DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 06/06/2026 has been entered.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 04/29/2026 was filed. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Response to Arguments
Applicant's arguments filed claims 1-20 have been fully considered but they are not persuasive.
In regard to Applicant stating Examiner fails to make a prima facia case, examiner would like to point out that both Lee and Modi are analyzing behaviors. With the reasoning of the obviousness of combining the prior art is to allow for better accuracy. (see Modi paragraph 0032).
Applicant also argues that the limitation “based on predicted future behavior, trigger real-time communication to user” is not taught by the prior art. Examiner would like to point out that Modi teaches that the data produced may be predicted by the model, and then the monitoring system can issue an alert such as email, SMS, a phone call, etc. This alert is interpreted as the communication to the user.
Specifically:
based on the predicted future behavior, trigger a real-time communication to the user. (Modi, paragraph 0019, “By combining historical and live data, meaningful insights can be generated close to real time.” And paragraph 0199, “This may be used to identify abnormal and/or malicious human interactions with the client system 100. The second layer of statistical learning may be provided by clustering users based on the data produced by the individual modules. Changes in the clusters may be detected, and/or associations can be made between clusters. The change in the data produced by the individual modules may be modelled over time. The data produced by the individual modules may also be dynamically weighted, and/or the data produced by the individual modules may be predicted [predicted future behavior].”) and paragraph 0223, “Where a particular event (or combination of events) is detected as it is occurring, the monitoring system 200 may be able to issue an alert via email, SMS, phone call or virtual assistant or another communication means. The system 200, if appropriately configured, may also be able to automatically implement one or more as actions in response to a particular event or combination of events.”)
Applicant also argues that Lee does not teach “process the extracted content from the transformed interaction data for the group of users using a classification algorithm configured to label the interaction data;”. Examiner would like to point out that the transformed data is the specified input data from the input image which is then labeled being interpreted as classification.
Specifically:
process the extracted content from the transformed interaction data for the group of users using a classification algorithm configured to label the interaction data; (Lee, paragraph 0052, “For example, in a patient treatment recommendation cognitive system, the labeled data may comprise labels, tags, or annotations that specify various medical concepts with which the data is associated, e.g., a disease, a treatment, a patient's age, a patient's gender, etc b[the group of users using ]. In the depicted example, the operation of the neural network model 230 is to classify a portion of an input image specified in a set of input data 220 into one of 10 categories representing numerical values that the portion of the input image represents, e.g., classes "O" to "9".”)
Next, Applicant argues that Lee and Modi do not teach making the data clean and vectorized. Examiner would like to point out that Lee teaches using data that data is processed in order for then after the second set of output nodes it can be vectorized allowing for the data to be cleaned up and classified correctly.
Specifically:
wherein transforming the interaction data comprises cleaning and vectorizing the data thereby improving the accessibility of the data so that an accessing classification machine learning model is able to process the transformed data more quickly than the accessing classification machine learning model is able to process the received interaction data; (Lee, paragraph 0004, “Neural network based deep learning is a class of machine learning algorithms that use a cascade of many layers of nonlinear processing units for feature extraction and transformation. Each successive layer uses the output from the previous layer as input. The algorithms may be supervised or unsupervised and applications include pattern analysis (unsupervised) and classification (supervised). Neural network based deep learning is based on the learning of multiple levels of features or representations of the data with higher level features being derived from lower level features to form a hierarchical representation.” And paragraph 0030, “Thus, after training the new protected model using these three sets of training data, an additional layer of nodes, referred to as the merge layer having merge nodes, is added to the new protected model to merge the first half and second half of the output nodes by joining the adversarially trained class, i.e., the classification output vector generated by the second set of output nodes, to its original class, i.e. the classification output vector generated by the first set of output nodes, so that the regular data samples in the first set of training data, and the adversarially generated data samples in the third set of training data, are correctly classified [interaction data comprises cleaning and vectorizing the data thereby improving the accessibility of the data].”)
However, the previously used prior art Lee and Modi have been remapped to teach the amended features.
Specifically:
process each user’s one or more segments by a second machine learning algorithm comprising a neural network, the second algorithm configured to make a prediction of future behavior; (Lee, paragraph 0055, “The labeled data 240 is then input to the cognitive system 250 for performance of cognitive operations on the labeled data 240. The particular cognitive operation performed by the cognitive system 250 depends on the cognitive system and may be any of a plethora of different types of cognitive operations. Examples of cognitive operations include various types of decision making operations or decision support operations, such as security system based operations for controlling access to facilities, data, or any other secure asset. Such security system cognitive operations may employ the labeled data 240 to perform facial recognition, voice print recognition, biometrics based decision making, or the like.” And paragraph 0056, “As shown in FIG. 2B, assuming that the data source 210 is an attacker 210 performing a white box gradient based attack, such as an evasion attack, the attacker 210 may attempt to cause the neural network [by a second machine learning algorithm comprising a neural network] 230 to misclassify the input data 220 by modifying the input data 220 to include imperceptible manipulations on the input data 220 and thereby generate adversarial input 270.” And paragraph 0091, “Predict and sense with situational awareness that mimic human cognition based on experiences [prediction of future behavior, examiner would like to point out that this predicting is happening with natural language which is being interpreted as the user segments.]”). Lee teaches using a neural network to label unlabeled data.
receive user information for the group of users, wherein the user information comprises user demographics including age and location; (Modi, paragraph 0005, “receiving metadata from one or more devices within the one or more monitored computer systems; identifying from the metadata events corresponding to a plurality of user interactions [user information for the group of users] with the monitored computer systems;” and paragraph 0192, “The contextual data 40 includes psychology- related data that is integrated into the monitoring system 200 by modelling qualitative studies into chains of possible events/intentions with various probabilities based on parameters like age, gender, cultural background, role in the organisation, and personality type.” And paragraph 0206, “User-related attributes may comprise distributions of activity types by time and/or location or a record of activity over a recent period ( such as a 30 day sliding window average of user activity).”) Modi teaches user attributes including age and location of the user.
Therefore the 35 USC 103 rejection is maintained.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or non-obviousness.
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 1-6, 8-12 and 14-19 are rejected under 35 U.S.C. 103 as being unpatentable over Lee et al (US Published Patent Application No. 20190130110, "Lee") [May 2, 2019], in view of Modi et al (US Published Patent Application No. 20180246797, "Modi") [Aug. 30, 2018].
In regard to claim 1, Lee teaches A system for using serially applied machine learning models to process labeled data to trigger concurrent transmission, thereby maximizing system processing efficiency, the system comprising: (Lee, paragraph 0006, “In one illustrative embodiment, a method is provided, in a data processing system comprising a processor and a memory, the memory comprising instructions which are executed by the processor to specifically configure the processor to implement a hardened neural network. The method comprises configuring the hardened neural network executing in the data processing system to introduce noise in internal feature representations of the hardened neural network.”)
at least one processor; (Lee, paragraph 0006, In one illustrative embodiment, a method is provided, in a data processing system comprising a processor and a memory, the memory comprising instructions which are executed by the processor to specifically configure the processor to implement a hardened neural network.”)
a communication interface communicatively coupled to the at least one processor; and (Lee, paragraph 0100, “The cognitive system 400 is implemented on one or more computing devices 304A-D ( comprising one or more processors and one or more memories, and potentially any other computing device elements generally known in the art including buses, storage devices, communication interfaces, and the like) connected to the computer network 402.”)
a memory device storing executable code that, when executed, causes the at least one processor to: (Lee, paragraph 0006, “In one illustrative embodiment, a method is provided, in a data processing system comprising a processor and a memory, the memory comprising instructions which are executed by the processor to specifically configure the processor to implement a hardened neural network.”)
receive interaction data for a group of users, wherein the interaction data comprises unclean interaction data and unvectorized interaction data that is slow to process using a classification machine learning model; (Lee, paragraph 0023, “In addressing these issues and providing such mechanisms, the illustrative embodiments, rather than using a classifier to identify an adversarial input, directly hinders proper gradient computation by adding noise [unclean interaction data and unvectorized interaction data], ]in the model itself, e.g., noise in the internal feature representations of the neural network itself [[slow to process using a classification machine learning model;] ], such that gradient computations are diverted.” And paragraph 0101, “The cognitive system 400 is configured to implement a request processing pipeline 408 that receive inputs from various sources [receive interaction data for a group of users]. The requests may be posed in the form of a natural language question, natural language request for information, natural language request for the performance of a cognitive operation, or the like. Alternatively, the "request" may simply be the input of data that is intended to be operated on by the cognitive system e.g., images, text, audio input, or the like, which is to be classified by the hardened model of the illustrative embodiments and then operated on by cognitive processes to generate a result of a cognitive operation.”)
wherein transforming the interaction data comprises cleaning and vectorizing the data thereby improving the accessibility of the data so that an accessing classification machine learning model is able to process the transformed data more quickly than the accessing classification machine learning model is able to process the received interaction data; (Lee, paragraph 0004, “Neural network based deep learning is a class of machine learning algorithms that use a cascade of many layers of nonlinear processing units for feature extraction and transformation. Each successive layer uses the output from the previous layer as input. The algorithms may be supervised or unsupervised and applications include pattern analysis (unsupervised) and classification (supervised). Neural network based deep learning is based on the learning of multiple levels of features or representations of the data with higher level features being derived from lower level features to form a hierarchical representation.” And paragraph 0030, “Thus, after training the new protected model using these three sets of training data, an additional layer of nodes, referred to as the merge layer having merge nodes, is added to the new protected model to merge the first half and second half of the output nodes by joining the adversarially trained class, i.e., the classification output vector generated by the second set of output nodes, to its original class, i.e. the classification output vector generated by the first set of output nodes, so that the regular data samples in the first set of training data, and the adversarially generated data samples in the third set of training data, are correctly classified [interaction data comprises cleaning and vectorizing the data thereby improving the accessibility of the data].”)
process the extracted content from the transformed interaction data for the group of users using a classification algorithm configured to label the interaction data; (Lee, paragraph 0052, “For example, in a patient treatment recommendation cognitive system, the labeled data may comprise labels, tags, or annotations that specify various medical concepts with which the data is associated, e.g., a disease, a treatment, a patient's age, a patient's gender, etc b[the group of users using ]. In the depicted example, the operation of the neural network model 230 is to classify a portion of an input image specified in a set of input data 220 into one of 10 categories representing numerical values that the portion of the input image represents, e.g., classes "O" to "9".”)
receive a result from the classification algorithm, wherein the result comprises labeled interaction data; (Lee, paragraph 0052, “For example, in a patient treatment recommendation cognitive system, the labeled data may comprise labels, tags, or annotations that specify various medical concepts with which the data is associated, e.g., a disease, a treatment, a patient's age, a patient's gender, etc. In the depicted example, the operation of the neural network model 230 is to classify a portion of an input image specified in a set of input data 220 into one of 10 categories representing numerical values that the portion of the input image represents, e.g., classes "O" to "9".”)
correlate the labeled interaction data with the user information to create a correlated dataset; (Lee, paragraph 0052, “For example, in a patient treatment recommendation cognitive system, the labeled data may comprise labels, tags, or annotations that specify various medical concepts with which the data is associated, e.g., a disease, a treatment, a patient's age, a patient's gender, etc. In the depicted example, the operation of the neural network model 230 is to classify a portion of an input image specified in a set of input data 220 into one of 10 categories representing numerical values that the portion of the input image represents, e.g., classes "O" to "9".”)
process the correlated dataset by a first machine learning algorithm configured to segment users of the group of users into a plurality of segments; (Lee, paragraph 0052, “For example, in a patient treatment recommendation cognitive system, the labeled data may comprise labels, tags, or annotations that specify various medical concepts with which the data is associated, e.g., a disease, a treatment, a patient's age, a patient's gender, etc [the group of users using ]. In the depicted example, the operation of the neural network model 230 is to classify a portion of an input image specified in a set of input data 220 into one of 10 categories representing numerical values that the portion of the input image represents, e.g., classes "O" to "9".”)
receive a second result, wherein the second result is one or more segments for each user of the group of users; (Lee, paragraph 0052, “labeled data set 240 is a set of output data generated by the trained neural network model 230 where the unlabeled input data is augmented with additional tags or labels of meaningful information for the particular cognitive operation for which the data is to be used. For example, in a patient treatment recommendation cognitive system, the labeled data may comprise labels, tags, or annotations that specify various medical concepts with which the data is associated, e.g., a disease, a treatment, a patient's age, a patient's gender, etc [the group of users using] In the depicted example, the operation of the neural network model 230 is to classify a portion of an input image specified in a set of input data 220 into one of 10 categories representing numerical values that the portion of the input image represents, e.g., classes "O" to "9".”)
process each user’s one or more segments by a second machine learning algorithm comprising a neural network, the second algorithm configured to make a prediction of future behavior; (Lee, paragraph 0055, “The labeled data 240 is then input to the cognitive system 250 for performance of cognitive operations on the labeled data 240. The particular cognitive operation performed by the cognitive system 250 depends on the cognitive system and may be any of a plethora of different types of cognitive operations. Examples of cognitive operations include various types of decision making operations or decision support operations, such as security system based operations for controlling access to facilities, data, or any other secure asset. Such security system cognitive operations may employ the labeled data 240 to perform facial recognition, voice print recognition, biometrics based decision making, or the like.” And paragraph 0056, “As shown in FIG. 2B, assuming that the data source 210 is an attacker 210 performing a white box gradient based attack, such as an evasion attack, the attacker 210 may attempt to cause the neural network [by a second machine learning algorithm comprising a neural network] 230 to misclassify the input data 220 by modifying the input data 220 to include imperceptible manipulations on the input data 220 and thereby generate adversarial input 270.” And paragraph 0091, “Predict and sense with situational awareness that mimic human cognition based on experiences [prediction of future behavior, examiner would like to point out that this predicting is happening with natural language which is being interpreted as the user segments.]”).
receive, for each user, a predicted future behavior from the second machine learning algorithm; (Lee, paragraph 0019, “Often times, such neural networks, and other types of machine learning or cognitive models, are utilized in or with cognitive systems to perform a classification operation upon which the cognitive system operates to perform a cognitive operation, e.g., classifying an input into one of a plurality of predetermined classifications (classes) which is then used to perform a more complex analysis or reasoning operation using cognitive system mechanisms.” And paragraph 0091, “Predict and sense with situational awareness that mimic human cognition based on experiences [prediction of future behavior examiner would like to point out that this predicting is happening with natural language which is being interpreted as the user segments.]”)
Lee does not explicitly teach extract content from the transformed interaction data;
receive user information for the group of users, wherein the user information comprises user demographics including age and location;
based on the predicted future behavior, trigger a real-time communication to the user.
However, Modi teaches extract content from the transformed interaction data; (Modi, paragraph 0175, “normalisation process is then used to transform the log files 10 (which may be in various different formats) into generic normalised metadata or log files 20. The normalization process operates by modelling any human interaction with the client system 100 by breaking it down into discrete events. These events are identified from the content of the log files 10. A schema for each data source used in the network 1000 is defined so that any log file 10 from a known data source in the network 1000 has an identifiable structure, and 'events' and other associated parameters (which may, for example, be metadata related to the events) may be easily identified and be transposed into the schema for the normalized log files 20.”)
receive user information for the group of users, wherein the user information comprises user demographics including age and location; (Modi, paragraph 0005, “receiving metadata from one or more devices within the one or more monitored computer systems; identifying from the metadata events corresponding to a plurality of user interactions [user information for the group of users] with the monitored computer systems;” and paragraph 0192, “The contextual data 40 includes psychology- related data that is integrated into the monitoring system 200 by modelling qualitative studies into chains of possible events/intentions with various probabilities based on parameters like age, gender, cultural background, role in the organisation, and personality type.” And paragraph 0206, “User-related attributes may comprise distributions of activity types by time and/or location or a record of activity over a recent period ( such as a 30 day sliding window average of user activity).”)
based on the predicted future behavior, trigger a real-time communication to the user. (Modi, paragraph 0019, “By combining historical and live data, meaningful insights can be generated close to real time.” And paragraph 0199, “This may be used to identify abnormal and/or malicious human interactions with the client system 100. The second layer of statistical learning may be provided by clustering users based on the data produced by the individual modules. Changes in the clusters may be detected, and/or associations can be made between clusters. The change in the data produced by the individual modules may be modelled over time. The data produced by the individual modules may also be dynamically weighted, and/or the data produced by the individual modules may be predicted [predicted future behavior].”) and paragraph 0223, “Where a particular event (or combination of events) is detected as it is occurring, the monitoring system 200 may be able to issue an alert via email, SMS, phone call or virtual assistant or another communication means. The system 200, if appropriately configured, may also be able to automatically implement one or more as actions in response to a particular event or combination of events.”)
Lee and Modi are related to the same field of endeavor (i.e. evaluating user behavior). In view of the teachings of Modi, it would have been obvious for a person with ordinary skill in the art to apply the teachings of Modi to Lee before the effective filing date of the claimed invention in order to have better accuracy. (Modi, paragraph 0032, “Updating the model in this way can enable the inclusion of further information into the probabilistic model for better accuracy.”)
In regard to claim 2 and analogous claim 15, Lee and Modi teach the system of claim 1.
Modi further teaches wherein the executable code further causes the processor to trigger a concurrent update to a user dashboard of the user based on the user's predicted future behavior. (Modi, paragraph 0154, “In an example, the monitoring system 200 also monitors changes in the behaviour of a single user or a group of users away from determined normal behaviour. Such changes in behaviour may come about in response to, for example, a policy change or training. New users may change their behaviour as they learn and progress. The 'normal behaviour' of users (such as new users) may be updated accordingly as their typical interactions with the client system 100 change over time. Furthermore the behaviour of a particular user or a user group can be evaluated to identify behaviour that might be particularly beneficial. Once beneficial behaviour is identified it can be encouraged appropriately.” And paragraph 0190, “…the graph database 224 and, optionally, the index database 222, and may produce outputs 30 which may be presented to an administrator via reports 120 or on a 'dashboard' web portal or application 110.”)
In regard to claim 3 and analogous claims 9 and 16, Lee and Modi teach the system of claim 2.
Modi further teaches wherein the user dashboard comprises educational material, tailored offers, and virtual assistants. (Modi, paragraph 0222, “Optionally, the monitoring system 200 may interface with an online dashboard 110, which may be available through a web portal or a mobile application, which may show reports (as previously described) and allow live monitoring of the events detected in the log files 10. This dashboard 110 may comprise a map/location-based view showing all activity or on a map, graphs showing relationships between objects, tables and data around identified graphs, details about events and timelines of related events, for example relating to the same user(s) or object(s). The dashboard 110 may provide the ability for an administrator to explore objects, actions and users connected to events in a global context.”)
In regard to claim 4 and analogous claims 10 and 17, Lee and Modi teach the system of claim 1.
Lee further teaches wherein the first algorithm comprises a classification method. (Lee, paragraph 0004, “The algorithms may be supervised or unsupervised and applications include pattern analysis (unsupervised) and classification (supervised).”)
In regard to claim 5 and analogous claims 11 and 18, Lee and Modi teach the system of claim 4.
Lee further teaches wherein the classification method is a supervised learning method. (Lee, paragraph 0004, “The algorithms may be supervised or unsupervised and applications include pattern analysis (unsupervised) and classification (supervised).”)
In regard to claim 6 and analogous claims 12 and 19, Lee and Modi teach the system of claim 4.
Lee further teaches wherein the classification method is an unsupervised learning method. (Lee, paragraph 0004, “The algorithms may be supervised or unsupervised and applications include pattern analysis (unsupervised) and classification (supervised).”)
In regard to claim 8, Lee teaches A system for monitoring user behavior comprising: at least one processor, (Lee, paragraph 0006, In one illustrative embodiment, a method is provided, in a data processing system comprising a processor and a memory, the memory comprising instructions which are executed by the processor to specifically configure the processor to implement a hardened neural network.”)
a communication interface communicatively coupled to the at least one processor, (Lee, paragraph 0100, “The cognitive system 400 is implemented on one or more computing devices 304A-D ( comprising one or more processors and one or more memories, and potentially any other computing device elements generally known in the art including buses, storage devices, communication interfaces, and the like) connected to the computer network 402.”)
a memory device storing executable code that, when executed, causes the at least one processor to: (Lee, paragraph 0006, “In one illustrative embodiment, a method is provided, in a data processing system comprising a processor and a memory, the memory comprising instructions which are executed by the processor to specifically configure the processor to implement a hardened neural network.”)
receive labeled interaction data for a group of users, wherein the labeled interaction data is labeled using a classification method; (Lee, paragraph 0055, “The labeled data 240 is then input to the cognitive system 250 for performance of cognitive operations on the labeled data 240. The particular cognitive operation performed by the cognitive system 250 depends on the cognitive system and may be any of a plethora of different types of cognitive operations.”)
correlate the labeled interaction data with the user information to create a correlated dataset; apply a first algorithm to the correlated dataset, wherein the algorithm is configured to segment users of the group of users into a plurality of segments; (Lee, paragraph 0052, “For example, in a patient treatment recommendation cognitive system, the labeled data may comprise labels, tags, or annotations that specify various medical concepts with which the data is associated, e.g., a disease, a treatment, a patient's age, a patient's gender, etc. In the depicted example, the operation of the neural network model 230 is to classify a portion of an input image specified in a set of input data 220 into one of 10 categories representing numerical values that the portion of the input image represents, e.g., classes "O" to "9".”).
receive a result from the first algorithm, wherein the result is one or more segments for each user of the group of users; (Lee, paragraph 0052, “For example, in a patient treatment recommendation cognitive system, the labeled data may comprise labels, tags, or annotations that specify various medical concepts with which the data is associated, e.g., a disease, a treatment, a patient's age, a patient's gender, etc. In the depicted example, the operation of the neural network model 230 is to classify a portion of an input image specified in a set of input data 220 into one of 10 categories representing numerical values that the portion of the input image represents, e.g., classes "O" to "9".”).
receive a second result, wherein the second result is a predicted future behavior for the users; (Lee, paragraph 0052, “For example, in a patient treatment recommendation cognitive system, the labeled data may comprise labels, tags, or annotations that specify various medical concepts with which the data is associated, e.g., a disease, a treatment, a patient's age, a patient's gender, etc. In the depicted example, the operation of the neural network model 230 is to classify a portion of an input image specified in a set of input data 220 into one of 10 categories representing numerical values that the portion of the input image represents, e.g., classes "O" to "9".” And paragraph 0091, “Predict and sense with situational awareness that mimic human cognition based on experiences [prediction of future behavior examiner would like to point out that this predicting is happening with natural language which is being interpreted as the user segments.]”)
Lee does not specifically teach receive user information for the group of users, wherein the user information comprises user demographics including age and location;
based on each user's segment, apply a second algorithm comprising a neural network, wherein the second algorithm is configured to make a prediction about the user's future behavior;
based on the user's predicted future behavior, trigger a concurrent communication to the user; and based on the user's predicted future behavior, trigger a concurrent update to the user's user dashboard.
However, Modi teaches receive user information for the group of users, wherein the user information comprises user demographics including age and location; (Modi, paragraph 0005, “receiving metadata from one or more devices within the one or more monitored computer systems; identifying from the metadata events corresponding to a plurality of user interactions [user information for the group of users] with the monitored computer systems;” and paragraph 0192, “The contextual data 40 includes psychology- related data that is integrated into the monitoring system 200 by modelling qualitative studies into chains of possible events/intentions with various probabilities based on parameters like age, gender, cultural background, role in the organisation, and personality type.” And paragraph 0206, “User-related attributes may comprise distributions of activity types by time and/or location or a record of activity over a recent period ( such as a 30 day sliding window average of user activity).”)
based on each user's segment, apply a second algorithm comprising a neural network, wherein the second algorithm is configured to make a prediction about the user's future behavior; (Modi, paragraph 0198, “Although the algorithms may be unsupervised, they may be used in combination with supervised models such as neural networks. The supervised neural net may be trained to recognise patterns of events (based on examples, or feedback by the operator) which may indicate that the user is unexpectedly changing their behaviour or marks a long term in their normal behaviour (the saved data relating to a user's normal behaviour may then be updated accordingly , apply a second algorithm comprising a neural network]).” and paragraph 0199, “This may be used to identify abnormal and/or malicious human interactions with the client system 100. The second layer of statistical learning may be provided by clustering users based on the data produced by the individual modules. Changes in the clusters may be detected, and/or associations can be made between clusters. The change in the data produced by the individual modules may be modelled over time. The data produced by the individual modules may also be dynamically weighted, and/or the data produced by the individual modules may be predicted.” and paragraph 0223, “Where a particular event (or combination of events) is detected as it is occurring, the monitoring system 200 may be able to issue an alert via email, SMS, phone call or virtual assistant or another communication means. The system 200, if appropriately configured, may also be able to automatically implement one or more as actions in response to a particular event or combination of events.”))
based on the user's predicted future behavior, trigger a concurrent communication to the user; and (Modi, paragraph 0019, “By combining historical and live data, meaningful insights can be generated close to real time.” And paragraph 0199, “This may be used to identify abnormal and/or malicious human interactions with the client system 100. The second layer of statistical learning may be provided by clustering users based on the data produced by the individual modules. Changes in the clusters may be detected, and/or associations can be made between clusters. The change in the data produced by the individual modules may be modelled over time. The data produced by the individual modules may also be dynamically weighted, and/or the data produced by the individual modules may be predicted.” and paragraph 0223, “Where a particular event (or combination of events) is detected as it is occurring, the monitoring system 200 may be able to issue an alert via email, SMS, phone call or virtual assistant or another communication means. The system 200, if appropriately configured, may also be able to automatically implement one or more as actions in response to a particular event or combination of events.”)
based on the user's predicted future behavior, trigger a concurrent update to the user's user dashboard. (Modi, paragraph 0222, “Optionally, the monitoring system 200 may interface with an online dashboard 110, which may be available through a web portal or a mobile application, which may show reports (as previously described) and allow live monitoring of the events detected in the log files 10. This dashboard 110 may comprise a map/location-based view showing all activity or on a map, graphs showing relationships between objects, tables and data around identified graphs, details about events and timelines of related events, for example relating to the same user(s) or object(s).” and paragraph 0199, “This may be used to identify abnormal and/or malicious human interactions with the client system 100. The second layer of statistical learning may be provided by clustering users based on the data produced by the individual modules. Changes in the clusters may be detected, and/or associations can be made between clusters. The change in the data produced by the individual modules may be modelled over time. The data produced by the individual modules may also be dynamically weighted, and/or the data produced by the individual modules may be predicted.”)
Lee and Modi are combinable for the same rationale as set forth above with respect to claim 1.
In regard to claim 14, Lee teaches A method for employing artificial intelligence to initiate a concurrent reaction according to predicted behavior, the method comprising: (Lee, paragraph 0005, “According to a first aspect, there is provided a method for monitoring user interactions within one or more monitored computer systems, comprising the steps of:” and paragraph 0091, “Predict and sense with situational awareness that mimic human cognition based on experiences [prediction of future behavior]”)
receiving interaction data for a group of users, wherein the interaction data comprises unclean interaction data and unvectorized interaction data that is slow to process using a classification machine learning model; (Lee, paragraph 0023, “In addressing these issues and providing such mechanisms, the illustrative embodiments, rather than using a classifier to identify an adversarial input, directly hinders proper gradient computation by adding noise [unclean interaction data and unvectorized interaction data], ]in the model itself, e.g., noise in the internal feature representations of the neural network itself [[slow to process using a classification machine learning model;] ], such that gradient computations are diverted.” And paragraph 0101, “The cognitive system 400 is configured to implement a request processing pipeline 408 that receive inputs from various sources [receive interaction data for a group of users]. The requests may be posed in the form of a natural language question, natural language request for information, natural language request for the performance of a cognitive operation, or the like. Alternatively, the "request" may simply be the input of data that is intended to be operated on by the cognitive system e.g., images, text, audio input, or the like, which is to be classified by the hardened model of the illustrative embodiments and then operated on by cognitive processes to generate a result of a cognitive operation.”)
wherein transforming the interaction data comprises cleaning and vectorizing the data thereby improving the accessibility of the data so that an accessing classification machine learning model is able to process the transformed data more quickly than the accessing classification machine learning model is able to process the received interaction data; (Lee, paragraph 0004, “Neural network based deep learning is a class of machine learning algorithms that use a cascade of many layers of nonlinear processing units for feature extraction and transformation. Each successive layer uses the output from the previous layer as input. The algorithms may be supervised or unsupervised and applications include pattern analysis (unsupervised) and classification (supervised). Neural network based deep learning is based on the learning of multiple levels of features or representations of the data with higher level features being derived from lower level features to form a hierarchical representation.” And paragraph 0030, “Thus, after training the new protected model using these three sets of training data, an additional layer of nodes, referred to as the merge layer having merge nodes, is added to the new protected model to merge the first half and second half of the output nodes by joining the adversarially trained class, i.e., the classification output vector generated by the second set of output nodes, to its original class, i.e. the classification output vector generated by the first set of output nodes, so that the regular data samples in the first set of training data, and the adversarially generated data samples in the third set of training data, are correctly classified [interaction data comprises cleaning and vectorizing the data thereby improving the accessibility of the data].”)
processing the extracted content from the transformed interaction data for a the group of users using a classification algorithm configured to label the interaction data; (Lee, paragraph 0052, “For example, in a patient treatment recommendation cognitive system, the labeled data may comprise labels, tags, or annotations that specify various medical concepts with which the data is associated, e.g., a disease, a treatment, a patient's age, a patient's gender, etc. In the depicted example, the operation of the neural network model 230 is to classify a portion of an input image specified in a set of input data 220 into one of 10 categories representing numerical values that the portion of the input image represents, e.g., classes "O" to "9".”)
receiving labeled interaction data for a group of users, (Lee, paragraph 0055, “The labeled data 240 is then input to the cognitive system 250 for performance of cognitive operations on the labeled data 240. The particular cognitive operation performed by the cognitive system 250 depends on the cognitive system and may be any of a plethora of different types of cognitive operations.”)
correlating the labeled interaction data with the user information to create a correlated dataset; applying a first algorithm to the correlated data, wherein the algorithm is configured to segment users into a plurality of segments; (Lee, paragraph 0052, “For example, in a patient treatment recommendation cognitive system, the labeled data may comprise labels, tags, or annotations that specify various medical concepts with which the data is associated, e.g., a disease, a treatment, a patient's age, a patient's gender, etc. In the depicted example, the operation of the neural network model 230 is to classify a portion of an input image specified in a set of input data 220 into one of 10 categories representing numerical values that the portion of the input image represents, e.g., classes "O" to "9".”).
Lee does not explicitly teach extracting content from the transformed interaction data;
receiving one or more segments for each user of the group of users, wherein the user information comprises user demographics including age and location;
based on a user's one or more segments, processing the one or more segment using a second algorithm comprising a neural network, the second algorithm configured to make a prediction about the user's future behavior; and
receiving, for each user, a predicted future behavior;
based on the user's predicted future behavior, triggering a concurrent communication to the user.
However, Modi teaches extracting content from the transformed interaction data; (Modi, paragraph 0175, “normalisation process is then used to transform the log files 10 (which may be in various different formats) into generic normalised metadata or log files 20. The normalization process operates by modelling any human interaction with the client system 100 by breaking it down into discrete events. These events are identified from the content of the log files 10. A schema for each data source used in the network 1000 is defined so that any log file 10 from a known data source in the network 1000 has an identifiable structure, and 'events' and other associated parameters (which may, for example, be metadata related to the events) may be easily identified and be transposed into the schema for the normalized log files 20.”)
receiving one or more segments for each user of the group of users, wherein the user information comprises user demographics including age and location; (Modi, paragraph 0005, “receiving metadata from one or more devices within the one or more monitored computer systems; identifying from the metadata events corresponding to a plurality of user interactions [user information for the group of users] with the monitored computer systems;” and paragraph 0192, “The contextual data 40 includes psychology- related data that is integrated into the monitoring system 200 by modelling qualitative studies into chains of possible events/intentions with various probabilities based on parameters like age, gender, cultural background, role in the organisation, and personality type.” And paragraph 0206, “User-related attributes may comprise distributions of activity types by time and/or location or a record of activity over a recent period ( such as a 30 day sliding window average of user activity).”)
based on a user's one or more segments, processing the one or more segment using a second algorithm comprising a neural network, the second algorithm configured to make a prediction about the user's future behavior; and (Modi, paragraph paragraph 0222, “Optionally, the monitoring system 200 may interface with an online dashboard 110, which may be available through a web portal or a mobile application, which may show reports (as previously described) and allow live monitoring of the events detected in the log files 10. This dashboard 110 may comprise a map/location-based view showing all activity or on a map, graphs showing relationships between objects, tables and data around identified graphs, details about events and timelines of related events, for example relating to the same user(s) or object(s).” and paragraph 0199, “This may be used to identify abnormal and/or malicious human interactions with the client system 100. The second layer of statistical learning may be provided by clustering users based on the data produced by the individual modules. Changes in the clusters may be detected, and/or associations can be made between clusters. The change in the data produced by the individual modules may be modelled over time. The data produced by the individual modules may also be dynamically weighted, and/or the data produced by the individual modules may be predicted.” and paragraph 0198, “Although the algorithms may be unsupervised, they may be used in combination with supervised models such as neural networks. The supervised neural net may be trained to recognise patterns of events (based on examples, or feedback by the operator) which may indicate that the user is unexpectedly changing their behaviour or marks a long term in their normal behaviour (the saved data relating to a user's normal behaviour may then be updated accordingly ,[ using a second algorithm comprising a neural network,]).”)
receiving, for each user, a predicted future behavior; (Modi, paragraph 0019, “By combining historical and live data, meaningful insights can be generated close to real time.”)
based on the user's predicted future behavior, triggering a concurrent communication to the user. (Modi, paragraph 0019, “By combining historical and live data, meaningful insights can be generated close to real time.”)
Lee and Modi are combinable for the same rationale as set forth above with respect to claim 1.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SKYLAR K VANWORMER whose telephone number is (703)756-1571. The examiner can normally be reached M-F 6:00am to 3:00 pm.
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, Usmaan Saeed can be reached at (571) 272-4046. 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.
/S.K.V./Examiner, Art Unit 2146
/USMAAN SAEED/Supervisory Patent Examiner, Art Unit 2146
Prosecution Insights