INFANT MONITORING SYSTEM AND METHODS

• US 20150094544A1
• Filed: 09/12/2014
• Published: 04/02/2015
• Est. Priority Date: 09/12/2013
• Status: Active Grant

• Current Assignee: Mattel Incorporated
• Original Assignee: Sproutling, Inc. (Mattel Incorporated)
• Inventors: Spolin, Mathew, Bruce, Christopher
• Granted Patent: US 9,277,870 B2
• Time in Patent Office: Days
• US Class Current: 600/301
• CPC Class Codes: A61B 2503/04 Babies, e.g. for SIDS detection
• CPC Class Codes: A61B 2560/0209 adapted for power saving
• CPC Class Codes: A61B 2560/0242 adapted to measure environmental factors, e.g. temperature, pollution
• CPC Class Codes: A61B 2562/00 Details of sensors; Constructional details of sensor housings or probes; Accessories for sensors
• CPC Class Codes: A61B 5/0008 Temperature signals
• CPC Class Codes: A61B 5/0022 Monitoring a patient using a global network, e.g. telephone networks, internet
• CPC Class Codes: A61B 5/01 Measuring temperature of body parts ; Diagnostic temperature sensing, e.g. for malignant or inflamed tissue clinical contact thermometers G01K13/20
• CPC Class Codes: A61B 5/0205 Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
• CPC Class Codes: A61B 5/02055 Simultaneously evaluating both cardiovascular condition and temperature
• CPC Class Codes: A61B 5/024 Detecting, measuring or recording pulse rate or heart rate A61B5/0205, A61B5/021 take precedence
• CPC Class Codes: A61B 5/02438 with portable devices, e.g. worn by the patient
• CPC Class Codes: A61B 5/02444 Details of sensor A61B5/02427 takes precedence
• CPC Class Codes: A61B 5/11 Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb for measuring pulse A61B5/02 ;A61B5/1038 takes precedence; motion detection to correct for motion artifacts in physiological signals A61B5/721
• CPC Class Codes: A61B 5/4809 Sleep detection, i.e. determining whether a subject is asleep or not
• CPC Class Codes: A61B 5/6829 Foot or ankle
• CPC Class Codes: A61B 5/6831 Straps, bands or harnesses
• CPC Class Codes: A61B 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: A61B 5/746 Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms alarms per se G08B
• CPC Class Codes: G06F 1/3206 Monitoring of events, devices or parameters that trigger a change in power modality
• CPC Class Codes: G16H 40/67 for remote operation
• CPC Class Codes: G16H 50/20 : for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/50 : for simulation or modelling of medical disorders

Abstract

One variation of a method for monitoring sleep of a user includes: assigning a collective wakefulness model—generated from sleep data collected from a set of other users—to the user for a first time period; storing a first set of vitals data collected by a wearable device worn by the user during first time period; extrapolating, from the collective wakefulness model, a first waking time of the user for a first sleep event during first time period based on data in the first set of vitals data; queuing the first waking time for transmission to a mobile computing device linked to the account for presentation to a guardian of the user; in response to expiration of the first time period, generating an individual wakefulness model specific to the user based on the first set of vitals data collected during the first time period.

Claims

1. A method for monitoring sleep of a user, comprising:

linking a wearable device to an account assigned to the user;

assigning a collective wakefulness model to the user for a first time period, the collective wakefulness model generated from sleep data collected from a set of other users;

storing a first set of vitals data collected by the wearable device worn by the user during first time period;

extrapolating, from the collective wakefulness model, a first waking time of the user for a first sleep event during first time period based on data in the first set of vitals data;

prior to the first waking time, queuing the first waking time for transmission to a mobile computing device linked to the account for presentation to a guardian of the user;

in response to expiration of the first time period, generating an individual wakefulness model specific to the user based on the first set of vitals data collected during the first time period;

assigning the individual model to the user for a second time period succeeding the first time period;

extrapolating, from the individual wakefulness model, a second waking time of the user for a second sleep event during the second time period based on a second set of vitals data received from the wearable device during the second time period; and

prior to the second waking time, queuing the second waking time for transmission to the mobile computing device for presentation to the guardian.

2. The method of claim 1, wherein assigning the collective wakefulness model to the user for the first time period comprises selecting a default collective wakefulness model for the user for the first time coinciding with a first use of the wearable device by the user.

3. The method of claim 2, wherein selecting the default collective wakefulness model for the user comprises retrieving an age of the user, correlating the age of the user with a particular development stage of the user, and selecting a default collective wakefulness model generated from sleep data collected from other users during the particular development stage.

4. The method of claim 1, wherein generating the individual wakefulness model comprises generating the individual wakefulness model specific to the user based on the first set of vitals data collected by the wearable device worn by the user and exclusive of vitals data collected from other users.

5. The method of claim 1, wherein generating the individual wakefulness model specific to the user comprises training a new wakefulness model specific to the user based on the first set of vitals data collected during the first time period and based on wakefulness states of the user during sleep events in the first time period determined from wakefulness states of other users in the set of other users.

6. The method of claim 1,

wherein assigning the collective wakefulness model for the user for the first time period comprises assigning a default collective wakefulness model to the user for a first development stage of the user;

wherein generating the individual wakefulness model comprises, in response to expiration of the first development period, generating the individual wakefulness model based on the first set of vitals data received from the wearable device during the first development stage and assigning the individual wakefulness model to the user a duration of a second development stage of the user succeeding the first development stage; and

further comprising, in response to expiration of the second development period, generating a second individual wakefulness model specific to the user based on a third set of vitals data received from the wearable device during the second development stage and assigning the second individual wakefulness model to the user for a duration of a third development stage of the user succeeding the second development stage.

7. The method of claim 6, further comprising extracting a development trend of the user from the second set of vitals data and the third set of vitals data and predicting a date of a future development event of the user based on a comparison of the development trend to a development history of an other user, the future development event selected from the group comprising:

a teething event, a rollover event, a crawling event, a walking event, and a first word event.

8. The method of claim 1, wherein storing the first set of vitals data comprises:

receiving a time series of heart rate data, a time series of skin temperature data, and a time series of motion data collected by the wearable device and routed through a base station linked to the account; and

receiving a first set of ambient condition data comprising a time series of ambient temperature data, a time series of ambient noise data, a time series of ambient light data, and a time series of ambient humidity data collected by the base station; and

storing the first set of ambient condition data with the first set of vitals data;

wherein extrapolating the first predicted waking time of the user comprises extrapolating the first predicted waking time of the user for the first sleep event further based on the first set of ambient condition data.

9. The method of claim 8, further comprising, in response to ambient noise in the time series of ambient noise data exceeding a threshold ambient noise valve, transmitting an alert to the mobile computing device.

10. The method of claim 1, further comprising extrapolating, from the individual wakefulness model, a revised second waking time of the user for the second sleep event based on a third set of vitals data received from the wearable device succeeding receipt of the second set of vitals data during the second time period.

11. The method of claim 10, wherein extrapolating the second predicted waking time of the user comprises extrapolating the second predicted waking time within a first confidence band;

and wherein extrapolating the revised second predicted waking time of the user comprises extrapolating the revised second predicted waking time within a second confidence ban narrow than the first confidence band.

12. A method for monitoring sleep of a user, comprising:

linking a wearable device to an account assigned to the user2;

selecting a collective wakefulness model for the user, the collective wakefulness model generated from sleep data collected from a set of other users;

at a first time during a sleep event of the user, extrapolating, from the collective wakefulness model, a predicted waking time of the user for the sleep event based on a first set of vitals data received from the wearable device worn by the user during the sleep event;

prior to the predicted waking time, transmitting the predicted waking time to a computing device associated with the account for presentation to a guardian of the user;

at a second time during the sleep event succeeding the first time, extrapolating, from the collective wakefulness model, a revised predicted waking time of the user for the sleep event based on a subsequent set of vitals data received from the wearable device during the sleep event; and

prior to the revised predicted waking time, transmitting the revised predicted waking time to the computing device for presentation to the guardian.

13. The method of claim 12, further comprising

storing the first set of vitals data and the subsequent set of vitals data with the account;

generating an individual wakefulness model specific to the user in response to receipt of a threshold volume of vitals data of the user over a series of sleep events and stored with the account;

extrapolating, from the individual wakefulness model, a second predicted waking time of the user for a second sleep event based on a second set of vitals data received from the wearable device worn by the user during the second sleep event succeeding the sleep event; and

prior to the second predicted waking time, transmitting the second predicted waking time to the computing device associated for presentation to the guardian.

14. The method of claim 13,

wherein selecting the collective wakefulness model for the user comprises assigning a default collective wakefulness model to the user for a duration of a first development stage of the user;

and

wherein generating the individual wakefulness model comprises generating the individual wakefulness model based on vitals data of the user received from the wearable device during the first development stage and assigning the individual wakefulness model to the user for a duration of a second development stage of the user succeeding the first development stage.

15. The method of claim 14, further comprising generating a second individual wakefulness model specific to the user based on vitals data of the user received from the wearable device during the second development stage and setting the second individual wakefulness model for application to vitals data of the user for a duration of a third development stage of the user succeeding the second development stage.

16. The method of claim 14, wherein generating the individual wakefulness model comprises generating the individual wakefulness model in response to receipt of vitals data of the user over a first duration of approximately one week;

and wherein setting the individual wakefulness model for application to vitals data of the user comprises setting the individual wakefulness model for the user for a second duration of approximately one week and immediately succeeding the first duration.

17. The method of claim 12, wherein selecting the collective wakefulness model for the user comprises associating the user with a cluster of other users in a collection of other users based on the first set of vitals data and selecting the collective wakefulness model generated from sleep data collected from users in the cluster of other users.

18. The method of claim 12, wherein extrapolating the predicted waking time of the user comprises extrapolating the predicted waking time of the user from the collective wakefulness model further based on a first set of ambient condition data received from a base station local to the wearable device and linked to the account, the first set of vitals data comprising an ambient noise level, an ambient light level, and an ambient humidity level of a space occupied by the base station during the time period, and the first set of vitals data comprising a heart rate and a skin temperature of the user during the sleep event.

19. The method of claim 18, wherein extrapolating the predicted waking time of the user comprises projecting the predicted waking time of the user based on the collective wakefulness model and a time series of ambient noise level, a time series of ambient light level, a time series of ambient humidity level, a time series of heart rate, and a time series of skin temperature collected during the first sleep event.

20. The method of claim 18, further comprising transmitting the heart rate and the skin temperature to the computing device for presentation to the guardian.

21. The method of claim 12, wherein extrapolating the predicted waking time of the user comprises extrapolating the predicted waking time within a first confidence band;

and wherein extrapolating the revised predicted waking time of the user comprises extrapolating the revised predicted waking time within a second confidence ban narrow than the first confidence band.