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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 June 29, 2026 has been entered.
Status of Claims
This office action for the 18/786328 application is in response to the communications filed June 29, 2026.
Claims 1, 2, 7, 9, 14, 15, 16 and 19 were amended June 29, 2026.
Claims 1-20 are currently pending and considered below.
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 a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
As per claim 1,
Step 1: The claim recites subject matter within a statutory category as a process.
Step 2A is a two-prong inquiry, in which Prong 1 determines whether a claim recites a judicial exception. Prong 2 determines if the additional limitations of the claim integrates the recited judicial exception into a practical application. If the additional elements of the claim fail to integrate the judicial exception into a practical application, claim is directed to the recited judicial exception, see MPEP 2106.04(II)(A).
Step 2A Prong 1: The claim contains subject matter that recites an abstract idea, with the steps of a method comprising: obtaining sensor data associated with a subject; extracting, for each time period of one or more past time periods or a current time period, one or more features based on the sensor data; generating, using the extracted one or more features in a specific time frame, a predicted symptom-intensity score for one or more symptoms of the subject using a symptom-forecasting model, the symptom-forecasting model uses power at each of one or more frequency bands as a proxy to calculate a symptom-intensity score based on one or more features corresponding to the current time period, or the previously extracted featured associated with the past time periods, the power is identified by transforming the sensor data into frequency-space data, wherein the predicted symptom-intensity score represents a predicted intensity of the one or more symptoms during a future time period; and outputting a result based on the predicted symptom-intensity score, wherein the result provides a basis for a recommendation or includes the recommendation to perform an intervening action to avoid symptoms in accordance with the predicted symptom-intensity score. These steps, as drafted, under the broadest reasonable interpretation recite:
certain methods of organizing human activity (e.g., fundamental economic principles or practices including: hedging; insurance; mitigating risk; etc., commercial or legal interactions including: agreements in the form of contracts; legal obligations; advertising, marketing or sales activities or behaviors; business relations; etc., managing personal behavior or relationships or interactions between people including: social activities; teaching; following rules or instructions; etc.) but for recitation of generic computer components. That is, other than reciting steps as performed by the generic computer components, nothing in the claim element precludes the step from being directed to certain methods of organizing human activity. For example, but for the additional element(s) of “computer-implemented”, the identified abstract idea, law of nature, or natural phenomenon identified above, in the context of this claim, encompasses a certain method of organizing human activity, namely managing personal behavior or relationships or interactions between people. This is because each of the limitations of the abstract idea recites a list of rules or instructions that a human person is able to perform in the course of their personal behavior. If a claim limitation, under its broadest reasonable interpretation, covers at least the recited methods of organizing human activity above, but for the recitation of generic computer components, then it falls within the “Certain Methods of Organizing Human Activity” grouping of abstract ideas. Accordingly, the claim recites an abstract idea. See MPEP 2106.04(a).
Step 2A Prong 2: The claim does not recite additional elements that integrate the judicial exception into a practical application. In particular, the additional elements do not integrate the abstract idea into a practical application, other than the abstract idea per se, because the additional elements amount to no more than limitations which:
amount to mere instructions to apply an exception, see MPEP 2106.05(f), such as:
“computer-implemented” and “includes a machine learning model that is deployed using an edge AU on a user device, and the machine learning model” which corresponds to merely using a computer as a tool to perform an abstract idea. Paragraph [0011] of the as-filed specification describes that the hardware that implements the abstract idea is at a level of a generic computer. Implementing an abstract idea on a generic computer, does not integrate the abstract idea into a practical application in Step 2A Prong Two or add significantly more in Step 2B, similar to how the recitation of the computer in the claim in Alice amounted to mere instructions to apply the abstract idea of intermediated settlement on a generic computer.
add insignificant extra-solution activity to the abstract idea, see MPEP 2106.05(g), such as:
“streaming the one or more features to a feature-lag buffer, wherein the one or more features corresponding to the one or more past time periods previously extracted features” and “the one or more features streamed at the feature-lag buffer” which corresponds to mere data gathering and/or output.
Accordingly, this claim is directed to an abstract idea.
Step 2B: The claim does not recite additional elements that amount to significantly more than the judicial exception. As discussed above with respect to discussion of integration of the abstract idea into a practical application, the additional elements amount to no more than mere instructions to apply an exception, add insignificant extra-solution activity to the abstract idea, and/or generally link the abstract idea to a particular technological environment or field of use. Additionally, the additional limitations, identified as insignificant extra-solution activity to the abstract idea, amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields such as:
computer functions that have been identified by the examiner as being well‐understood, routine, and conventional functions in light of the prior art, wherein the examiner has provided multiple references as evidence as required by Berkheimer v. HP, Inc., 881 F.3d 1360, 1368, 125 USPQ2d 1649, 1654 (Fed. Cir. 2018), see MPEP 2106.05(d)(I), such as:
“streaming the one or more features to a feature-lag buffer, wherein the one or more features corresponding to the one or more past time periods previously extracted features” and “the one or more features streamed at the feature-lag buffer” which is described at a level understood to be well-known, routine, and conventional, in view of:
Pati et al. (US 2023/0050193; herein referred to as Pati) which teaches a feature engineering process 100. According to some embodiment of the present disclosure, feature vectors 120 such as complex features, may be generated by applying feature engineering process 140 on selected anomalous related features form the data stored in a raw data database 110. The generated feature vectors 120 may be provided as an input to an ML modeling 130 for an increased accuracy and scalability of the ML model operation. Once the anomaly detection model gets trained, the performance of anomaly detection model may be evaluated using unseen data such as test data, which is a subset of the initial sampled data. The prediction results may be compared with fraud data in case there are enough fraud data present or, if there is not enough fraud data then transactions which are marked as anomaly may be analyzed to check what outlier behavior have affected the anomaly scoring on the test data. In case, the results are not up to the mark, then the tuning and training of the anomaly detection model e.g., operation 250 and operation 255 may start again. According to some embodiments of the present disclosure, fraud transactions, such as ‘T1’ and ‘T2’ in FIG. 3A and non-fraud transactions ‘T3’, ‘T4’ and ‘T5’ in FIG. 3A are having different distributions. The fraud distribution is denoted by 340b and non-fraud distribution is denoted by 330 b. Therefore, graph 300B demonstrates that the implementation of feature engineering such as feature engineering phase that is operated in Representative Dataset Generation (RDG) module, which is shown in FIGS. 2A-2B, distinguishes between anomalous and non-anomalous data and contributes in modeling the anomaly detection model. See Paragraphs [0063], [0064], [0103] and [0114] of Pati.
Baradaran et al. (US 2020/0067949; herein referred to as Baradaran) which teaches Misuse detection techniques can rely on a set of static network traffic patterns that have been observed before in connection with malicious use. As a result, some misuse detection techniques can be ineffective in preventing attacks or anomalous network behavior that have not been previously observed. One way to address the shortcomings of misuse detection techniques is to complement misuse detection with anomaly detection techniques, which rely on more automated approaches primarily based on machine learning. One aspect of machine learning is designing a good set of features that can capture the desired behavior. Too many features can be computationally prohibitive and/or result in overfitting, while too few would deem insufficient and/or inaccurate. Feature engineering in case of web-based anomaly detection is no exception. In this respect, the present disclosure describes techniques for modeling the intended behavior of users or applications by extracting the relevant features from various sources of data, such as web logs, access logs, gateway logs, system logs, capture files, such as pcap files, among others. The present disclosure provides systems and methods for identifying a set of features that can be used in detecting anomalous behavior in accessing web applications. These features are extracted from the network traffic and are based on individual requests and/or aggregated user behavior during an entire session. Each subset of features is designed to target a particular type of anomaly or misuse. Various sets of features can be used to identify a group of anomalous behavior. These features can be used by themselves or as a combination, depending on the characteristics of the applications for which anomalies or misuse are being detected. By profiling the normal or non-anomalous data and extracting and modeling each feature set, anomalies can be identified as a deviation from the normal behavior. See Paragraphs [0004]-[0006] of Baradaran
Accordingly, it has been determined that the claimed function above was well-known, routine and conventional prior to filing.
Looking at the limitations of the claim as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 2,
Claim 2 depends from claim 1 and inherits all the limitations of the claim from which it depends. Claim 2 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“further comprising: determining, for each time period of the one or more past time periods or a current time period, a symptom-intensity score based on at least a portion of the sensor data that corresponds to the time period, wherein the one or more features for the time period are determined using the symptom-intensity score.” further describes the abstract idea. This claim limitation is still directed to “Certain Methods of Organizing Human Activity” and therefore continues to recite an abstract idea.
Looking at the limitations of the claim as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 3,
Claim 3 depends from claim 1 and inherits all the limitations of the claim from which it depends. Claim 3 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“wherein the predicted symptom-intensity score corresponds to a predicted intensity of the one or more symptoms of Parkinson's disease.” further describes the abstract idea. This claim limitation is still directed to “Certain Methods of Organizing Human Activity” and therefore continues to recite an abstract idea.
Looking at the limitations of the claim as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 4,
Claim 4 depends from claim 1 and inherits all the limitations of the claim from which it depends. Claim 4 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“wherein the predicted symptom-intensity score corresponds to a predicted intensity of tremors or a predicted intensity of dyskinesia.” further describes the abstract idea. This claim limitation is still directed to “Certain Methods of Organizing Human Activity” and therefore continues to recite an abstract idea.
Looking at the limitations of the claim as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 5,
Claim 5 depends from claim 1 and inherits all the limitations of the claim from which it depends. Claim 5 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“wherein the sensor data comprises data collected by an accelerometer or a gyroscope.” further defines an additional element that was insufficient to provide a practical application and/or significantly more. The claim with this further defining limitation still corresponds to merely using a computer as a tool to perform an abstract idea.
Looking at the limitations of the claim as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 6,
Claim 6 depends from claim 1 and inherits all the limitations of the claim from which it depends. Claim 6 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“wherein the predicted symptom-intensity score is further generated based on medical information comprising dosage information associated with a treatment of the subject, medication time delta information, and information regarding effect of the treatment on the subject.” further describes the abstract idea. This claim limitation is still directed to “Certain Methods of Organizing Human Activity” and therefore continues to recite an abstract idea.
Looking at the limitations of the claim as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 7,
Claim 7 depends from claim 1 and inherits all the limitations of the claim from which it depends. Claim 7 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“wherein generating the predicted symptom-intensity score includes generating a trend using symptom-intensity scores corresponding to the one or more past time periods or a current time period, and wherein the predicted symptom-intensity score is based on the trend.” further describes the abstract idea. This claim limitation is still directed to “Certain Methods of Organizing Human Activity” and therefore continues to recite an abstract idea.
Looking at the limitations of the claim as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 8,
Claim 8 depends from claim 1 and inherits all the limitations of the claim from which it depends. Claim 8 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“wherein the predicted symptom-intensity score is further generated based on multi-modal data comprising the sensor data, medical information, and mobility metrics of the subject.” further describes the abstract idea. This claim limitation is still directed to “Certain Methods of Organizing Human Activity” and therefore continues to recite an abstract idea.
Looking at the limitations of the claim as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 9,
Claim 9 is substantially similar to claim 1. Accordingly, claim 9 is rejected for the same reasons as claim 1.
As per claim 10,
Claim 10 is substantially similar to claim 3. Accordingly, claim 10 is rejected for the same reasons as claim 3.
As per claim 11,
Claim 11 is substantially similar to claim 4. Accordingly, claim 11 is rejected for the same reasons as claim 4.
As per claim 12,
Claim 12 is substantially similar to claim 5. Accordingly, claim 12 is rejected for the same reasons as claim 5.
As per claim 13,
Claim 13 is substantially similar to claim 6. Accordingly, claim 13 is rejected for the same reasons as claim 6.
As per claim 14,
Claim 14 is substantially similar to claim 7. Accordingly, claim 14 is rejected for the same reasons as claim 7.
As per claim 15,
Claim 15 is substantially similar to claim 1. Accordingly, claim 15 is rejected for the same reasons as claim 1.
As per claim 16,
Claim 16 is substantially similar to claim 2. Accordingly, claim 16 is rejected for the same reasons as claim 2.
As per claim 17,
Claim 17 is substantially similar to claim 3. Accordingly, claim 17 is rejected for the same reasons as claim 3.
As per claim 18,
Claim 18 is substantially similar to claim 6. Accordingly, claim 18 is rejected for the same reasons as claim 6.
As per claim 19,
Claim 19 is substantially similar to claim 7. Accordingly, claim 19 is rejected for the same reasons as claim 7.
As per claim 20,
Claim 20 is substantially similar to claim 8. Accordingly, claim 20 is rejected for the same reasons as claim 8.
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.
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 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Kapur et al. (US 2024/0185997; herein referred to as Kapur) in view of Pati.
As per claim 1,
Kapur teaches computer-implemented method comprising: obtaining sensor data associated with a subject:
(Paragraph [0003] of Kapur. The teaching describes a computer-implemented method that includes receiving, at a first time during a clinical exam and from a wearable sensor system, first sensor data indicative of a first patient activity.)
Kapur further teaches extracting, for each time period of one or more past time periods or a current time period, one or more features based on the sensor data:
(Paragraph [0006] of Kapur. The teaching describes identifying an annotating non-exam activities during monitoring of a patient in a free-living setting. The computer-implemented method includes receiving, at an input device of a wearable user device, a first user input identifying a beginning of a first time period in which a virtual motor exam (VME) is conducted and receiving, at the input device of the wearable user device, a second user input identifying an end of the first time period. The computer-implemented method also includes accessing, by the wearable user device and based on the VME, first signal data output by a first sensor of the wearable user device during the first time period.)
Kapur further teaches generating, using the extracted one or more features in a specific time frame, a predicted symptom-intensity score for one or more symptoms of the subject using a symptom-forecasting model, wherein the symptom-forecasting model includes a machine learning model that is deployed using an edge AI on a user device, and the machine learning model uses: power at each of one or more frequency bands as a proxy to calculate a symptom intensity score based on: the one or more features corresponding to the current time period, or the previously extracted features associated with the past time periods, the power is identified by transforming the sensor data into frequency-space data, wherein the predicted symptom-intensity score represents a predicted intensity of the one or more symptoms during a future time period:
(Paragraphs [0071], [0088], [0121] and [0131] of Kapur. The teaching describes training a second machine-learning algorithm using the second sensor data and the second annotation. The second machine-learning algorithm may be of a similar or identical type to the first machine-learning algorithm described above, and with the additional training data from the second sensor data and the second annotations, the second machine-learning algorithm may produce additional annotations, more accurate annotations, and further be capable of identifying activities associated with the VME, or other tasks, without input from the user indicating the start of a task. The second machine-learning algorithm may receive inputs of the sensor data, time, activity data, or any other suitable data corresponding to actions, activities, and free living environments. The second machine-learning algorithm may be trained using the second annotations, the sensor data, and any additional data, such as the time of day, location data, and activity data, such as to recognize correlations between the sensor data and other aspects of their daily lives. For example, the second machine learning algorithm may receive sensor data and then annotations from the first machine-learning algorithm, along with time information. The second machine-learning algorithm may encode such data into a latent space, which may enable it to populate the latent space over time and develop the ability to predict user activity based on the encoded data. For example, over time, the second machine-learning algorithm may develop a latent space that indicates that the user has more significant tremors in the morning, but that they abate over the course of the day, or that the tremors are associated with particular movements. In this manner, the second machine-learning algorithm may be trained to identify patterns and long-term trends in symptoms and conditions for the user. A task requiring the user to hold hands still in their lap may have varying results over time and receive different ratings, the machine-learning algorithm may identify that sensor data indicating higher amplitude or frequency of tremors may receive a lower rating while more steady sensor data (with respect to accelerometer data) may receive a higher rating. The user device 102 includes one or more processor units 106 that are configured to access a memory 108 having instructions stored thereon. The processor units 106 of FIG. 1 may be implemented as any electronic device capable of processing, receiving, or transmitting data or instructions. For example, the processor units 106 may include one or more of: a microprocessor, a central processing unit (CPU), an application-specific integrated circuit (ASIC), a digital signal processor (DSP), or combinations of such devices. The service provider 204 may be any suitable computing device (e.g., personal computer, handheld device, server computer, server cluster, virtual computer) configured to execute computer-executable instructions to perform operations such as those described herein. This is construed to mean that the machine learning models disclosed are executed at the local device level consistent with an edge AI implementation.)
Kapur further teaches outputting a result based on the predicted symptom-intensity score, wherein the result provides a basis for a recommendation or includes the recommendation to perform an intervening action to avoid symptoms in accordance with the predicted symptom-intensity score:
(Paragraph [0132] of Kapur. The teaching describes generating, using the second machine-learning algorithm, a third annotation associated with an activity. The second machine-learning algorithm may enable identification of longer term patterns, trends, and correlations between certain activities, times of days, and other triggers for symptoms or conditions. The second machine-learning algorithm may generate third annotations corresponding to sensor data gathered while the user wears the user device 102 but outside of a clinical or VME setting and may therefore provide insights into longer term trends, triggers, or other patterns associated with various symptoms of a user. This is enabled by identifying longer terms trends and triggers by identifying portions of sensor data identified by similarity with previously tagged sensor data and subsequently identifying further data over a longer period of time to identify additional triggers for particular symptoms or times of day when a condition may be especially difficult for a user. The third annotations may be more expansive than the first and second annotations and may annotate the sensor data outside of the indicated times when a user performed a VME task. For instance, in the exemplary illustration above, a user may sit with their hands in their lap in a manner similar to a VME task without intentionally performing a VME task. The second machine-learning algorithm may first identify periods of activities similar to VME or clinical tasks. The second machine-learning algorithm, or an additional machine-learning algorithm, may then generate the third annotations corresponding to contexts, performance, and other information related to the tasks to append to the sensor data. This output of a third annotation provides a basis for a recommendation.)
Kapur does not explicitly teach streaming the one or more features to a feature-lag buffer, wherein the one or more features corresponding to the one or more past time periods comprises previously extracted features.
However, Pati teaches streaming the one or more features to a feature-lag buffer, wherein the one or more features corresponding to the one or more past time periods comprises previously extracted features
(Paragraphs [0063], [0064], [0103] and [0114] of Pati. The teaching describes a feature engineering process 100 construed to be a feature-lag buffer. According to some embodiment of the present disclosure, feature vectors 120 such as complex features, may be generated by applying feature engineering process 140 on selected anomalous related features form the data stored in a raw data database 110. The generated feature vectors 120 may be provided as an input to an ML modeling 130 for an increased accuracy and scalability of the ML model operation. Once the anomaly detection model gets trained, the performance of anomaly detection model may be evaluated using unseen data such as test data, which is a subset of the initial sampled data. The prediction results may be compared with fraud data in case there are enough fraud data present or, if there is not enough fraud data then transactions which are marked as anomaly may be analyzed to check what outlier behavior have affected the anomaly scoring on the test data. In case, the results are not up to the mark, then the tuning and training of the anomaly detection model e.g., operation 250 and operation 255 may start again. According to some embodiments of the present disclosure, fraud transactions, such as ‘T1’ and ‘T2’ in FIG. 3A and non-fraud transactions ‘T3’, ‘T4’ and ‘T5’ in FIG. 3A are having different distributions. The fraud distribution is denoted by 340b and non-fraud distribution is denoted by 330 b. Therefore, graph 300B demonstrates that the implementation of feature engineering such as feature engineering phase that is operated in Representative Dataset Generation (RDG) module, which is shown in FIGS. 2A-2B, distinguishes between anomalous and non-anomalous data and contributes in modeling the anomaly detection model. See Paragraphs [0063], [0064], [0103] and [0114] of Pati.
It would have been obvious to one of ordinary skill in the art before the time of filing to add to the machine learning methods of Kapur, the feature engineering feature-lag buffer of Pati. Paragraph [0046] of Pati describes that the feature engineering disclosed provides for improved features of data sets provided to machine learning models. One of ordinary skill in the art in possession of Kapur would have looked to Pati to achieve this improvement in anomaly detection in machine learning models. One of ordinary skill in the art would have added to Kapur, the teaching of Pati based on this incentive without yielding unexpected results.
As per claim 2,
The combined teaching of Kapur and Pati teaches the limitations of claim 1.
Kapur further teaches further comprising: determining, for each time period of one or more past time periods or a current time period, a symptom-intensity score based on at least a portion of the sensor data that corresponds to the time period, wherein the one or more features for the time period are determined using the symptom-intensity score:
(Paragraph [0131] of Kapur. The teaching describes training a second machine-learning algorithm using the second sensor data and the second annotation. The second machine-learning algorithm may be of a similar or identical type to the first machine-learning algorithm described above, and with the additional training data from the second sensor data and the second annotations, the second machine-learning algorithm may produce additional annotations, more accurate annotations, and further be capable of identifying activities associated with the VME, or other tasks, without input from the user indicating the start of a task. The second machine-learning algorithm may receive inputs of the sensor data, time, activity data, or any other suitable data corresponding to actions, activities, and free living environments. The second machine-learning algorithm may be trained using the second annotations, the sensor data, and any additional data, such as the time of day, location data, and activity data, such as to recognize correlations between the sensor data and other aspects of their daily lives. For example, the second machine learning algorithm may receive sensor data and then annotations from the first machine-learning algorithm, along with time information. The second machine-learning algorithm may encode such data into a latent space, which may enable it to populate the latent space over time and develop the ability to predict user activity based on the encoded data. For example, over time, the second machine-learning algorithm may develop a latent space that indicates that the user has more significant tremors in the morning, but that they abate over the course of the day, or that the tremors are associated with particular movements. In this manner, the second machine-learning algorithm may be trained to identify patterns and long-term trends in symptoms and conditions for the user.)
As per claim 3,
The combined teaching of Kapur and Pati teaches the limitations of claim 1.
Kapur further teaches wherein the predicted symptom-intensity score corresponds to a predicted intensity of the one or more symptoms of Parkinson's disease:
(Paragraph [0032] of Kapur. The teaching describes a sensor-based remote monitoring may help health care professionals better track disease progression such as in Parkinson's disease (PD), and measure users' response to putative disease-modifying therapeutic interventions)
As per claim 4,
The combined teaching of Kapur and Pati teaches the limitations of claim 1.
Kapur further teaches wherein the predicted symptom-intensity score corresponds to a predicted intensity of tremors or a predicted intensity of dyskinesia:
(Paragraph [0131] of Kapur. The teaching describes training a second machine-learning algorithm using the second sensor data and the second annotation. The second machine-learning algorithm may be of a similar or identical type to the first machine-learning algorithm described above, and with the additional training data from the second sensor data and the second annotations, the second machine-learning algorithm may produce additional annotations, more accurate annotations, and further be capable of identifying activities associated with the VME, or other tasks, without input from the user indicating the start of a task. The second machine-learning algorithm may receive inputs of the sensor data, time, activity data, or any other suitable data corresponding to actions, activities, and free living environments. The second machine-learning algorithm may be trained using the second annotations, the sensor data, and any additional data, such as the time of day, location data, and activity data, such as to recognize correlations between the sensor data and other aspects of their daily lives. For example, the second machine learning algorithm may receive sensor data and then annotations from the first machine-learning algorithm, along with time information. The second machine-learning algorithm may encode such data into a latent space, which may enable it to populate the latent space over time and develop the ability to predict user activity based on the encoded data. For example, over time, the second machine-learning algorithm may develop a latent space that indicates that the user has more significant tremors in the morning, but that they abate over the course of the day, or that the tremors are associated with particular movements. In this manner, the second machine-learning algorithm may be trained to identify patterns and long-term trends in symptoms and conditions for the user.)
As per claim 5,
The combined teaching of Kapur and Pati teaches the limitations of claim 1.
Kapur further teaches wherein the sensor data comprises data collected by an accelerometer or a gyroscope:
(Paragraph [0044] of Kapur. The teaching describes that during execution of PD-VME tasks, tri-axial accelerometer and gyroscope data was collected at a sample rate of 200 Hz.)
As per claim 6,
The combined teaching of Kapur and Pati teaches the limitations of claim 1.
Kapur further teaches wherein the predicted symptom-intensity score is further generated based on medical information comprising dosage information associated with a treatment of the subject, medication time delta information, and information regarding effect of the treatment on the subject:
(Paragraph [0066] of Kapur. The teaching describes that dopaminergic medication can considerably improve severity of motor signs over short time frames. This “on-off” difference is well-accepted as a clinically meaningful change, and when coupled with wearable sensors and user-reported tagging of daily medication regimen, creates multiple “natural experiments” in the course of users' daily lives. These may allow testing of the clinical validity of the PD-VME measures as pharmacodynamic/response biomarkers for people with PD in the remote setting. Indeed, digital measures for tremor, upper-extremity bradykinesia and gait may be able to detect significant change in users' motor signs before and after medication intake. These pharmacodynamic/response biomarkers are construed to include dosages, time deltas and effect of the treatment.)
As per claim 7,
The combined teaching of Kapur and Pati teaches the limitations of claim 1.
Kapur further teaches wherein generating the predicted symptom-intensity score includes generating a trend using symptom-intensity scores corresponding to the one or more period of one or more past time periods or a current time period, and wherein the predicted symptom-intensity score is based on the trend:
(Paragraph [0131] of Kapur. The teaching describes training a second machine-learning algorithm using the second sensor data and the second annotation. The second machine-learning algorithm may be of a similar or identical type to the first machine-learning algorithm described above, and with the additional training data from the second sensor data and the second annotations, the second machine-learning algorithm may produce additional annotations, more accurate annotations, and further be capable of identifying activities associated with the VME, or other tasks, without input from the user indicating the start of a task. The second machine-learning algorithm may receive inputs of the sensor data, time, activity data, or any other suitable data corresponding to actions, activities, and free living environments. The second machine-learning algorithm may be trained using the second annotations, the sensor data, and any additional data, such as the time of day, location data, and activity data, such as to recognize correlations between the sensor data and other aspects of their daily lives. For example, the second machine learning algorithm may receive sensor data and then annotations from the first machine-learning algorithm, along with time information. The second machine-learning algorithm may encode such data into a latent space, which may enable it to populate the latent space over time and develop the ability to predict user activity based on the encoded data. For example, over time, the second machine-learning algorithm may develop a latent space that indicates that the user has more significant tremors in the morning, but that they abate over the course of the day, or that the tremors are associated with particular movements. In this manner, the second machine-learning algorithm may be trained to identify patterns and long-term trends in symptoms and conditions for the user.)
As per claim 8,
The combined teaching of Kapur and Pati teaches the limitations of claim 1.
Kapur further teaches wherein the predicted symptom-intensity score is further generated based on multi-modal data comprising the sensor data, medical information, and mobility metrics of the subject:
(Paragraph [0044] of Kapur. The teaching describes that during execution of PD-VME tasks, tri-axial accelerometer and gyroscope [multi-modal] data was collected at a sample rate of 200 Hz.)
(Paragraph [0066] of Kapur. The teaching describes that dopaminergic medication can considerably improve severity of motor signs over short time frames. This “on-off” difference is well-accepted as a clinically meaningful change, and when coupled with wearable sensors and user-reported tagging of daily medication regimen, creates multiple “natural experiments” in the course of users' daily lives. These may allow testing of the clinical validity of the PD-VME measures as pharmacodynamic/response biomarkers for people with PD in the remote setting. Indeed, digital measures for tremor, upper-extremity bradykinesia and gait may be able to detect significant change in users' motor signs before and after medication intake [medical information].)
(Paragraph [0131] of Kapur. The teaching describes training a second machine-learning algorithm using the second sensor data and the second annotation. The second machine-learning algorithm may be of a similar or identical type to the first machine-learning algorithm described above, and with the additional training data from the second sensor data and the second annotations, the second machine-learning algorithm may produce additional annotations, more accurate annotations, and further be capable of identifying activities associated with the VME, or other tasks, without input from the user indicating the start of a task. The second machine-learning algorithm may receive inputs of the sensor data, time, activity data, or any other suitable data corresponding to actions, activities [mobility metrics], and free living environments. The second machine-learning algorithm may be trained using the second annotations, the sensor data, and any additional data, such as the time of day, location data, and activity data, such as to recognize correlations between the sensor data and other aspects of their daily lives. For example, the second machine learning algorithm may receive sensor data and then annotations from the first machine-learning algorithm, along with time information. The second machine-learning algorithm may encode such data into a latent space, which may enable it to populate the latent space over time and develop the ability to predict user activity based on the encoded data. For example, over time, the second machine-learning algorithm may develop a latent space that indicates that the user has more significant tremors in the morning, but that they abate over the course of the day, or that the tremors are associated with particular movements. In this manner, the second machine-learning algorithm may be trained to identify patterns and long-term trends in symptoms and conditions for the user.)
As per claim 9,
Claim 9 is substantially similar to claim 1. Accordingly, claim 9 is rejected for the same reasons as claim 1.
As per claim 10,
Claim 10 is substantially similar to claim 3. Accordingly, claim 10 is rejected for the same reasons as claim 3.
As per claim 11,
Claim 11 is substantially similar to claim 4. Accordingly, claim 11 is rejected for the same reasons as claim 4.
As per claim 12,
Claim 12 is substantially similar to claim 5. Accordingly, claim 12 is rejected for the same reasons as claim 5.
As per claim 13,
Claim 13 is substantially similar to claim 6. Accordingly, claim 13 is rejected for the same reasons as claim 6.
As per claim 14,
Claim 14 is substantially similar to claim 7. Accordingly, claim 14 is rejected for the same reasons as claim 7.
As per claim 15,
Claim 15 is substantially similar to claim 1. Accordingly, claim 15 is rejected for the same reasons as claim 1.
As per claim 16,
Claim 16 is substantially similar to claim 2. Accordingly, claim 16 is rejected for the same reasons as claim 2.
As per claim 17,
Claim 17 is substantially similar to claim 3. Accordingly, claim 17 is rejected for the same reasons as claim 3.
As per claim 18,
Claim 18 is substantially similar to claim 6. Accordingly, claim 18 is rejected for the same reasons as claim 6.
As per claim 19,
Claim 19 is substantially similar to claim 7. Accordingly, claim 19 is rejected for the same reasons as claim 7.
As per claim 20,
Claim 20 is substantially similar to claim 8. Accordingly, claim 20 is rejected for the same reasons as claim 8.
Response to Arguments
Applicant's arguments filed June 29, 2026 have been fully considered.
Applicant’s arguments pertaining to rejections made under 35 U.S.C. 101 are not persuasive.
The Applicant argues that the pending claims provide a particular machine-implemented process with the recitation of the edge AI implementation as opposed to a generic deployment of technology.
The Examiner respectfully disagrees. The implementation of an AI model at edge level usage merely defines where the AI model is stored and executed. As opposed to running on a remote server, the model would be executed on local hardware. The Examiner is not convinced that such an implementation would amount to a particular machine as it is defined by the MPEP. The MPEP is primarily concerned with hardware configuration and type when it considers what a particular machine is. MPEP 2106.05(b). Software, as is the case with edge AI implementation, does not appear to be a relevant factor in establishing a “particular machine”.
The Applicant further argues that combination of edge AI and streaming the features associated with the patient time periods in feature-lag buffer amounts to a technical improvement by improving accuracy and timeliness of monitoring and predicting symptoms of a neurodegenerative disorder to enable timely intervention.
The Examiner respectfully disagrees. In the Examiner’s understanding, the element of a “feature-lag buffer” is a form of feature engineering wherein such methods are aimed at providing more accurate pattern recognition in a time series. Such feature engineering methods have been shown to be well-known, routine and conventional as evidenced by the references in the rejection above. It would appear that the applicant has implemented known methods of feature engineering to apply them to the specific field of detecting neurodegenerative diseases. It does not appear that the technical field of feature engineering has advanced as much as it has been applied to this specific implementation. The combination of this feature engineering process with AI techniques do not appear to enhance the field of feature engineering when the AI implementation, even edge AI, is claimed at such a high level of generality. The edge AI is being used in little more than a nominal feature. Accordingly, the Examiner is not convinced that technology is being improved at the level claimed.
Applicant’s arguments pertaining to rejections made under 35 U.S.C. 102 are persuasive. These rejections have been withdrawn.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHAD A NEWTON whose telephone number is (313)446-6604. The examiner can normally be reached M-F 8:00AM-4:00PM (EST).
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, PETER H. CHOI can be reached at (469) 295-9171. 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.
/CHAD A NEWTON/Primary Examiner, Art Unit 3681
Prosecution Insights