation of change between the baseline set of time series values and the first set of time series values by summing integrated gradients for each of the first set of time series values (e.g. Litt, in column 5 lines 14-48, “observation window during which time processing of the brain activity signal is continuous… pre-ictal time frame for seizure prediction… large set of independent, instantaneous and historical features are extracted from the intracranial EEG, real-time brain activity data and/or other physiologic data… for each individual patient”; Merrill, in paragraphs 37 and 125 and claim 16, “Adverse Action information is comprised of input variables and their contribution to the difference in score… decompositions for each segment are summed (sum of segment decompositions) together to produce a sum of the segment decompositions to determine the contribution… wherein the model explanation information identifies model disparity between the evaluation input data set and the reference input data set”); and selecting one or more of the determined allocations as an explanation for the event prediction (e.g. Merrill, in paragraph 37, “generated information includes Adverse Action information. In some variations, the Adverse Action information is comprised of input variables and their contribution to the difference”).
Claims 10-13 are the method claims corresponding to system claims 3-6, and are rejected under the same reasons set forth.
Claims 17-19 are the medium claims corresponding to system claims 4-6 and are rejected under the same reasons set forth.
Claims 7, 14, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Litt et al. (US 6658287 B1) in view of Echauz et al. (US 20020103512 A1), Galloway et al. (US 20180260706 A1) and Merrill et al. (US 20200265336 A1), and further in view of Chintalapati et al. (US 20200104775 A1).
As per claim 7, the rejection of claim 3 is incorporated and the combination further teaches wherein the one or more processors are configured to generate explanatory data (e.g. Merrill, in paragraphs 22, 29-30, 37-38, 65, and 125, “contribution values for a feature…are computed using a specific method as described in Merrill, et al., “Generalized Integrated Gradients: A practical method for explaining diverse ensemble… produce a…prediction… models to be used in applications that require transparency and explanations, such as in financial services, where regulation and prudence require model-based decisions be explained to consumers, risk managers, and regulators… output explanation module 124 functions to generate information based on the influence of features”) by: training the set of timing-prediction models using a data set of entity behaviors (e.g. Litt, in column 2 lines 1-11, column 5 lines 14-48, column 17 lines 38-49, column 18 lines 25-35, and column 25 lines 44-64, “analyzing the feature vector with a trainable algorithm implemented by, for example, a wavelet neural network… observation window during which time processing of the brain activity signal is continuous… pre-ictal time frame for seizure prediction… large set of independent, instantaneous and historical features are extracted from the intracranial EEG, real-time brain activity data and/or other physiologic data… for each individual patient… the WNN module is effectively 4 separate WNNs, each trained on a corresponding prediction horizon. The number of prediction horizons and their corresponding time interval may vary… based on feature behavior” and figure 7); calculating, for each of the values of the set of time series values, a Shapley value contribution (e.g. Litt, in column 5 lines 14-48, “observation window during which time processing of the brain activity signal is continuous… pre-ictal time frame for seizure prediction… large set of independent, instantaneous and historical features are extracted from the intracranial EEG, real-time brain activity data and/or other physiologic data… for each individual patient”; Merrill, in paragraphs 21 and 24, “the model explanation system is based on measure-theoretic methods that extend Aumann-Shapley as described herein… produces a specific quantification of the importance of each input variable to a model-based decision, such as, e.g., a decision to deny a credit application. This quantification can be used to power explanations that enable model users to understand why a model made a given decision and what to do to change the model-based decision outcome… the componentwise integral includes contribution values {c.sub.1, c.sub.2, c.sub.3} which correspond to the feature contribution of features {x.sub.1, x.sub.2, x.sub.3}, respectively”); associating the Shapley value contributions with entity behaviors by combining, for each entity behavior, individual contributions of attributes upon which the entity behavior is dependent prediction (e.g. Litt, in column 5 lines 14-48 and column 25 lines 44-64, “observation window during which time processing of the brain activity signal is continuous… pre-ictal time frame for seizure prediction… large set of independent, instantaneous and historical features are extracted from the intracranial EEG, real-time brain activity data and/or other physiologic data…for each individual patient… based on feature behavior”; Merrill, in paragraphs 21 and 24, “the model explanation system is based on measure-theoretic methods that extend Aumann-Shapley as described herein… produces a specific quantification of the importance of each input variable to a model-based decision, such as, e.g., a decision to deny a credit application. This quantification can be used to power explanations that enable model users to understand why a model made a given decision and what to do to change the model-based decision outcome… the componentwise integral includes contribution values {c.sub.1, c.sub.2, c.sub.3} which correspond to the feature contribution of features {x.sub.1, x.sub.2, x.sub.3}, respectively”),
but does not specifically teach selecting one or more entity behaviors having a greatest Shapley value contribution as an explanation of the event prediction.
However, Chintalapati teaches selecting one or more entity attributes having a greatest Shapley value contribution as an explanation of an event prediction (e.g. in paragraphs 4, 27, and 122, “an explanation of the metrics with the greatest entropy change for the subset of the plurality of metric indicators is generated… using computational techniques including but not limited to…Shapley Additive Explanation”). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of the combination to include the teachings of Chintalapati because one of ordinary skill in the art would have recognized the benefit of providing explanations for attributes that have the most impact.
Claim 14 is the method claim corresponding to system claim 7 and is rejected under the same reasons set forth.
Claim 20 is the medium claim corresponding to system claim 7 and is rejected under the same reasons set forth.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
For example,
Khorrami et al. (US 20190340392 A1) teaches “multiple temporal lengths provides a multi-resolution approach that facilitates learning of temporal patterns that are apparent over different time scales… the time series signals in the specific application” (e.g. in paragraph 73).
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 WILLIAM WONG whose telephone number is (571)270-1399. The examiner can normally be reached Monday-Friday 9am-5pm.
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, TAMARA KYLE can be reached at (571)272-4241. 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.
/W.W/Examiner, Art Unit 2144 09/05/2026
/TAMARA T KYLE/Supervisory Patent Examiner, Art Unit 2144
Prosecution Insights