DETAILED ACTION
This action is in response to the claims filed 02/27/2026 for Application number 18/057,883. Claims 1, 2, 10, 12, and 17 have been amended. Thus claims 1-20 are currently 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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 02/27/2026 has been entered.
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 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Regarding claim 1,
Step 1 Analysis: Claim 1 is directed to a process, which falls within one of the four statutory categories.
Step 2A Prong 1 Analysis: Claim 1 recites, in part, The limitations of:
generating, [by the processing device using the predictive model with the updated estimated parameters], an uncertainty interval for a future observed value can be considered to be an evaluation in the human mind
determining, [by the processing device], an observed value corresponding to the future observed value is outside of the uncertainty interval can be considered to be an evaluation in the human mind
generating, [by the processing device], an indication that the observed value is an anomaly can be considered to be an evaluation in the human mind
These limitations as drafted, are processes that, under broadest reasonable interpretation, covers performance of the limitation in the mind or with the aid of pen and paper which falls within the “Mental Processes” grouping of abstract ideas.
Additionally, the claim recites:
computing, [by a processing device], estimated parameters by a predictive model can be considered to be a mathematical calculation
computing, [by the processing device], updated estimated parameters of a [predictive model] for the time-series data by performing a rank one update on previously estimated parameters of [the predictive model] can be considered to be a mathematical calculation
This limitation as drafted, is a process that, under broadest reasonable interpretation, covers mathematical calculations thus falls under the “Mathematical Concepts” grouping of abstract ideas.
Accordingly, the claim recites an abstract idea.
Step 2A Prong 2 Analysis: This judicial exception is not integrated into a practical application. In particular, the claim recites the additional element - “a processing device” and “updating, by the processing device, the predictive model using the updated estimated parameters”. Thus, this element in the claim is recited at a high level of generality such that it amounts to no more than mere instructions to apply the exception using a generic computer component. Please see MPEP §2106.05(f). Additionally, the claim recites the additional element – “a predictive model”. This element is merely generally linked to the judicial exception. Please see MPEP §2106.05(h). Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
The claim further recites: receiving, by the processing device via a network, time-series data in a real-time stream, the time-series data describing continuously observed values separated by a period of time and
receiving, by the processing device, the future observed value subsequent to the generating the uncertainty interval for the future observed value
These limitations are mere data gathering steps and thus are insignificant extra-solution activities. Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. The claim as a whole is directed to an abstract idea.
Step 2B Analysis: The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of utilizing a processing device to perform the steps of the claimed process amount to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. Additionally, utilizing a predictive model to perform the steps of the claimed process amount to no more than generally linking the additional element to the judicial exception. Furthermore, the limitations of receiving, by the processing device via a network, time-series data in a real-time stream, the time-series data describing continuously observed values separated by a period of time and
receiving, by the processing device, the future observed value subsequent to the generating the uncertainty interval for the future observed value
are well-understood, routine, and conventional, as evidenced by MPEP §2106.05(d)(II)(I), “receiving or transmitting data over a network”. These limitations therefore remain insignificant extra-solution activity even upon reconsideration, and does not amount to significantly more. Even when considered in combination, these additional elements amount to mere instructions to apply the exception using generic computer components, generally linking the additional element to the judicial exception and insignificant extra-solution activity, which cannot provide an inventive concept. The claim is not patent eligible.
Regarding claim 2, the rejection of claim 1 is further incorporated, and further, the claim recites: wherein the computing the estimated parameters by the predictive model includes a non-periodic first component and a periodic second component. This limitation amounts to more specifics of the judicial exception identified in the rejection of claim 1 above.
The claim does not include any additional elements that amount to an integration of the judicial exception into a practical application, nor to significantly more than the judicial exception. The claim is not patent eligible.
Regarding claim 3, the rejection of claim 1 is further incorporated, and further, the claim recites: wherein the time-series data is non-stationary. This limitation amounts to more specifics of the judicial exception identified in the rejection of claim 1 above.
The claim does not include any additional elements that amount to an integration of the judicial exception into a practical application, nor to significantly more than the judicial exception. The claim is not patent eligible.
Regarding claim 4, the rejection of claim 1 is further incorporated, and further, the claim recites: wherein the predictive model is based on an approximate Gaussian process. This claim recites additional mathematical concepts in addition to the judicial exception identified in the rejection of claim 1, thus recites a judicial exception.
The claim does not include any additional elements that amount to an integration of the judicial exception into a practical application, nor to significantly more than the judicial exception. The claim is not patent eligible.
Regarding claim 5, the rejection of claim 1 is further incorporated, and further, the claim recites: wherein the predictive model is implemented using Bayesian linear regression. This claim recites additional mathematical concepts in addition to the judicial exception identified in the rejection of claim 1, thus recites a judicial exception.
The claim does not include any additional elements that amount to an integration of the judicial exception into a practical application, nor to significantly more than the judicial exception. The claim is not patent eligible.
Regarding claim 6, the rejection of claim 1 is further incorporated, and further, the claim recites: wherein the uncertainty interval is generated using a maximum a posteriori estimate. This claim recites additional mathematical concepts in addition to the judicial exception identified in the rejection of claim 1, thus recites a judicial exception.
The claim does not include any additional elements that amount to an integration of the judicial exception into a practical application, nor to significantly more than the judicial exception. The claim is not patent eligible.
Regarding claim 7, the rejection of claim 1 is further incorporated, and further, the claim recites: wherein the updated estimated parameters are computed using exponentially weighted updates that decay based on the period of time. This claim recites additional mathematical concepts in addition to the judicial exception identified in the rejection of claim 1, thus recites a judicial exception.
The claim does not include any additional elements that amount to an integration of the judicial exception into a practical application, nor to significantly more than the judicial exception. The claim is not patent eligible.
Regarding claim 8, the rejection of claim 1 is further incorporated, and further, the claim recites: wherein the exponentially weighted updates have a decay rate based on a fraction of the period of time. This claim recites additional mathematical concepts in addition to the judicial exception identified in the rejection of claim 1, thus recites a judicial exception.
The claim does not include any additional elements that amount to an integration of the judicial exception into a practical application, nor to significantly more than the judicial exception. The claim is not patent eligible.
Regarding claim 9, the rejection of claim 1 is further incorporated, and further, the claim recites: wherein the exponentially weighted updates are used to vary regression coefficients over time. This claim recites additional mathematical concepts in addition to the judicial exception identified in the rejection of claim 1, thus recites a judicial exception.
The claim does not include any additional elements that amount to an integration of the judicial exception into a practical application, nor to significantly more than the judicial exception. The claim is not patent eligible.
Claim 10 recites features similar to claim 1 and is rejected for at least the same reasons therein. Claim 10 additionally recites a memory component. This is an additional element that amounts to mere instructions to apply the exception using a generic computer component. Please see MPEP 2106.05(f).
Regarding Claim 11-16, they recite features similar to claims 2-7 respectively and are rejected for at least the same reasons therein.
Regarding claim 17,
Step 1 Analysis: Claim 17 is directed to a machine, which falls within one of the four statutory categories.
Step 2A Prong 1 Analysis: Claim 17 recites, in part, The limitations of:
generating, [using the predictive model with the updated estimated parameters], an uncertainty interval for a future observed value can be considered to be an evaluation in the human mind
comparing an observed value corresponding to the future observed value with the predicted value can be considered to be an evaluation in the human mind
generating an indication that the observed value is an anomaly based on comparing the observed value with the predicted value can be considered to be an evaluation in the human mind
These limitations as drafted, are processes that, under broadest reasonable interpretation, covers performance of the limitation in the mind or with the aid of pen and paper which falls within the “Mental Processes” grouping of abstract ideas.
Additionally, the claim recites:
computing estimated parameters by a predictive model based on training data can be considered to be a mathematical calculation
computing updated estimated parameters of the predictive model for time- series data received in a real-time stream via a network as describing continuously observed values of the time-series separated by a period of time by performing a rank one update on previously estimated parameters of the predictive model computed based on the training data can be considered to be a mathematical calculation
This limitation as drafted, is a process that, under broadest reasonable interpretation, covers mathematical calculations thus falls under the “Mathematical Concepts” grouping of abstract ideas.
Accordingly, the claim recites an abstract idea.
Step 2A Prong 2 Analysis: This judicial exception is not integrated into a practical application. In particular, the claim recites the additional element - “a non-transitory computer-readable storage medium”, “processing device” and “updating the predictive model using the updated estimated parameters”. Thus, this element in the claim is recited at a high level of generality such that it amounts to no more than mere instructions to apply the exception using a generic computer component. Please see MPEP §2106.05(f). Additionally, the claim recites the additional element – “a predictive model”. This element is merely generally linked to the judicial exception. Please see MPEP §2106.05(h). Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
The claim further recites: for time-series data received in a real-time stream via a network and receiving, by the processing device, the future observed value subsequent to the generating the uncertainty interval for the future observed value.
These limitations are mere data gathering steps and thus is are insignificant extra-solution activities. Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. The claim as a whole is directed to an abstract idea.
Step 2B Analysis: The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of utilizing a processing device, a non-transitory computer-readable storage medium, and updating the predictive model using the updated estimated parameters to perform the steps of the claimed process amount to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. Additionally, utilizing a predictive model to perform the steps of the claimed process amount to no more than generally linking the additional element to the judicial exception. Furthermore, the limitations of for time-series data received in a real-time stream via a network and receiving, by the processing device, the future observed value subsequent to the generating the uncertainty interval for the future observed value are well-understood, routine, and conventional, as evidenced by MPEP §2106.05(d)(II)(I), “receiving or transmitting data over a network”. These limitations therefore remain insignificant extra-solution activity even upon reconsideration, and does not amount to significantly more. Even when considered in combination, these additional elements amount to mere instructions to apply the exception using generic computer components, generally linking the additional element to the judicial exception and insignificant extra-solution activity, which cannot provide an inventive concept. The claim is not patent eligible.
Regarding Claim 18-20, they recite features similar to claims 4, 3 and 7 respectively and are rejected for at least the same reasons therein.
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.
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.
Claims 1-3, 10-12, 17, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Moghtaderi et al. ("US 20160189041 A1", hereinafter "Moghtaderi") in view of Osogami ("US 20200265303 A1", hereinafter "Osogami") and further in view of Wu et al. ("Developing an Unsupervised Real-Time Anomaly Detection Scheme for Time Series With Multi-Seasonality", hereinafter "Wu").
Regarding claim 1, Moghtaderi teaches A method comprising:
receiving, by a processing device via a network (¶0077), time-series data [in a real-time stream], the time-series data describing continuously observed values separated by a period of time (“In various embodiments, the method 300 may process one or a multitude of time series such that it processes one of such time series at a time for one time point. The method 300 can then be repeated for every time point within a time duration of interest, in order, from the farthest time point to the latest.” [¶0042);
generating, by the processing device using the predictive model (See ¶0063 and ¶0065 for predictive models) with the updated estimated parameters, an uncertainty interval for a future observed value (“At operation 406, the training time series T is used to generate the parameters for each of a plurality of prediction methods… At operation 408, q prediction error time series of length L (for time points from (P-L) to (P-1) where P is smaller than L) corresponding to the q prediction methods applied in the context on time series S in the past, are extracted. These prediction error time series are the result of the operation 400 for historical time points, i.e., time points older than P… If the distances computed exceed a predetermined threshold, the time index P is marked as containing an anomaly.” [¶0050-¶0054]);
determining, by the processing device, an observed value corresponding to the future observed value is outside of the uncertainty interval (“The actual (measured) data (“observed” value) at time point t is compared with the predictions (“future observed value”) from operation 306 and a statistical test is applied to the differences between the predicted and actual data.; and
generating, by the processing device, an indication that the observed value is an anomaly. (“The results of this test are used to flag the data at time point t as anomalous or not.” [¶0045])
However, Moghtaderi fails to explicitly teach computing, by a processor device, estimated parameters by a predictive model
computing, by the processing device, updated estimated parameters of a predictive model for the time-series data by performing a rank one update on previously estimated parameters of the predictive model;
updating, by the processing device, the predictive model using the updated estimated parameters;
Osogami teaches computing, by a processor device, estimated parameters by a predictive model (“Therefore, the prediction system incorporates an adaptive forgetting rate and adaptive hyper-forgetting rate to facilitate adaptation to non-stationary time-series. The parameters and forgetting rates are learned through updating upon optimization using the pseudo-inverse of the Hessian of a loss function.” [¶0027; learning parameters corresponds to computing estimated parameters])
computing, by the processing device, updated estimated parameters of a predictive model for the time-series data by performing a rank one update on previously estimated parameters of the predictive model (“Such analysis is relatively efficient computationally, thus providing increased rank-one updates for parameter optimization. Moreover, the recursion of the pseudo-inverse accumulates error at a relatively slow rate, thus improving the accuracy of the optimization.” [¶0027]);
updating, by the processing device, the predictive model using the updated estimated parameters; (“The model is updated in the memory with the updated model parameters.” [¶0004; See also ¶0073-¶0077 discloses more details of parameter updates])
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Moghtaderi’s teachings in order to compute estimated parameters, implement a rank one update, and update the model with the estimated parameters as taught by Osogami. One would have been motivated to make this modification to facilitate adaptation to non-stationary time-series while improving the accuracy of the optimization of model parameters. [¶0027, Osogami]
However Moghtaderi/Osogami fails to explicitly teach receiving, by the processing device via a network, time-series data in a real-time stream and
receiving, by the processing device, the future observed value subsequent to the generating the uncertainty interval for the future observed value
Wu teaches receiving, by the processing device via a network, time-series data in a real-time stream (“The aim of this project is to develop the automated method to spot the potential anomalies and quantify them at real time as the process invocations are being logged in the server” [pg. 4155, left col ¶3]) and
receiving, by the processing device, the future observed value subsequent to the generating the uncertainty interval for the future observed value (“Based on the above ensemble, we propose a new metric, termed Local Trend Inconsistency (LTI), for measuring the deviation of an actual sequence from the predictions in real-time, and assigns an anomaly score to each of the newly arrived data points (which we also call frames) in order to quantify the probability that a frame is anomalous.” [pg. 4148, left col, ¶2])
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Moghtaderi’s/Osogami’s teachings by receiving real-time data and generating an uncertainty interval in real-time as taught by Wu. One would have been motivated to make this modification as this method would significantly mitigate the impact of anomalous samples while enabling the algorithm to work efficiently without maintaining or caching too many historical data frames. [Wu, pg. 4148, left col, ¶2])
Regarding claim 2, Moghtaderi/Osogami/Wu teaches The method as described in claim 1, where Wu further teaches wherein the computing the estimated parameters by the predictive model includes a non-periodic first component and a periodic second component (“where gc(t) is the trend term that models non-periodic changes, sc(t) represents the seasonal term that quantifies the seasonal effects” [pg. 4152, right col, ¶2])
Same motivation to combine the teachings of Moghtaderi/Osogami/Wu as claim 1.
Regarding claim 3, Moghtaderi/Osogami teaches The method as described in claim 1, Moghtaderi teaches wherein the time-series data is non-stationary. (“The anomaly-detection system is designed to seamlessly handle non-stationarity by integrating data from multiple local time regimes.” [¶0016])
Claim 10 recites features similar to claim 1 and is rejected for at least the same reasons therein. Claim 10 additionally requires A system comprising: a memory component; and a processing device coupled to the memory component, the processing device to perform operations (Moghtaderi, “For example, one hardware module may perform an operation and store the output of that operation in a memory device to which it is communicatively coupled. A further hardware module may then, at a later time, access the memory device to retrieve and process the stored output.” [¶0069])
Regarding claims 11 and 12, they are substantially similar to claims 3 and 2 respectively, and are rejected in the same manner, the same art, and reasoning applying.
Claim 17 recites features similar to claim 1 and is rejected for at least the same reasons therein. Claim 17 additionally requires A non-transitory computer-readable storage medium storing executable instructions, which when executed by a processing device (Moghtaderi, ¶0081)
Regarding claim 19, it is substantially similar to claim 3 respectively, and is rejected in the same manner, the same art, and reasoning applying.
Claims 4, 15 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Moghtaderi in view of Osogami and Wu and further in view of Xu et al. ("Adaptive Streaming Anomaly Analysis", hereinafter "Xu").
Regarding claim 4, Moghtaderi/Osogami/Wu teaches The method as described in claim 1, however fails to explicitly teach wherein the predictive model is based on an approximate Gaussian process.
Xu teaches wherein the predictive model is based on an approximate Gaussian process. (“Then the functions (i.e. the time series) are drawn from a Gaussian process GP(µ,(ν − 2)ζ) with the kernel ζ. µ denotes mean function, and is often set as zero without loss of generality” [pg. 2, top para])
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Moghtaderi’s/Osogami’s/Wu’s teachings in order to use a Gaussian process as taught by Xu. One would have been motivated to make this modification in order to be flexible to capture the complex patterns in time series. [pg. 2, top para, Xu]
Regarding claim 15, it is substantially similar to claim 4 respectively, and is rejected in the same manner, the same art, and reasoning applying.
Regarding claim 18, it is substantially similar to claim 4 respectively, and is rejected in the same manner, the same art, and reasoning applying.
Claims 5 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over Moghtaderi in view of Osogami and Wu and further in view of Liu et al. ("Online Conditional Outlier Detection in Nonstationary Time Series", hereinafter "Liu").
Regarding claim 5, Moghtaderi/Osogami/Wu teaches The method as described in claim 1, however fails to explicitly teach wherein the predictive model is implemented using Bayesian linear regression.
Liu teaches wherein the predictive model is implemented using Bayesian linear regression. (“To implement the second layer, we use Bayesian linear regression, so we can add uncertainty to the model to accommodate the scarcity of examples for different sources of variability.” [pg. 86, bottom right col – pg. 87, top left col])
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Moghtaderi’s/Osogami’s/Wu’s teachings to use Bayesian linear regression as taught by Liu. One would have been motivated to make this modification in order to add uncertainty to the model to accommodate scarcity of examples.” [pg. 86, bottom right col – pg. 87, top left col, Liu]
Regarding claim 13, it is substantially similar to claim 5 respectively, and is rejected in the same manner, the same art, and reasoning applying.
Claims 6 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Moghtaderi in view of Osogami and Wu and further in view of Hill et al. ("Real-time Bayesian Anomaly Detection for Environmental Sensor Data", hereinafter "Hill").
Regarding claim 6, Moghtaderi/Osogami/Wu teaches The method as described in claim 1, however fails to explicitly teach wherein the uncertainty interval is generated using a maximum a posteriori estimate.
Hill teaches wherein the uncertainty interval is generated using a maximum a posteriori estimate. (“The maximum a posteriori estimate, (e.g. the most likely value given the posterior distribution) of the hidden state variable indicating the measurement status can then be used to classify the sensor measurements as normal or anomalous” [pg. 4, bottom para])
It would have been obvious to one of ordinary skill in the art before the effective filing date ot modify Moghtaderi’s/Osogami’s/Wu’s teachings to use a maximum a posteriori estimate as taught by Hill. One would have been motivated to make this modification in order to determine if a measured state is normal or anomalous. [pg. 4, bottom para, Hill]
Regarding claim 14, it is substantially similar to claim respectively, and is rejected in the same manner, the same art, and reasoning applying.
Claims 7, 8, 16, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Moghtaderi in view of Osogami and Wu and further in view of Rebjock et al. ("Online false discovery rate control for anomaly detection in time series", hereinafter "Rebjock").
Regarding claim 7, Moghtaderi/Osogami/Wu teaches The method as described in claim 1, however fails to explicitly teach wherein the updated estimated parameters are computed using exponentially weighted updates that decay based on the period of time.
Rebjock teaches wherein the updated estimated parameters are computed using exponentially weighted updates that decay based on the period of time. (“In words, more weight is given to recent rejections, and the past shrinks exponentially. This is arguably the most intuitive notion of FDR for very long, possibly infinite streams of data.” [pg. 6, top para])
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Moghtaderi’s/Osogami’s/Wu’s teachings to use exponentially weighted updates that decay as taught by Rebjock. One would have been motivated to make this modification in order to give more weight to new observations than past observations. [pg. 6, top para, Rebjock]
Regarding claim 8, Moghtaderi/Osogami/Wu/Rebjock teaches The method as described in claim 7, where Rebjock teaches wherein the exponentially weighted updates have a decay rate based on a fraction of the period of time. (“
PNG
media_image1.png
94
572
media_image1.png
Greyscale
” [pg. 6, top equation, decay rate is based on T])
Same motivation to combine the teachings of Moghtaderi/Osogami/Wu/Rebjock as claim 7.
Regarding claims 16 and 20, they are substantially similar to claim 7 respectively, and are rejected in the same manner, the same art, and reasoning applying.
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Moghtaderi in view of Osogami, Wu and Rebjock and further in view of Liu.
Regarding claim 9, Moghtaderi/Osogami/Wu/Rebjock teaches The method as described in claim 7, however fails to explicitly teach wherein the exponentially weighted updates are used to vary regression coefficients over time.
Liu teaches wherein the exponentially weighted updates are used to vary regression coefficients over time. (“The second-layer model takes the output of the first-layer model, z, and a time series of context variables, x, as input, and outputs a sequence of final outlier scores, v. We adopt a Bayesian approach to model zt given xt. Specifically, we assume the following linear model… That is, given w, β, and xt, zt follows a normal distribution… the posterior distribution for (w, β) is again normal-Gamma with updated parameters” [pg. 88, § Second Layer model, bottom left col – top right col; β, xt corresponds to regression coefficients])
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Moghtaderi’s/Osogami’s/Wu’s/Rebjock’s teachings, specifically to use exponentially weighted updates of Rebjock to vary regression coefficients over updates as taught by Liu. One would have been motivated to make this modification in order to add uncertainty to the model to accommodate scarcity of examples.” [pg. 86, bottom right col – pg. 87, top left col, Liu]
Response to Arguments
Applicant's arguments filed 02/27/2026 have been fully considered but they are not persuasive.
Regarding the 35 U.S.C. §101 Rejection:
Applicant appears to refer to Ex parte Desjardins for the basis of the 101 arguments, however the examiner asserts that the instant application’s claims are not similar to the claims of Desjardins. In particular the claims of the instant application lack details recited in the training process of the machine learning/predictive model.
Regarding the analysis of Step 2A Prong1, applicant asserts that the described system and methods enable real-time operation of computer systems processing streaming time-series data which is not practically performable by a human mind. Examiner respectfully disagrees. The examiner noted that the particular limitations of generating, [by the processing device using the predictive model with the updated estimated parameters], an uncertainty interval for a future observed value
determining, [by the processing device], an observed value corresponding to the future observed value is outside of the uncertainty interval
generating, [by the processing device], an indication that the observed value is an anomaly
are all steps which can be practically performed in the human mind. Merely stating the claim limitation requires the use of a computer does not mean that the step itself could not be practically performable in the human mind. Please see Please see MPEP §2106.04.(a)(2).III.C. “A Claim That Requires a Computer May Still Recite a Mental Process”
Additionally, the claim recites:
computing, [by a processing device], estimated parameters by a predictive model can be considered to be a mathematical calculation
computing, [by the processing device], updated estimated parameters of a [predictive model] for the time-series data by performing a rank one update on previously estimated parameters of [the predictive model] can be considered to be a mathematical calculation
The examiner further notes that these limitations are merely mathematical calculations performed by the use of a computer thus as noted above in the 101 rejection, the examiner has indicated that the processing device is an additional element which merely applies the judicial exception using a generic computer component.
Applicant further asserts that the claims are integrated into a practical application by providing specific technological improvement to the operation of network-based monitoring systems. Examiner respectfully disagrees. The claims fail to reflect any improvement over existing computer technology or operation of a neural network rather the claims are directed towards an improvement in the anomaly detection method. Improvements to an abstract idea are still considered to be an abstract idea. Therefore, applicant’s arguments are not persuasive.
Specifically, applicant argues the claims address a technical problem rooted in computer technology. Examiner respectfully disagrees. The claims fail to explicitly reflect the details of an unconventional technical solution or identifies the technical improvement realized by the claim over the prior art. Please see MPEP 2106.05(a). As noted above, the claims fail to reflect any improvement over existing computer technology. The steps of the claims are recited in a broad and generic manner such that it is merely using a predictive model to perform a prediction and determining whether an observed value is an anomaly without any details of the actual training process of the model.
Applicant further asserts the claimed invention provides computational-efficiency and memory saving improvements, enabling real-time operation, and empirical evidence of technological improvement. Examiner respectfully disagrees. As noted in the 101 rejection above, performing a rank one update on previously estimated parameters amounts to a mathematical calculation. There are no details or additional elements within the claims or that specific limitation which reflect any improvement in the functioning/training of the predictive model. Additionally, merely asserting that “training and inference times are reduced by 95%” without any details of how to achieve that result in the claims does not present a persuasive argument. Applicant further argues various features and cited improvements from the specification however these details are not clearly recited in the claims therefore the examiner asserts that the claims lack enough detail to reflect any computational-efficiency and memory saving improvements, enabling real-time operation, and empirical evidence of technological improvement.
Applicant asserts that the “rank one update approach” is not well-understood, routine, and conventional. Examiner respectfully disagrees. The “rank one update” recited in the claims is analyzed to be an abstract idea under the 101 eligibility test. The consideration for well-understood, routine, and conventional activity is only required following a determination if the claim recites any additional elements which fall under insignificant extra-solution activity. However, the “rank one update” was not considered to be an additional element thus the consideration for “well-understood, routine, and conventional” is not required. Therefore, applicant’s arguments are not persuasive.
Regarding the 35 U.S.C. §103 Rejection:
Applicant’s regarding the previously cited prior art failing to teach the newly amended limitations of independent claims 1, 10 and 17 have been considered but are moot because these new limitations are now taught by the newly presented prior art of Wu. Please see the updated 103 rejection above.
Applicant’s arguments with respect to the rejections of the dependent claims have been fully considered but they are not persuasive as they rely upon the allowability of the independent claims
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MICHAEL H HOANG whose telephone number is (571)272-8491. The examiner can normally be reached Mon-Fri 8:30AM-4:30PM.
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, Kakali Chaki can be reached at (571) 272-3719. 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.
/MICHAEL H HOANG/PRIMARY EXAMINER, Art Unit 2122