WO2021146156A1 - Systèmes et procédés de surveillance de données et de validation de capture - Google Patents

Systèmes et procédés de surveillance de données et de validation de capture Download PDF

Info

Publication number
WO2021146156A1
WO2021146156A1 PCT/US2021/013024 US2021013024W WO2021146156A1 WO 2021146156 A1 WO2021146156 A1 WO 2021146156A1 US 2021013024 W US2021013024 W US 2021013024W WO 2021146156 A1 WO2021146156 A1 WO 2021146156A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
user
incentive
end user
component
Prior art date
Application number
PCT/US2021/013024
Other languages
English (en)
Inventor
Romesh Shalendra DE SILVA
Jacob Albert KETEYIAN
Hadi JAVEED
Trevor Dougherty CAMBELL
Original Assignee
Vincere Health Inc.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Vincere Health Inc. filed Critical Vincere Health Inc.
Publication of WO2021146156A1 publication Critical patent/WO2021146156A1/fr

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/0004—Gaseous mixtures, e.g. polluted air
    • G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
    • G01N33/0027—General constructional details of gas analysers, e.g. portable test equipment concerning the detector
    • G01N33/0036—General constructional details of gas analysers, e.g. portable test equipment concerning the detector specially adapted to detect a particular component
    • G01N33/004—CO or CO2
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/48—Biological material, e.g. blood, urine; Haemocytometers
    • G01N33/483—Physical analysis of biological material
    • G01N33/497—Physical analysis of biological material of gaseous biological material, e.g. breath
    • G01N33/4975—Physical analysis of biological material of gaseous biological material, e.g. breath other than oxygen, carbon dioxide or alcohol, e.g. organic vapours

Definitions

  • various aspects of the invention provide users with tailored, temporal, and targeted incentives that help the user manage programs and/or regimens to cease smoking and other health related regimens.
  • Various embodiments couple a mobile application with sensing devices to provide assurance that sensor or biometric readings are being taken at appropriate intervals and by the appropriate users.
  • Further embodiments manage health regimen execution responsive to validated sensor data.
  • the system tailors information, incentives, and various functions based on system insights derived from machine learning models that analyze the validated data.
  • the system is configured to execute various incentives in real-time responsive to behavioral modeling and detection of stressful events and/or probable points of failure to encourage users to make healthier decisions exactly when they are needed most.
  • a monitoring and data validation system comprising at least one processor operatively connected to a memory, an authentication component, executed by the at least one processor, configured to determine an end user device is an authenticated state, a data capture component, executed by the at least one processor, for receiving carbon monoxide measurement data from an end user via at least one sensor, and a data validation component, executed by the at least one processor, configured to validate that the received carbon monoxide measurement data has been captured from the end user.
  • the system further comprises a compliance component configured to establish a schedule or timing of data capture sessions.
  • the compliance component is further configured to trigger functions on the end user device to facilitate compliance with the established schedule or the timing of the data capture sessions.
  • the compliance component is configured to dynamically schedule data capture sessions, responsive to a predicted potential failure of the end user to follow a regimen.
  • the system is further configured to automatically generate predictions of probable failure for a respective user based on input of at least one or more of user location information, timing of behavioral triggers, or visual capture data associated with the end user.
  • the system further comprises an incentive component, executed by the at least one processor, configured to generate and communicate incentive awards to the end user.
  • the incentive component is further configured to dynamically generate an incentive responsive to a predicted potential failure of the end user to follow a regimen.
  • the incentive component is further configured to dynamically update an incentive responsive to a predicted potential failure of the end user to follow a regimen.
  • the incentive component further comprises an intelligent model that accepts as input user context information and outputs prediction information for identifying likelihood of a failure to follow a regimen.
  • the incentive component is configured to dynamically determine an incentive tailored to the user’s profile and optimizing a determined probability that the user will value the incentive.
  • a computer implemented method for monitoring and data validation comprises determining, by at least one processor, an end user device is an authenticated state, receiving, by the at least one processor, carbon monoxide measurement data from an end user via at least one sensor, and validating, by the at least one processor, that the received carbon monoxide measurement data has been captured from the end user.
  • the method further comprises establishing a schedule or timing of data capture sessions.
  • the method further comprises triggering functions on the end user device to facilitate compliance with the established schedule or the timing of the data capture sessions.
  • the method further comprises dynamically scheduling data capture sessions responsive to a predicted potential failure of the end user to follow a regimen.
  • the method further comprises automatically generating predictions of probable failure for a respective user based on input of at least one or more of user location information, timing of behavioral triggers, or visual capture data associated with the end user.
  • the method further comprises generating and communicating incentive awards to the end user.
  • the method further comprises dynamically generating an incentive responsive to a predicted potential failure of the end user to follow a regimen.
  • the method further comprises dynamically updating an incentive responsive to a predicted potential failure of the end user to follow a regimen.
  • the method further comprises processing as input user context information and generating prediction information for identifying likelihood of a failure to follow a regimen, according to an intelligent model.
  • the method further comprises dynamically determining an incentive tailored to the user’s profile and optimizing a determined probability that the user will value the incentive.
  • FIG. 1 is a block diagram of an example monitoring and data validation system, according to one embodiment
  • FIG. 2 is a block diagram of a BI component of an embodiment of a monitoring and data validation system
  • FIG. 3 is a block diagram of an example process flow for generating a campaign or regimen to be executed on the system
  • FIG. 4 is an example process for managing user task execution, according to one embodiment
  • FIG. 5 is an example process flow for performing campaign or regimen tasks, according to one embodiment
  • FIG. 6 is an example process flow for managing a task performance window, according to one embodiment
  • FIG. 7 is an example process flow for managing incentive redemption, according to one embodiment
  • FIG. 8 illustrates information collected by a monitoring and data validation system during execution of a regimen or campaign, according to one embodiment
  • FIG. 9 is a block diagram of an example special purpose computer system on which various aspects of the invention can be practiced according to one embodiment.
  • the system includes a mobile application that pairs with a hardware device that monitors carbon monoxide (CO) in parts per million (PPM).
  • CO carbon monoxide
  • PPM parts per million
  • users perform breath tests by exhaling into the hardware device to prove that they have not been smoking cigarettes or other combustible tobacco products. If a user receives a test result with a measurement that is below a certain CO PPM threshold, the system is configured to execute various tailored incentives (e.g., real-time financial incentives).
  • the system includes integrated validation of sensor data.
  • the system is configured to verify that a user is not cheating with at least a facial recognition feature.
  • the mobile application can include facial recognition functions that can be executed to verify that the identity of the user exhaling into the device matches the identity of the intended user, and not another individual.
  • time stamped video capture can be used to validate contemporaneous capture of sensor data.
  • any data can be captured with location information to provide additional verification.
  • object recognition can be executed to verify the presence of a measurement device (e.g., CO sensor), and proper use of the same.
  • QR codes or wireless signals from sensor devices can also be used to verify the presence and proper use of measurement devices.
  • a measurement device can be provided to an end user with a QR code that is uniquely assigned to the intended user of the device.
  • the system can be configured to verify the presence of the measurement device in conjunction with verification of the user’s face, for example, when performing a test.
  • the system can be configured to verify the presence of the measurement device is in a proper data capture position (e.g., breath sensor in the user's mouth, among other options).
  • digital validation of the user is conducted autonomously in conjunction with sensor data captured by a monitoring and data validation system.
  • the system executes a computer vision-based facial recognition function to validate the user while data is being captured from a device/sensor.
  • the mobile application can employ an API for accessing cloud based vision recognition functions made available as a cloud based service.
  • a separate computer vision algorithm can be configured to verify the presence of the appropriate hardware device, for example, in the user’s mouth to ensure that the correct user is performing the breath test correctly. In various embodiments, these two processes objectively verify the authenticity and validity of data points generated by users.
  • a computer vision algorithm used to ascertain a user’s emotional state is also applied at the same time as each facial recognition process.
  • the emotional state information can be captured as user context information at any time, and often in conjunction with various testing.
  • the system bundles user context information (e.g., time, location, emotional state, etc.) with test readings (e.g., carbon monoxide breath test, etc.).
  • analyzing this data using AI learning algorithms enables the system to predict smoking risk, and further to adapt incentives and prioritize users to intervene with human counseling in ways simply unavailable in conventional systems and/or treatment methodologies.
  • the data collected from the users is stored in the cloud. This data is accessible via a presentation on a dashboard for the user to see.
  • the software that has been developed to date supports the CO monitoring hardware device; however, the software platform has been developed in a modular way such that the platform itself can support any hardware device with an “API” or application programming interface. The idea is that whatever hardware device desired, the system can be configured to interface with that device and capture device data and/or contextual data. In various embodiments, the system is capable of interfacing with a wide variety of hardware devices, such as: smart watches, wearable health monitoring devices, IoT connected health monitoring devices, etc.
  • Fig. 8 illustrates information collected by the system during execution of a regimen or campaign.
  • a treatment regimen e.g., smoking cessation program
  • Fig. 8 illustrates information collected by the system during execution of a regimen or campaign.
  • two individuals performed two breath tests twice per day over a one-month period.
  • the x- axis is time
  • the y-axis is the user’s CO PPM reading. Peaks and troughs of the user’s CO readings start to tell a story about their lives and subsequent smoking behavior as the system correlates contextual information about the users with the observed readings.
  • the system is configured to capture these contextual qualitative data points about users’ behavioral health (e.g., via computer vision analysis, captured location information, timing, etc.), habits, and triggers.
  • the system can include a two way messaging and notification system, along with other data inputs (such as location data, weather, etc.) to facilitate contextual data capture.
  • user behavioral data is gathered and stored, which can be processed by a behavioral insights (“BI”) component and/or incentive component discussed below.
  • BI behavioral insights
  • the BI component includes the machine learning and artificial intelligence algorithms that can be applied across all the sources of data and users to predict and preempt instances of higher CO readings. For example, by predicting the local maxima of smoking likelihood, the system can dynamically adapt incentive offerings (e.g., increase the number of incentives/actions, increase incentive amounts, etc.) to counteract the increased smoking likelihood.
  • incentive offerings e.g., increase the number of incentives/actions, increase incentive amounts, etc.
  • the incentive computation algorithm involves periodically querying the BI component to calculate the likelihood of a CO maximum and updating the incentive selected, action selection, and/or the amount of an offering amount to proportionally reflect the change in likelihood.
  • the system is configured to increase the user’s perceived value of an incentive, action, or penalty to achieve any regimen based objective.
  • the system is configured to apply machine learning models on the captured user information to determine when intervention is required. Machine learning models can also determine the incentive, reward, action, and/or penalty that will be the most effective in adjusting user behavior.
  • the system is configured to use AI to predict the probability of a given outcome variable (such as steps, heart rate, task completion, etc.), and adapting an incentive offering to be proportional to the change in the likelihood of that outcome.
  • a given outcome variable such as steps, heart rate, task completion, etc.
  • Various system implementations are configured to disburse incentives intelligently, increase them, or even withhold them, at critical periods for a user.
  • system and/or incentive component can include a machine learning approach based on a Markov Decision Process.
  • the agent is configured to be executed as a decision engine, which can be tailored to each user profile and regimen being executed.
  • each model is associated with a set of states, which can include any one or more of the following: i) CO device and app usage data points collected from participants; ii) other environmental data points (such as location, weather, location and time, context information, etc.); iii) health counselor inputs that classify user behavior (e.g., a counselor who is monitoring the user’s data dashboard and reaches out to the user to offer support has the ability to tag the peaks and troughs of the user’s results with their observations of the user’s behavior associated with those results.
  • states can include any one or more of the following: i) CO device and app usage data points collected from participants; ii) other environmental data points (such as location, weather, location and time, context information, etc.); iii) health counselor inputs that classify user behavior (e.g., a counselor who is monitoring the user’s data dashboard and reaches out to the user to offer support has the ability to tag the peaks and troughs of the user’s results with their observations of the
  • actions of the agent executed by the system include dynamically modulating incentive actions and/or amounts, selecting and triggering the appropriate notifications according to system determined timing, and identify user contexts that trigger health counselor intervention (e.g., which may include direct chat sessions triggered by the system, video conferences initiated by the system, among other options).
  • the system trains a variety of models on user data pertaining to incentives, and their effect on users following treatment regimens, identification of timing and context of failure to follow treatment regimens, etc.
  • large volumes of data can be used to train the respective models with more data improving the various example models.
  • the models are tuned to develop context information (e.g., increase model sensitivity to context of desired and undesired behavior, for example).
  • context information e.g., increase model sensitivity to context of desired and undesired behavior, for example.
  • Various combinations of context can be used in various models to provide more degrees of freedom and enable the system to train on multiple sets of contexts, and evaluate multiple models to test a variety of machine learning approaches.
  • multiple models are executed and the combined results used to select incentives and/or to trigger system based interventions.
  • collected data e.g., context, timing, location, regimen, compliance, non-compliance, etc.
  • the various models can be tested across the population data to determine their efficacy in achieving various desired goals or outcomes — and even efficacy of multiple models or combinations in achieving system defined goals or outcomes.
  • the system developed/collected user data can span many domains, including, for example, data points such as carbon monoxide concentration from breath test results, incentive/action executed, time of day of test, day of the week for a test, timing of notifications (e.g., nudges and reminders, among other options), etc.
  • the modeled data can also include geolocation data, weather data, data on to other users, event tagging, etc.
  • supervised learning models can be used where human health counselors classify data points (e.g., via a system dashboard) with information on user behavior and outcomes to help to train the model other embodiments, the classified data can be used in an unsupervised training model, and the classified data can be of multiple inputs used to train various models.
  • the system is configured to improve the contextualization of collected data by storing the collected user data within a graph database.
  • the graph database enables improved storage (e.g., higher data fidelity, better relationship tracking, smaller space, improved data relationship definition, etc.) of large sets of unstructured and semi- structured data.
  • the system is configured to identify, form, and/or store relationships between data that may otherwise be difficult to derive.
  • the system can be configured to collect a critical mass of user data to begin training, execute testing, and then apply reinforcement learning models to the dataset(s).
  • the nature of the learning models is such that the final algorithm with the relevant inputs and parameters for optimization can be defined over time and many iterations.
  • the model can be dynamically defined over tuning operations and iterations.
  • the graph database architecture enables supervised and unsupervised learning models and/or combinations of both to develop improvements in user segmentation and improvements in learning how to categorize users.
  • the improved user classification can be used to narrow a set of modeled states and permit a more efficient reinforcement learning model.
  • Various implementations include models that optimize on one or more of the following features:
  • the system can use devices configured for carbon monoxide sensing.
  • Other embodiments can include other health connected devices such as FitBits, Apple Watches, step counters, smart watches, continuous glucose monitors, continuous blood pressure cuffs, wearable health monitoring devices (e.g., heart rate sensors, EEG, breath rate sensors, etc.), IoT connected health monitoring devices, and/or other respiratory devices that monitor a variety of ailments, any combination of which can be integrated into the system to capture data and develop relationships in a graph based data structure.
  • other health connected devices such as FitBits, Apple Watches, step counters, smart watches, continuous glucose monitors, continuous blood pressure cuffs, wearable health monitoring devices (e.g., heart rate sensors, EEG, breath rate sensors, etc.), IoT connected health monitoring devices, and/or other respiratory devices that monitor a variety of ailments, any combination of which can be integrated into the system to capture data and develop relationships in a graph based data structure.
  • Various embodiments are configured to model behaviors and/or contexts derived from the additional information to trigger system action/intervention to ensure and/or improve user compliance with a treatment regimen.
  • the system is configured to incentivize and withhold incentives in the same or similar manner discussed herein for triggers identified in the additional data streams of the additional devices.
  • the system based incentives/interventions can include financial rewards such as cash, physical gift cards, and e-gift cards; however, in other examples incentives can include other options including incentives tailored to specific users, additional options/actions for complying with a regimen, etc.
  • users can be awarded virtual incentives that users can redeem at their discretion and/or for a wide variety of items, rewards, perks, or benefits.
  • FIG. 1 is a block diagram of example system components according to one embodiment.
  • the device data templates can include sensors native to a mobile phone 106, a carbon monoxide monitoring device 108, and/or wearable health monitoring devices 110.
  • a mobile application connected to the various devices can capture data and communicate it to the system 112.
  • the system can be configured to manage individual user data streams (e.g. data stream component 114).
  • Other architectures can be used in different embodiments, and a variety of different monitoring devices can provide data to the system.
  • the system works in tandem with a variety of devices - such as mobile phones, carbon monoxide monitoring devices, or wearable health monitoring devices - using these devices to generate and collect user data.
  • the captured user data is passed through a mobile application, which communicates to the system (e.g., a user data stream system).
  • the mobile application acts as a conduit for data transit between device inputs and the system.
  • the system can include a behavioral insights (“BI”) component.
  • the BI component can be configured to process user data and automatically determine incentive offerings, behavioral nudges, just-in-time interventions, optimal timing of interventions/actions, etc.
  • the BI component is configured to collect and process data from the system’s central datastore, which can include machine learning modeling on the captured user data.
  • the BI component can be configured to employ natural language processing, time-series analyses, and/or reinforcement learning.
  • the BI component can interface with many system processes.
  • the BI component can be instantiated alone or as part of other system components, including for example an incentive component.
  • FIG. 2 is an example block diagram of a behavioral insights component 202.
  • the behavioral insights component 202 can receive data from a user data stream component 204.
  • the received data can be stored as part of a behavioral data store 206.
  • the data in the behavioral data store 206 can be processed via machine learning model 208.
  • a reinforcement learning model is used to process the received data.
  • time series analysis can be used to process the received data (e.g. by a time series analysis component 210).
  • a natural language processing component 212 can be used to process the received data.
  • algorithmic processing can be applied to the behavioral data store shown at block 214.
  • the algorithmic processing shown at block 214 can include other machine learning models, rule based processing, among other options.
  • Fig. 3 is an example process flow for generating a campaign or regimen to be executed on the system.
  • a campaign is created by first defining the length that the campaign will endure at 302.
  • the “rules” of the campaign can be established at 304, such that the data input requirements / task performance requirements, or biofeedback measurement thresholds are defined.
  • the thresholds can be defined as a threshold of reading from a digital monitoring device such as a CO monitor or completion of a set of tasks.
  • any schedule for performing tasks or generating data is also defined.
  • the incentive offering structure is defined at 308, allowing administrators to determine what incentives a user might receive throughout the campaign.
  • the campaign is finally ratified by enrolling selected users into the defined campaign at 310, and notifying these users of their enrollment in the campaign at 312.
  • the system is configured to manage users through scheduled tests that are part of a regimen or campaign. For example, users can be required to conduct tasks (e.g., perform activities, exercises, etc.) or generate data (e.g., capture health data) from user devices (e.g., CO monitor, blood pressure monitor, EEG monitor, step counter, glucose monitor, etc.) according to a defined schedule.
  • the system is configured to manage and automatically remind users of their campaign’s defined parameters. If this is the case, there are established task performance periods during which tasks and schedules, and triggered/targeted incentives can modify scheduled incentives to ensure the tasks are conducted.
  • the system manages regimen or campaign schedules based on a task performance window that is opened when a user is required to conduct a task.
  • Fig. 4 is an example process for managing user task execution. The process begins at 402 with a query to behavioral information. The returned data is used to perform an evaluation as to whether or not the user may be eligible for a modified incentive offering at 404.
  • this is done by querying a BI component, which can also perform the evaluation of user behavior and associated user data at 404. For example, if the BI component determines that a user is eligible for a modified incentive offering (404 YES), the user is notified of the modified offering. In other embodiments, the process 400 can determine that a new incentive and/or action is appropriate where originally no action and/or incentive would have been presented.
  • the analysis at 400 can include analysis of any one or more and/or any combination of: user data such as historical CO levels, emotional state, steps, GPS location(s), proximity to other users (e.g., in the network), timing of texts, timing of notifications, difference in time between notifications and tests, weather, calendar and schedule, user response content and timing, and engagement rates, among other variables.
  • user data such as historical CO levels, emotional state, steps, GPS location(s), proximity to other users (e.g., in the network), timing of texts, timing of notifications, difference in time between notifications and tests, weather, calendar and schedule, user response content and timing, and engagement rates, among other variables.
  • the modified action and/or incentive is created (e.g., 406) - which can include execution of a sub-process to determine the optimal change or new action and/or incentive tailored to the user.
  • a modified incentive and/or action is communicated to the user, and the task performance window then opens as it is scheduled (e.g., 410). If the analysis determines that a user is ineligible for a modified incentive offering (e.g., 404 NO), the user will be notified of any original incentive offering and/or action at 408 and the task performance window opens at 410.
  • the system enables “dynamic” modulation of incentives and/or action depending on user or population behavior.
  • the system produces better outcomes than conventional approaches and can also provide a mechanism to more effectively influence behavior of users through the deployment of these “dynamic” offerings —which some conventional systems fail to provide.
  • regimen execution can start when a user performs a required task; concurrently, while the user performs this task, the system conducts an evaluation as to whether or not the user and/or their generated data or task result is authentic. If authenticity is not established, the process begins again from the beginning, notifying the user of the authentication failure. If authenticity is established, then the system evaluates the user’s task result / generated data. Next, the user’s eligibility for an incentive is evaluated (which is often dependent on their task result or generated data); if the user is not eligible for an incentive, they are notified accordingly and the task performance process concludes. If a user is determined to be eligible for an incentive, the system delivers the offered incentive to the user, and the task performance process concludes.
  • Fig. 5 is an example process flow 500 for performing campaign or regimen tasks.
  • process 500 begins at 502 when a user initiates a test and or a task process. Responsive to a user attempting to access the system, authentication operations are executed at 506 and if the user is determined to not be authenticated at 508 NO, the user is notified of an authentication failure at 504. If the user is authenticated at 508 YES, process 500 continues at 510, for example, with a user operating a data input device to perform a required task.
  • process 500 continues with evaluation of the user action, results, outcome, and/or performance at 512.
  • a valuation at 512 can include validation that a respective user is employing their associated device to deliver valid outputs.
  • this can include video monitoring and analysis to determine a carbon monoxide sensor is being employed by the respective user — and the results are not being faked.
  • Further evaluation can be executed, for example, at 514.
  • the user’s eligibility for an incentive and/or action can be determined at 514. If the user is not eligible for an incentive 516 NO, the user is notified of ineligibility at 518. If the user is eligible for an incentive 516 YES, process 500 continues at 520 an incentive and/or action award is communicated to the user.
  • the system is configured to control closing a task performance window for at least two reasons. For example, if a user performs the required task the window can close, and if a user does not perform the required task and the task performance window has expired the window can close.
  • Fig. 6 is an example process flow 600 for managing a task performance window.
  • Process 600 can begin once a scheduled time window is identified.
  • Process 600 begins with a monitoring loop — has the user performed the task 602 (e.g., provide sensor data, capture context information, etc.), followed by checking of whether the time window has expired 604 NO. If neither condition is met the loop continues until time expires 604 YES or the user performs the task 602 YES.
  • Process 600 continues to 606 for both YES branches, with closing of the task performance window.
  • the collected data and context information can be evaluated and/or aggregated 608 for storage at 610.
  • Intelligent models can be used to process the collected data and/or the aggregated data at 612. For example, various models can be used on individual data and/or aggregated data to determine if modified incentives are needed, optimal, and to further refine existing models with additional context/outcome information.
  • the analysis can also include rule based processing alone, in combination, and/or as alternative to machine learning approaches, all of which can derive insights on incentives, actions, user behavior, user context, and/or potential outcomes (e.g., when needed, which ones are optimal for improving regimen compliance, which ones are optimal for which users, etc.) at 614.
  • Incentive Delivery Example by performing required tasks and/or generating data, users can accumulate incentives within their internal account. At some point, a user may wish to withdraw their accumulated incentives from their internal account and redeem these incentives to an external account of their choosing. If a user wishes to withdraw their accumulated incentives, the system first performs an evaluation as to whether or not a user is eligible to perform this action. For example, eligibility to withdraw may be based on a user achieving a particular minimum account balance, performing a particular task or generating data, completing a certain fraction of tasks or a campaign, achieving a particular outcome, or may be based on a determined time delay.
  • a user is determined to be ineligible to withdraw their accumulated incentives, they are notified accordingly and the incentive delivery process concludes. If a user is determined to be eligible to withdraw, the system initiates the transfer of funds from the user’s internal account to their chosen external account. This incentive redemption event is then accounted for by reflecting the withdrawal in the user’s internal account, and the incentive delivery process concludes.
  • Fig. 7 is an example process 700 for managing incentive redemption.
  • Process 700 can begin at 702 with users receiving incentives.
  • An incentive can be accumulated, for example, in an internal account at 704.
  • withdrawal accumulated incentives e.g. 706 YES
  • the user’s eligibility to withdraw is determined at 708. If no withdrawal is desired 706 no further action is taken. If the user is not eligible to withdraw (e.g. 710 NO), the user is notified at 712. If the user is eligible to withdraw 710 YES, process 700 can continue, for example, with transfer funds to the user’s external account at 714. Other options for redeeming awards and/or incentives can be executed at 714 in other embodiments.
  • the user’s account is updated to reflect the redemption at 716.
  • the system leverage machine learning models to automatically enable loss aversion behavioral modification by framing system based incentives, for example, as an amount that is available to the user, that is lost if they do not comply with the test conditions/regimen/campaign.
  • reinforcing the loss aversion heuristic can be done by requiring cash contributions from the users themselves so they have skin directly in the game, and/or from an employer or provider that sponsors incentives.
  • providers and/or employers can match or contribute a multiple of what the user contributes, or fund the entirety of the incentives in some embodiments.
  • incentives may be redeemed in the form of cash, gift cards, contributions to health savings accounts or 401k accounts on behalf of the user or their nominees, among other options.
  • the system generates and displays an administrative dashboard for managing regimen/campaign definition and execution.
  • the dashboard can be utilized by smoking cessation and behavioral health counselors and provides data and insights unavailable in conventional approaches (e.g., uniquely presents objective data on the daily smoking and emotional health level of users at an individual and population level).
  • the system is configured to generate a combined smoking health and emotional health score, on which the system can automatically prompt an action by the counselor (e.g., to prioritize which users need more help).
  • the administrative dashboard is configured to integrate with existing medical billing software, Electronic Health Records (EHR) systems, Electronic Medical Records (EMR) systems, Personal Health Record (PHR) systems, among other options.
  • EHR Electronic Health Records
  • EMR Electronic Medical Records
  • PHR Personal Health Record
  • the administrative dashboard can also be configured to enable generation and/or exports of reports that contain relevant insights, text data, numerical data, scheduling data, CPT code billing data, clinical data, device data, historical data, and/or financial data.
  • the reports can be used by clinicians, counselors, and other care providers to complete medical or treatment reimbursement submissions on their respective billing systems or platforms.
  • the distributed computer system 900 includes one more computer systems that exchange information. More specifically, the distributed computer system 900 includes computer systems 902, 904 and 906. As shown, the computer systems 902, 904 and 906 are interconnected by, and may exchange data through, a communication network 908.
  • a monitoring and data validation system and/or engine can be implemented on 902, which can communicate with, for example, an incentive and/or a BI component on 904, and/or other systems implemented on 906 (e.g., validation component, etc.), which can operate together to provide the monitoring and data validation system functions as discussed herein.
  • monitoring and data validation systems can be implemented on 902 or be distributed between 902-906.
  • conventional computer systems can be improved based on the present disclosure, in some examples, enabling new functionality unavailable in various conventional systems, in other examples, by improving execution efficiency (e.g., reducing memory required, improving accuracy of interactions, reducing network traffic, dynamically determining and delivering updated and/or new actions or incentives, validating user data capture, training models on validated data samples, etc.), among other options.
  • the network 908 may include any communication network through which computer systems may exchange data.
  • the computer systems 902, 904 and 906 and the network 908 may use various methods, protocols and standards, including, among others, Fibre Channel, Token Ring, Ethernet, Wireless Ethernet, Bluetooth, IP, IPV6, TCP/IP, UDP, DTN, HTTP, FTP, SNMP, SMS, MMS, SS7, JSON, SOAP, CORBA, REST and Web Services.
  • the computer systems 902, 904 and 906 may transmit data via the network 908 using a variety of security measures including, for example, TLS, SSL, or VPN. While the distributed computer system 900 illustrates three networked computer systems, the distributed computer system 900 is not so limited and may include any number of computer systems and computing devices, networked using any medium and communication protocol.
  • the computer system 902 includes a processor 910, a memory 912, a bus 914, an interface 916, and data storage 918.
  • the processor 910 performs a series of instructions that result in manipulated data.
  • the processor 910 may be any type of processor, multiprocessor or controller. Some exemplary processors include commercially available processors such as an Intel Xeon, Itanium, Core, Celeron, or Pentium processor, an AMD Opteron processor, a Sun UltraSPARC or IBM Power5+ processor and an IBM mainframe chip.
  • the processor 910 is connected to other system components, including one or more memory devices 912, by the bus 914.
  • the memory 912 stores programs and data during operation of the computer system 902.
  • the memory 912 may be a relatively high performance, volatile, random access memory such as a dynamic random access memory (DRAM) or static memory (SRAM).
  • the memory 912 may include any device for storing data, such as a disk drive or other non-volatile storage device.
  • Various examples may organize the memory 912 into particularized and, in some cases, unique structures to perform the functions disclosed herein. These data structures may be sized and organized to store values for particular data and types of data.
  • Components of the computer system 902 are coupled by an interconnection element such as the bus 914.
  • the bus 914 may include one or more physical busses, for example, busses between components that are integrated within the same machine, but may include any communication coupling between system elements including specialized or standard computing bus technologies such as IDE, SCSI, PCI, and InfiniBand.
  • the bus 914 enables communications, such as data and instructions, to be exchanged between system components of the computer system 902.
  • the computer system 902 also includes one or more interface devices 916 such as input devices, output devices and combination input/output devices.
  • Interface devices may receive input or provide output. More particularly, output devices may render information for external presentation. Input devices may accept information from external sources. Examples of interface devices include keyboards, mouse devices, trackballs, microphones, touch screens, printing devices, display screens, speakers, network interface cards, etc. Interface devices allow the computer system 902 to exchange information and to communicate with external entities, such as users and other systems.
  • the data storage 918 includes a computer readable and writeable nonvolatile, or non- transitory, data storage medium in which instructions are stored that define a program or other object that is executed by the processor 910.
  • the data storage 918 also may include information that is recorded, on or in, the medium, and that is processed by the processor 910 during execution of the program. More specifically, the information may be stored in one or more data structures specifically configured to conserve storage space or increase data exchange performance.
  • the instructions stored in the date storage may be persistently stored as encoded signals, and the instructions may cause the processor 910 to perform any of the functions described herein.
  • the medium may be, for example, optical disk, magnetic disk, or flash memory, among other options.
  • the processor 910 or some other controller causes data to be read from the nonvolatile recording medium into another memory, such as the memory 912, that allows for faster access to the information by the processor 910 than does the storage medium included in the data storage 918.
  • the memory may be located in the data storage 918 or in the memory 912, however, the processor 910 manipulates the data within the memory, and then copies the data to the storage medium associated with the data storage 918 after processing is completed.
  • a variety of components may manage data movement between the storage medium and other memory elements and examples are not limited to particular data management components. Further, examples are not limited to a particular memory system or data storage system.
  • the computer system 902 is shown by way of example as one type of computer system upon which various aspects and functions may be practiced, aspects and functions are not limited to being implemented on the computer system 902 as shown in FIG. 9. Various aspects and functions may be practiced on one or more computers having different architectures or components than that shown in FIG. 9.
  • the computer system 902 may include specially programmed, special-purpose hardware, such as an application-specific integrated circuit (ASIC) tailored to perform a particular operation disclosed herein.
  • ASIC application-specific integrated circuit
  • another example may perform the same function using a grid of several general-purpose computing devices running MAC OS System X with Motorola PowerPC processors and several specialized computing devices running proprietary hardware and operating systems.
  • the computer system 902 may be a computer system including an operating system that manages at least a portion of the hardware elements included in the computer system 902.
  • a processor or controller such as the processor 910, executes an operating system.
  • Examples of a particular operating system that may be executed include a Windows-based operating system, such as, Windows NT, Windows 2000 (Windows ME), Windows XP, Windows Vista, Windows Server, Windows 7, 8 or 10 operating systems, available from the Microsoft Corporation, a MAC OS System X operating system available from Apple Computer, one of many Linux-based operating system distributions, for example, the Enterprise Linux operating system available from Red Hat Inc., a Solaris operating system available from Sun Microsystems, or a UNIX operating systems available from various sources. Many other operating systems may be used, and examples are not limited to any particular operating system.
  • the processor 910 and operating system together define a computer platform for which application programs in high-level programming languages are written.
  • These component applications may be executable, intermediate, bytecode or interpreted code which communicates over a communication network, for example, the Internet, using a communication protocol, for example, TCP/IP.
  • aspects may be implemented using an object-oriented programming language, such as .Net, SmallTalk, Java, C++, Ada, C# (C- Sharp), Objective C, or Javascript.
  • object-oriented programming languages such as .Net, SmallTalk, Java, C++, Ada, C# (C- Sharp), Objective C, or Javascript.
  • Other object-oriented programming languages may also be used.
  • functional, scripting, or logical programming languages may be used.
  • various aspects and functions may be implemented in a non- programmed environment, for example, documents created in HTML, XML or other format that, when viewed in a window of a browser program, can render aspects of a graphical-user interface or perform other functions.
  • various examples may be implemented as programmed or non-programmed elements, or any combination thereof.
  • a web page may be implemented using HTML while a data object called from within the web page may be written in C++.
  • the examples are not limited to a specific programming language and any suitable programming language could be used.
  • the functional components disclosed herein may include a wide variety of elements, e.g., specialized hardware, executable code, data structures or data objects, that are configured to perform the functions described herein.
  • the components disclosed herein may read parameters that affect the functions performed by the components. These parameters may be physically stored in any form of suitable memory including volatile memory (such as RAM) or nonvolatile memory (such as a magnetic hard drive). In addition, the parameters may be logically stored in a propriety data structure (such as a database or file defined by a user mode application) or in a commonly shared data structure (such as an application registry that is defined by an operating system). In addition, some examples provide for both system and user interfaces that allow external entities to modify the parameters and thereby configure the behavior of the components.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Food Science & Technology (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • Biomedical Technology (AREA)
  • General Physics & Mathematics (AREA)
  • Medicinal Chemistry (AREA)
  • Pathology (AREA)
  • Molecular Biology (AREA)
  • Combustion & Propulsion (AREA)
  • Biophysics (AREA)
  • Hematology (AREA)
  • Urology & Nephrology (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

L'invention concerne des systèmes et des procédés qui adaptent des incitations ciblées à des utilisateurs à des moments optimaux afin d'aider lesdits utilisateurs à gérer des programmes et/ou des régimes, par exemple pour arrêter de fumer ou pour suivre d'autres régimes liés à la santé. Divers modes de réalisation consistent à coupler une application mobile avec des dispositifs de détection pour valider des relevés de capteur ou biométriques pris à des moments opportuns et par les utilisateurs appropriés. Le système peut adapter des informations, des incitations et diverses fonctions à des utilisateurs respectifs en fonction de connaissances dérivées de modèles d'apprentissage automatique qui analysent des données validées. Par exemple, le système peut communiquer diverses incitations en temps réel en réponse à la détection ou à la prédiction d'événements stressants et/ou de points de défaillance probables. La distribution d'incitations ciblées aux moments optimaux encourage les utilisateurs à prendre des décisions plus saines lorsqu'elles sont le plus nécessaires et fournit une fonctionnalité non disponible dans diverses approches classiques.
PCT/US2021/013024 2020-01-13 2021-01-12 Systèmes et procédés de surveillance de données et de validation de capture WO2021146156A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US202062960292P 2020-01-13 2020-01-13
US62/960,292 2020-01-13

Publications (1)

Publication Number Publication Date
WO2021146156A1 true WO2021146156A1 (fr) 2021-07-22

Family

ID=76864785

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2021/013024 WO2021146156A1 (fr) 2020-01-13 2021-01-12 Systèmes et procédés de surveillance de données et de validation de capture

Country Status (1)

Country Link
WO (1) WO2021146156A1 (fr)

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10206572B1 (en) * 2017-10-10 2019-02-19 Carrot, Inc. Systems and methods for quantification of, and prediction of smoking behavior

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10206572B1 (en) * 2017-10-10 2019-02-19 Carrot, Inc. Systems and methods for quantification of, and prediction of smoking behavior

Similar Documents

Publication Publication Date Title
US10327690B2 (en) Human-digital media interaction tracking
Smith et al. Gaze amplifies value in decision making
US9370689B2 (en) System and methods for providing dynamic integrated wellness assessment
Becker et al. Predictive modeling in e-mental health: a common language framework
Gonul et al. An expandable approach for design and personalization of digital, just-in-time adaptive interventions
US11537935B2 (en) Data processing system with machine learning engine to provide output generating functions
US11791034B2 (en) Adaptive artificial intelligence system for identifying behaviors associated with mental illness and modifying treatment plans based on emergent recognition of aberrant reactions
US20200104935A1 (en) Systems and methods for wealth and health planning
Soto et al. Observing and predicting knowledge worker stress, focus and awakeness in the wild
US20210110924A1 (en) System and method for monitoring system compliance with measures to improve system health
Engelmann et al. Top down or bottom up? Disentangling the channels of attention in risky choice
Reiter et al. Never miss a beep: Using mobile sensing to investigate (non-) compliance in experience sampling studies
WO2021003681A1 (fr) Procédé et système de test de performance neuropsychologique
WO2021146156A1 (fr) Systèmes et procédés de surveillance de données et de validation de capture
US20220051795A1 (en) Analysis system and analysis method
US20230040463A1 (en) Risk assessment and intervention platform architecture for predicting and reducing negative outcomes in clinical trials
KR102227767B1 (ko) 목표달성 시 목표의 난이도에 따른 배당률이 적용된 배당액을 지급하여 동기부여를 극대화한 다이어리 플랫폼 제공 시스템
WO2020210438A1 (fr) Système de traitement de données à moteur d'apprentissage automatique pour fournir des fonctions de génération de sortie
US20150254402A1 (en) Consumer Health Score Bureau System and Method to Facilitate a Multi-Sponsor Model of Health Improvement
Leschanowsky et al. Uncertain yet Rational-Uncertainty as an Evaluation Measure of Rational Privacy Decision-Making in Conversational AI
Pinto et al. Artificial intelligence gamified AAL solution
Zhu et al. The Promise of Just-in-Time Adaptive Interventions for Organizational Scholarship and Practice: Conceptual Development and Research Agenda
Thomas Vattukalathil Application of data analytics and machine learning on data collected by smartphones to understand human behavioural patterns
US20240112791A1 (en) Token misalignment detection and remediation device
Drosatos et al. Gambling behaviour data and modalities of persuasive interaction for enabling responsible online gambling

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21741106

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 25.10.2022)

122 Ep: pct application non-entry in european phase

Ref document number: 21741106

Country of ref document: EP

Kind code of ref document: A1